ChatGPT INTEGRATION PLEASE🔥🔥🔥

Fotor's NFT Creator - GoArt, Turns Your Digital Photos into NFT Artworks

That would sure be cool. Imagine being able to ask it questions in fluid English (not having to know some arcane search syntax) and get back answers like this. Then again, seminary professors, beware! This will definitely be used by students to avoid learning for themselves. We need to be sure we are not producing a next generation of seminary grads who can only parrot what AI tells them.

Jan Krohn

And Fotor AI for media generation.

I Typed the Bible Into an Artificial Intelligence Art Generator. Here's What Happened - YouTube

I don’t disagree about the ability of cutting corners, but that’s true for just about everything on the Internet. I guess it comes down to integrity.

AI is so interesting/curious to me right now. This in an interesting video.

Peter K

Yes please!!

Logos Devs - there's a way to "fine tune" ChatGPT with specific content (ex. Content purchased on Logos). I think people would pay well for an ability to chat with ChatGPT that has been fine tuned to Logos' content.

https://beta.openai.com/docs/api-reference/fine-tunes/create

Training an AI using the Logo's content and then being able to use it to perform search functions etc would be wonderful.
Moreover, being able to prioritize or limit the AI to specific resources would also be essential, and would help overcome any biases introduced to its responses if it’s sourcing material from 'everything in logos' or even everything in my own library. Personalizing the AI to each user has so much potential.

You mean I shouldn't be able to ask "How did those bl....dy heretics/schismatics get it so wrong about nnnn?" just because each of us mean a different group by heretics/schismatics/pagans?

Hahaha - well if the AI is on my side then I must be right!

This would be great!

Mark Barnes (Logos)

Like most other forward-thinking tech companies, we're very engaged in thinking about how AI could improve our products and following all the advances closely. However, it's fair to say that while there have been many very impressive demos, OpenAI and others are still a long way off being able to offer reliable ChatGPT integration to companies like Faithlife, a very long way off from making that affordable, and a very, very long way off making it possible to customize for individuals.

So we can expect something in the beta for v24 then? Thanks Mark!! 😜

I'm sure there are also ethical concerns with how people like preachers and students would be tempted to use AI for their writing. A lot of people's sermons already sound like they could have been just as easily written by chatbots (smh). And we already have proven instances of preachers and scholars plagiarizing. Seems like AI is about to make things even worse.

But I'm all for a customized AI experience for Logos at what ever point that becomes technologically and financially feasible. The cheaters are going to find a way to cheat regardless. Faithlife just has to protect itself from liability for any user wrongdoing. Expect updated terms and conditions whenever Faithlife implements AI lol.

Simon’s Brother

I am not convinced such technology is a good idea in a product Logos, it all comes down to how it was implemented. I want Logos to be able to better point me to resources that are more relevant to what I am studying, but I don‘t want AI replacing the development of my own learning, reading and critical thinking skills. As it is today most people rely on translations and secondary sources as we don’t know the languages the primary sources were written. To then have AI to replace our need to even read the translations and secondary sources and eliminate the joy of discovery and need for us to think for ourselves, I’m not in favour of such a direction for Logos Bible Software.

I don’t believe this is the intent of Brandon‘s suggestion just putting out my 2 cents.

I am not convinced such technology is a good idea in a product Logos, it all comes down to how it was implemented. I want Logos to be able to better point me to resources that are more relevant to what I am studying, but I don‘t want AI replacing the development of my own learning, reading and critical thinking skills. As it is today most people rely on translations and secondary sources as we don’t know the languages the primary sources were written. To then have AI to replace our need to even read the translations and secondary sources and eliminate the joy of discovery and need for us to think for ourselves, I’m not in favour of such a direction for Logos Bible Software.

I don’t believe this is the intent of Brandon‘s suggestion just putting out my 2 cents.

I would be in favor of them using AI to make Faithlife Assistant work better, such as finding information using the resources in my library to answer questions, changing settings, executing commands, suggesting books and articles from my library, or even teaching me how to use a feature in Logos. It would help with accessibility as well. But they shouldn't implement it in a way that it writes sermons and papers for you, which people are demo-ing in YouTube videos right now.

I would be in favor of them using AI to make Faithlife Assistant work better, such as finding information using the resources in my library to answer questions, changing settings, executing commands, suggesting books and articles from my library, or even teaching me how to use a feature in Logos. It would help with accessibility as well. But they shouldn't implement it in a way that it writes sermons and papers for you, which people are demo-ing in YouTube videos right now.

This. This is how I imagine AI could be most helpfully integrated into Logos in a responsible way.

The whole reason we have Bible Software in the first place is to make the work of ministry easier and faster. Physically searching for a word in BDAG while exegeting a passage takes 2 minutes, but it only takes a few seconds in Logos. Physically searching my college library while researching for an essay can take hours, with Logos it is minutes. If AI implementation into logos continues to improve upon the speed at which I can access or process data then I'm all for it. Time saved here behind the scenes allows me more time to speak with people, share the gospel, pray etc.

But getting AI to write sermons or essays for me which I pass off as my own.? Yeah nah that's a hard pass. The work of ministry is the application of the gospel to the lives and hearts of people - I can do that because I know my people, an AI doesn't.

Simon’s Brother

I have no issue with the finding of information, it’s AI doing the work I should be doing myself as someine created in the image of God with the ability to reason and think for myself. I should be coming prayerfully before God and seeking the guidance of the Holy Spirit rather than an asking a AI to take the place of my reliance upon the Holy Spirit.

I am not convinced such technology is a good idea in a product Logos, it all comes down to how it was implemented. I want Logos to be able to better point me to resources that are more relevant to what I am studying, but I don‘t want AI replacing the development of my own learning, reading and critical thinking skills. As it is today most people rely on translations and secondary sources as we don’t know the languages the primary sources were written. To then have AI to replace our need to even read the translations and secondary sources and eliminate the joy of discovery and need for us to think for ourselves, I’m not in favour of such a direction for Logos Bible Software.

I don’t believe this is the intent of Brandon‘s suggestion just putting out my 2 cents.

I would be in favor of them using AI to make Faithlife Assistant work better, such as finding information using the resources in my library to answer questions, changing settings, executing commands, suggesting books and articles from my library, or even teaching me how to use a feature in Logos. It would help with accessibility as well. But they shouldn't implement it in a way that it writes sermons and papers for you, which people are demo-ing in YouTube videos right now.

Fábio Silva

Fair enough, and well done for addressing this directly. Cost wise you could alway offer on the side a subscription based model (faithlife assistant premium 😁)... Like any other technology innovation prices start high but then tends to drop massively, if the only thin holding this back would be coat I'm sure some of us would be willing to front that cost (within reason).

I'm not going to pretend that I know enough about the other issues raised, but makes sense seeing that this technology is still in its infancy. Again I guess it's a matter of time for those issues to resolved/polished, and am glad that you guys have it on the radar.

Logos 11 maybe?😁😁😁 "Bible study taken to the AI-xtreme with Logos 11" (might or might not have been created by chat GPT)

That would sure be cool. Imagine being able to ask it questions in fluid English (not having to know some arcane search syntax) and get back answers like this. Then again, seminary professors, beware! This will definitely be used by students to avoid learning for themselves. We need to be sure we are not producing a next generation of seminary grads who can only parrot what AI tells them.

I'm with you on this AI search thingy .... Then we add voice to that and bidda bang!!! Less typing!!!! Dr. Spock lives again!!!

I see it now..... "Logos... find the answer to who Cains wife was?" Seriously... I think AI would help Search. [8-|]

I'm with you on this AI search thingy .... Then we add voice to that and bidda bang!!! Less typing!!!! Dr. Spock lives again!!!

I see it now..... "Logos... find the answer to who Cains wife was?" Seriously... I think AI would help Search.

I remember a day around 30 years ago, when I was driving to work, and had time to reflect on what would make my life easier. At the time I used to use a hand-held mini tape recorder to record messages/reminders to myself (e.g, remember to schedule appointment with..., etc.), and I kept it on the passenger's seat whenever I was driving, as that's when those ideas would pop into my head.

I was thinking how cool it would be if there were a digital assistant that you could talk to, ask it questions and have it do stuff for you, hands free. You could ask it complicated requests like: "look into flights from Seattle to Boston for approximately Feb 17-22 and let me know the best options, and then book the one I choose."

Well, fast forward a few decades, and now there's Siri. And now ChatGPT is taking the AI up a notch. We are almost at that vision I had of the smart digital assistant. ChatGPT needs voice recognition and needs to have access to up-to-the-minute info, and integration with the mobile apps that Siri can control, and then we're there. It's not that far off: maybe 3-5 years.

I imagine I'd want to use it in Logos to do manual tasks for me, like look up all the books I've bought over the years that I haven't tagged yet, and tag them according to these rules: ... (An AI could scan through the content of a book and figure out if it has to do with any of your topic tags, such as some of mine: Arts, Poetry, Film, Science, Sermons, Hymns, etc. It could learn my tagging habits and keep up with them when I fall behind.)

lol. I had a mini tape recorder that I carried with me also.... and then when I got to the office....I gave it to my secretary.... she was like a digital helper! "Julie... get me a red eye to IAH for the 29th coming back on the 8th." and bingo.... it was done!

I think it will happen with digital things. It seems logical that it's the next big step. I do see a cavity in all this.... that of making bible study mundane and thus people doing less of it.... I don't mind helps.... but nothing can take the place of human study. And as to God's word.... I think people are dumb enough already... OMHO [8-|]

Doc B

and get back answers like this

So where can I find a teenager (or the equivalent) to show me how to install and set up this thing on my computer? It looks like a heck of a lot of fun.

New York rabbi delivers sermon written by artificial intelligence

and get back answers like this

So where can I find a teenager (or the equivalent) to show me how to install and set up this thing on my computer? It looks like a heck of a lot of fun.

You don't need to install anything. You go to https://chat.openai.com/chat and set up an account. Then just type your question into the box at the bottom of the screen.

Occasionally you might get a message saying ChatGPT is overloaded and you'll have to try again some other time. But they've been working at scaling it up to be able to handle the higher load with all the recent interest in it. Also occasionally you might have to refresh the browser tab (F5 on Windows) if you've been inactive for a while and come back to try another chat.

All, in all, it's been very educational playing with it for the past couple of weeks. I'm finding what its limitations are (and there are many). But I'm also impressed at how much it can do.

There are all kinds of interesting ethical discussions taking place about this new technology. I wanted to understand it so that I could engage thoughtfully, in a theologically informed way, in such discussions.

I'll leave you with this intriguing article from the Jewish Chronicle:

And this one in Church Today:

Is Artificial Intelligence the Solution For Helping Church Staff?

I love reading all these ideas. I hope Logos is seeing and asking, “How can we…”

I have asked ChatGPT to write a sermon based on the passage, or to write an outline based on the passage, and it does a good job of giving you the surface level premise, but there’s nothing dynamic.

I think it’s a great selling point to note that the larger your library, the smarter (or more options) the AI would be. We have factbook and fuzzy search, very helpful, this would move in that direction and be an incredibly helpful tool.

Sometimes I just don’t know how to properly search all of my resources, this would be a game changer in research and preparation.

I love reading all these ideas. I hope Logos is seeing and asking, “How can we…”

Sometimes I just don’t know how to properly search all of my resources, this would be a game changer in research and preparation.

Nick Lees

I love this idea and totally agree. This would be invaluable. I have so many resources available to me in Logos that there is no easy way to reliably survey them all. But an AI assistant could help synthesize things!

But an AI assistant could help synthesize things!

I appear to be in the extreme minority -- I have not been impressed by ChatGPT and the more I play with it the more unimpressed I get. Why? specifically because it doesn't appear to do much synthesizing - it parrots back from limited, general source. Even when you prompt it to get details, it "forgets" those details in subsequent answers. And it is comfortable using out-of-date resources e.g. when I was asking about percentages of church memberships it decided 2011 Pew data was the gold standard. I do find it very useful when I have forgotten a detail or to find translations of obscure works ... i.e. when I want information that requires no thought, it is good and finding it and feeding it back to me.

Another example of its lack of consistency:

[quote]

What extinct Central Asian languages have Christian texts?

There are several extinct Central Asian languages that have Christian texts, including:

Sogdian: Sogdian was an Iranian language spoken in Central Asia in the medieval period, and it has a rich corpus of literature, including both secular and religious texts. While Sogdian was primarily a Zoroastrian language, there is evidence of Christian influence in some Sogdian texts. For example, there are translations of parts of the New Testament into Sogdian, as well as hymns and other Christian religious texts.
Khotanese: Khotanese was an extinct Indo-Iranian language spoken in the Tarim Basin in present-day Xinjiang, China. While there is no evidence of Christian literature in Khotanese, it is known for its Buddhist and Manichaean texts.
Bactrian: Bactrian was an Iranian language spoken in ancient Bactria, which roughly corresponds to modern-day Afghanistan. There is evidence of Christian influence in some Bactrian texts, including a Christian epitaph from a tomb in northern Afghanistan.
Chorasmian: Chorasmian was an extinct Iranian language spoken in the region of Khwarezm, which is located in modern-day Uzbekistan, Turkmenistan, and Kazakhstan. While there is no evidence of Christian literature in Chorasmian, it is known for its use in Zoroastrian religious texts.
Old Uighur: Old Uighur was a Turkic language spoken in the Tarim Basin in the medieval period. While there is no evidence of Christian literature in Old Uighur, it is known for its Buddhist and Manichaean texts.

I thought Old Uighur texts consisted of a single stele.

Old Uighur is a medieval Turkic language that was spoken in the Tarim Basin in present-day Xinjiang, China. While it is true that the most famous Old Uighur text is the "Old Turkic Inscription," also known as the Orkhon Inscription, which is a runic inscription on a stone monument dating back to the 8th century, there are also other Old Uighur manuscripts that have been discovered.

In fact, there is a significant corpus of Old Uighur literature, including Buddhist, Manichaean, and Nestorian Christian texts, in addition to secular works such as administrative documents, letters, and legal texts. These manuscripts were discovered in the Dunhuang Caves, a complex of Buddhist temples and cave shrines in Gansu Province, China, and other locations in the Tarim Basin.

The Nestorian Christian texts in Old Uighur include fragments of the Bible, liturgical texts, and other religious works, and they offer insights into the history of Christianity in Central Asia during the medieval period. These Old Uighur Christian texts also demonstrate the cosmopolitan nature of the Silk Road, which facilitated the exchange of religious ideas and cultural influences across Eurasia.

Mark

I appear to be in the extreme minority -- I have not been impressed by ChatGPT

AI is very new and exciting to people. I think people on this thread are thinking of its possibilities. In the next few years, I suppose AI will be much better. And Faithlife hopefully (in the background) is beginning to think about its potential to enhance or destroy their software.

And Faithlife hopefully (in the background) is beginning to think about its potential to enhance or destroy their software.

I believe they are already using some AI - most natural language processing includes AI components and some of their tagging implies at least AI assisted tagging. In the documentation of datasets the word "training" is a give away of AI processing.

Lew Worthington

I appear to be in the extreme minority -- I have not been impressed by ChatGPT

AI is very new and exciting to people. I think people on this thread are thinking of its possibilities. In the next few years, I suppose AI will be much better. And Faithlife hopefully (in the background) is beginning to think about its potential to enhance or destroy their software.

I am also unimpressed, but the future possibilities are intriguing. To revert to the chess comparison, in the late 1960s, the English International Master, David Levy made a bet that no chess computer could beat him within 10 years. There is now no human player that could come close to the playing strength of the AI beast we can put in our pocket. It will be interesting to see what develops over the next couple decades, but I am much more comfortable understanding and negotiating when I understand another person's opinion, and how their (and my) self-interest lies behind their (and my) judgments in theology or whatever. While chess is technically definable in completely objective terms (although perhaps an SSD the size of the universe could not contain a database of all possible games), it is possible that human interactions with God -- and indeed, how to talk about human interactions with God -- are not so mathematical.

But concepts like "convincing arguments" could be statistically compared, so is it conceivable that an AI program similar to Alpha Zero could be tuned based on human responses to their arguments? And doesn't this open up stuff about the discussion of the Holy Spirit's part in wooing human hearts based on the words that someone says? If nothing else, it may force us to refine our language when we talk about passages like 1 Thes 1:5, 1 Cor 2:1, and 2 Tim 1:7.

It all seems weird to think about now and maybe scoff at such a notion, but I already regularly phrase emails written on my phone using the suggested phrase because it's easier than typing out precisely what I would've said otherwise.

And yet, I can see huge value in all of this. But like any technological advancement, I hope we can be discerning in its use, something humanity has not demonstrated in the past.

2. Why doesn't ChatGPT know about X?

Anyone attempting to use the current ChatGPT model should be aware of its (many) limitations.

Please, please, please read the information about its limitations on OpenAI's website so you know what ChatGPT can and cannot do.

[quote]

Limitations

ChatGPT sometimes writes plausible-sounding but incorrect or nonsensical answers. Fixing this issue is challenging, as: (1) during RL training, there’s currently no source of truth; (2) training the model to be more cautious causes it to decline questions that it can answer correctly; and (3) supervised training misleads the model because the ideal answer depends on what the model knows, rather than what the human demonstrator knows.
ChatGPT is sensitive to tweaks to the input phrasing or attempting the same prompt multiple times. For example, given one phrasing of a question, the model can claim to not know the answer, but given a slight rephrase, can answer correctly.
The model is often excessively verbose and overuses certain phrases, such as restating that it’s a language model trained by OpenAI. These issues arise from biases in the training data (trainers prefer longer answers that look more comprehensive) and well-known over-optimization issues.12
Ideally, the model would ask clarifying questions when the user provided an ambiguous query. Instead, our current models usually guess what the user intended.
While we’ve made efforts to make the model refuse inappropriate requests, it will sometimes respond to harmful instructions or exhibit biased behavior. We’re using the Moderation API to warn or block certain types of unsafe content, but we expect it to have some false negatives and positives for now. We’re eager to collect user feedback to aid our ongoing work to improve this system.

See also these blog posts from ChatGPT:

1. ChatGPT General FAQ

3. Does ChatGPT remember what happened earlier in the conversation?

4. ChatGPT emails, links and other actions - Here's an excerpt from this post:

[quote]

One of the main challenges of ChatGPT is that it predicts feasible responses, which look like reasonable text but may not always be true. This means that ChatGPT may not always give you accurate or reliable information, and may even contradict itself.

...

...you may ask ChatGPT to look up some facts or data (e.g. the capital of a country or the weather forecast) and it may respond with plausible but incorrect answers. ChatGPT does not have access to any external sources of information or knowledge, and it may rely on its own memory or guesswork to generate responses.

It may also confuse or mix up different topics or domains, or repeat or contradict itself over time. Therefore, you should always verify any information or claims that ChatGPT makes with other sources, and do not rely on it for any critical or sensitive decisions or actions. ChatGPT is not a substitute for human judgment, expertise, or responsibility.

ChatGPT is a fascinating and innovative tool that can help you explore the possibilities and challenges of natural language generation and interaction. However, you should also use it responsibly and realistically, and remember that it is not a human, a machine, or a magic wand, but a complex and creative language model.

5. ChatGPT — Release Notes

I'm posting this because it seems like a lot of people are attempting to use ChatGPT without reading this info, and thus seem to be unaware of its limitations or have unrealistic expectations of the model. It's not even connecting to the internet to look up information. It only knows what was loaded into the model as of 2021, it's no longer being trained, and it doesn't know what it doesn't know, but it's programmed to give a guess at a response rather than tell the user it doesn't know something. It also can only keep track of conversations up to a certain number of characters so it can't remember a whole conversation that you have with it over a certain length.

So far I've only found ChatGPT useful for brainstorming, thought-starting, and thought-organizing purposes. It can help you start a task if you're blocked and having trouble getting started. It can help you get ideas for what you should be researching yourself using reputable, reliable sources. You can't trust it for accurate information at all. This opinion is specifically about the current version of ChatGPT and not about the potential of AI in general.

Factbook is nice. But if you could somehow introduce and integrate Open AI ChatGPT in to Logos.
I would love it if Logos better understood the resources I own and become better at answering questions based on the resources I own.

This would be INCREDIBLY valuable for the user.
AND become a BIG reason to purchase more resources.

Couldn't agree more!

Many moons ago... it was rumored that TV would put church buildings extinct.

I think OpenAI ChatGPT could enhance things like Factbook and Search and some others greatly. Hope it becomes a reality.

Adam Roe

I agree with the OP, and would encourage Logos to get on this quickly. I am able to create Bible Studies in 10 minutes with ChatGPT. Bring that technology to Logos and I'm buying a lot more resources because I trust the resources. With ChatGPT I still have to do some fact checking, though I've not yet run into any issues.

I find it amazing that users are so quick to adopt a tool that provides garbage answers and admits that it provides garbage answers. Doesn't that imply uncritical reading? Having dated 30 year ago, a man who made some major contributions to AI, I know some of the areas in which AI has and can make very significant contributions. I would suggest that Logos needs to apply AI to argument tracing and unstated assumptions before even thinking about letting AI synthesize information - what Chat GPT does poorly.

Don't get me wrong ChatGPT has made some very serious progress on the conversational interface and the awareness of a thread of queries. However, by carefully choosing your questions you can get brilliant answers, or laughable answers, or anything in between.

An example of ChatGPT being very useful in building a bibliography - asking it to parrot back information that is unambiguous is its forte. Early Christian Literature in Lesser Known Languages (logos.com)

Adam Roe

I don't know how everyone else is using ChatGPT, but I've received consistently solid, reliable results. Certainly, there are challenges to integration, but they're obstacles worth overcoming, in my opinion.

I don't know how everyone else is using ChatGPT, but I've received consistently solid, reliable results. Certainly, there are challenges to integration, but they're obstacles worth overcoming, in my opinion.

I've received some shockingly wrong results. There was one where it was wantonly making up random quotes that it said where in poems by well-known poets, but they were not.

And this was the latest bunch of nonsense it came up with:

I really urge people to be careful and do their own homework rather than relying entirely on ChatGPT for answers. You have to know enough about a topic (or know how to find out about it through other means) in order to fact-check ChatGPT. It took me quite a bit of time to do the fact-checking above. I really worry about when people don't have the time to fact-check, because they are using ChatGPT to save time. That's when misinformation will be passed off on others as truth.

https://community.logos.com/forums/p/213793/1246002.aspx#1246002

I don't know how everyone else is using ChatGPT, but I've received consistently solid, reliable results. Certainly, there are challenges to integration, but they're obstacles worth overcoming, in my opinion.

See also this thread about some of the problems with ChatGPT inventing fake bibliographical data for books that don't exist:

Again, I absolutely would not rely on ChatGPT for factual information, not at all. I would only use it for brainstorming purposes. It's like having a conversation partner that doesn't really know that much but is really intelligent sounding. You have to be an expert on what you're asking it because it gives very plausible sounding but incorrect information. You may think it's giving you solid results but you may just not have caught the mistakes.

It's a natural language model, not a research assistant. That's why it can give such good-sounding answers but still be woefully wrong and contradictory. If the makers of ChatGPT themselves say that it can't be trusted for factual, reliable information, you should probably believe them.

David R. McAllan

Factbook is nice. But if you could somehow introduce and integrate Open AI ChatGPT in to Logos.
I would love it if Logos better understood the resources I own and become better at answering questions based on the resources I own.

This would be INCREDIBLY valuable for the user.
AND become a BIG reason to purchase more resources.

Oh, how this will make me lazy!

A Reformed

No, please, no. No, just, please, no. NNNNNNNOOOOOOOOOOOOOOOOOOOOO!!!!!!!!!!

Jimmy Duran

Nithin Thompson

yes. Agreed!

For those who've been watching my use of ChatGPT (Why did Lexham Include 1 Enoch in their English LXX? - Logos Forums and ChatGPT workflow - see AI at work (and pick up a little Bible interpretation methodology along the way) - Logos Forums), the more I use it, the more I don't want it integrated. Like Google, having it available on the side is sufficient and avoids the support problems that its answers and their interpretation would cause.

Doc B

the more I use it, the more I don't want it integrated

I'm arriving at the same conclusion for similar reasons (along with speed as well...no way it would 'speed up' Logos).

I will use it as a adjunct but I don't want it integrated unless some big changes are made.

J. Remington Bowling

The first point, regarding the fabricated quote, seems to me like a good reason in favor of Logos integration. Allowing the model(s) to consult Logos resources through the plugin API or fine tuning would make such "hallucinations" less likely. Ultimately, if we want LLMs to provide accurate information (especially when it comes to more niche domains), it needs to have access to it.

This is why I'm not persuaded by the argument that LLMs hallucinate and, therefore, we shouldn't want Logos integration. One way or another, LLMs will need to be exposed to the information if we expect greater accuracy. As I think I mentioned before, there also needs to be a reasonable expectation for what sort of accuracy is possible or should be demanded.

Regarding support problems. Since OpenAI, Google, and Microsoft all provide warnings at the various points of entry about things like hallucinations, people caught off guard by it bear some of the responsibility themselves. And I would expect a similar warning from FaithLife if it integrates (which seems inevitable at this point, whether it be 1 year or 5 years from now).

The concern that Logos will slow or halt progress on other areas, at least temporarily, is completely legitimate if we are convinced that these other things are more pressing. But that's probably a hard thing to poll their market on.

(I tried downloading the workflow, but I'm not sure how it's supposed to work... I've never used the workflow feature before.)

I'm arriving at the same conclusion for similar reasons (along with speed as well...no way it would 'speed up' Logos).

If we are talking about the plugin API, my guess is that it most likely wouldn't have any noticeable impact on your local install. It would probably just be querying FaithLife's servers? If we are talking about fine-tuning, that is done by OpenAI's servers. The wait-time you're looking at would mostly just be network traffic I imagine. But maybe I'm wrong.

The first point, regarding the fabricated quote,

The "proposed fabricated quote" ... I am unconvinced it is anything other than a post aging out of the web.

Adam

I agree, I'm loving all these ideas as well! This would be such an enhancement - honestly beyond our imagination. I wonder... maybe we can ask ChatGPT how to integrate ChatGPT into the logos bible software to get some ideas to share and help out the company...

how to integrate ChatGPT into the logos bible software

Welcome to the forums, Adam. Integrating ChatGPT and training ChatGPT are things that any IT specialist who understands AI systems can do. That it not where the "uniqueness" of ChatGPT lies. I think many Logos users would appreciate having a more conversational interface to our resources which is what ChatGPT provides. But it is not designed to be customized at the user level, meaning what we have in our library would not determine the answers we see. We couldn't hide books we think are garbage - if they were included in the training, their view point would still be represented. So to integrate:

Step 1: Get the Logos users to agree on a very large corpus of books that are deemed to be accurate.

Step 2: Train ChatGPT on that corpus

Step 3: Get all Logos users to agree that answers from ChatGPT to questions such as "What does the Bible say about the necessity of baptism" are correct.

Step 4: Realize that ain't gonna happen. Limit ChatGPT to questions such as "What does Ephrem the Syrian say about the necessity of baptism?"

Step 5: Realize much of the agreed upon corpus is not discursive. Limit ChatGPT to questions such as "What does a 5 point Calvinist say about the necessity of baptism?" and "What does a 4 point Calvinist say about the necessity of baptism?" and "What does a 3 point Calvinist say about the necessity of baptism?" and "What does a 2 point Calvinist say about the necessity of baptism?" and "What does a 1 point Calvinist say about the necessity of baptism?"

Step 6: Realize that the core issue the users want is access to raw data, information that confirms their current beliefs, and material based on the logic of belief revision to convince others that their current beliefs are correct. Yes, there is also a subset of users who are interested in the array of positions taken on issues (from grammar to theology), who promoted them, when they were prevalent, and available written records of those positions. Ask oneself two questions: 1. What kind of AI fits best with what the users actually want? 2. What is it about ChatGPT that makes users think it is the solution?

Step 7: Recognize that it is best to seek out the best solution for the problems that exist rather than seeking the best problem for a preselected solution. I suspect but have no intention of doing the survey and statistical analysis to prove it, that people are impressed by Chat GPT's conversational tone and memory of past questions in the conversation. Put those elements in the specifications for providing users with the data they want. Then go out and research what flavor of AI best suits the problem. Given the differences in the appropriate logics used, I suspect the answer is not ChatGPT.

Step 8: Recognize has Faithlife already applied artificial intelligence and training to develop some of the tools that are already available to us. Look for the key wording "train" in the documentation as opposed to "curate". Recognize that the surveys re:L9 before the specs for L10 were developed, did not put (re)development of Faithlife Assistant (conversational access to data) high on the list. If you think it should have been, vote for it, push for it but trust FL professionals to select the appropriate tools for the issue and within their budget.

how to integrate ChatGPT into the logos bible software

Step 1: Get the Logos users to agree on a very large corpus of books that are deemed to be accurate.

Step 2: Train ChatGPT on that corpus

Step 3: Get all Logos users to agree that answers from ChatGPT to questions such as "What does the Bible say about the necessity of baptism" are correct.

Step 4: Realize that ain't gonna happen. Limit ChatGPT to questions such as "What does Ephrem the Syrian say about the necessity of baptism?"

Step 5: Realize much of the agreed upon corpus is not discursive. Limit ChatGPT to questions such as "What does a 5 point Calvinist say about the necessity of baptism?" and "What does a 4 point Calvinist say about the necessity of baptism?" and "What does a 3 point Calvinist say about the necessity of baptism?" and "What does a 2 point Calvinist say about the necessity of baptism?" and "What does a 1 point Calvinist say about the necessity of baptism?"

Step 6: Realize that the core issue the users want is access to raw data, information that confirms their current beliefs, and material based on the logic of belief revision to convince others that their current beliefs are correct. Yes, there is also a subset of users who are interested in the array of positions taken on issues (from grammar to theology), who promoted them, when they were prevalent, and available written records of those positions. Ask oneself two questions: 1. What kind of AI fits best with what the users actually want? 2. What is it about ChatGPT that makes users think it is the solution?

Step 7: Recognize that it is best to seek out the best solution for the problems that exist rather than seeking the best problem for a preselected solution. I suspect but have no intention of doing the survey and statistical analysis to prove it, that people are impressed by Chat GPT's conversational tone and memory of past questions in the conversation. Put those elements in the specifications for providing users with the data they want. Then go out and research what flavor of AI best suits the problem. Given the differences in the appropriate logics used, I suspect the answer is not ChatGPT.

Step 8: Recognize has Faithlife already applied artificial intelligence and training to develop some of the tools that are already available to us. Look for the key wording "train" in the documentation as opposed to "curate". Recognize that the surveys re:L9 before the specs for L10 were developed, did not put (re)development of Faithlife Assistant (conversational access to data) high on the list. If you think it should have been, votes for it, push for it but trust FL professionals to select the appropriate tools for the issue and within their budget.

I'm a thinking that's a tall, tall glass of water! [8-|]

Adam

how to integrate ChatGPT into the logos bible software

Welcome to the forums, Adam. Integrating ChatGPT and training ChatGPT are things that any IT specialist who understands AI systems can do. That it not where the "uniqueness" of ChatGPT lies. I think many Logos users would appreciate having a more conversational interface to our resources which is what ChatGPT provides. But it is not designed to be customized at the user level, meaning what we have in our library would not determine the answers we see. We couldn't hide books we think are garbage - if they were included in the training, their view point would still be represented. So to integrate:

Step 1: Get the Logos users to agree on a very large corpus of books that are deemed to be accurate.

Step 2: Train ChatGPT on that corpus

Step 3: Get all Logos users to agree that answers from ChatGPT to questions such as "What does the Bible say about the necessity of baptism" are correct.

Step 4: Realize that ain't gonna happen. Limit ChatGPT to questions such as "What does Ephrem the Syrian say about the necessity of baptism?"

Step 5: Realize much of the agreed upon corpus is not discursive. Limit ChatGPT to questions such as "What does a 5 point Calvinist say about the necessity of baptism?" and "What does a 4 point Calvinist say about the necessity of baptism?" and "What does a 3 point Calvinist say about the necessity of baptism?" and "What does a 2 point Calvinist say about the necessity of baptism?" and "What does a 1 point Calvinist say about the necessity of baptism?"

Step 6: Realize that the core issue the users want is access to raw data, information that confirms their current beliefs, and material based on the logic of belief revision to convince others that their current beliefs are correct. Yes, there is also a subset of users who are interested in the array of positions taken on issues (from grammar to theology), who promoted them, when they were prevalent, and available written records of those positions. Ask oneself two questions: 1. What kind of AI fits best with what the users actually want? 2. What is it about ChatGPT that makes users think it is the solution?

Step 7: Recognize that it is best to seek out the best solution for the problems that exist rather than seeking the best problem for a preselected solution. I suspect but have no intention of doing the survey and statistical analysis to prove it, that people are impressed by Chat GPT's conversational tone and memory of past questions in the conversation. Put those elements in the specifications for providing users with the data they want. Then go out and research what flavor of AI best suits the problem. Given the differences in the appropriate logics used, I suspect the answer is not ChatGPT.

Step 8: Recognize has Faithlife already applied artificial intelligence and training to develop some of the tools that are already available to us. Look for the key wording "train" in the documentation as opposed to "curate". Recognize that the surveys re:L9 before the specs for L10 were developed, did not put (re)development of Faithlife Assistant (conversational access to data) high on the list. If you think it should have been, vote for it, push for it but trust FL professionals to select the appropriate tools for the issue and within their budget.

I must admit I didn't think about that complication - the issue of interpretation. My mind was more geared towards objective research practicality which GPT functions well for even outside of Logos or Verbum. So I guess i will concede that that is something that does need to be considered as being a hurdle that needs to be figured out. However, there does seem to be a fix for it by using the program as it is right now. For instance, for a Catholic, I can restrict the sources that Chat GPT is using to provide the answers to my questions. Meaning that GPT can only use the Bible, the Catechism, Papal encyclicals, etc. and i can also set the persona of ChatGPT to be a Catholic Theologian. So i would imagine that this can also be done for various protestant users that wish to have their sources tailored to their particular religion so they dont receive skewed results.

In terms of implementation into Verbum or Logos, after going through some classes on GPT it seems as though individually implementing it into Verbum/logos may really not be as complicated as we think. If a company can use the API of ChatGPT for their own personal chatbots on their site with tailored company information being used as its knowledge base, then its really not far fetched to have it on a personal level tailored to whats in our libraries.

Quite frankly we all know that this is the future. We can argue against it, but thats not going to make this AI breakthrough technology go away. This is massive and its progressing very fast. The question really is not if but when will logos and verbum provide this technology for their customer base. If they move too slow another company may beat them to the race.

J. Remington Bowling

I agree, I'm loving all these ideas as well! This would be such an enhancement - honestly beyond our imagination. I wonder... maybe we can ask ChatGPT how to integrate ChatGPT into the logos bible software to get some ideas to share and help out the company...

Most likely won't have been exposed to enough information about Logos to give any helpful (or factual) feedback. The plugin route that is still in beta stage seems like the path of least resistance. It could also leave the integration as something you're only engaged in outside of the Logos app, as some have requested.

Zach Nerison

[H] YES

The law of the handicap of a head start (original Dutch: Wet van de remmende voorsprong), first-mover disadvantage, or dialectics of lead, is a theory that suggests that an initial head start in a given area may result in a handicap in the long term.
The lesson that Blackberry learned.

Logos,

you integrate AI by catching up FAST or you could be obsolete. No time for lunch breaks.

But I will still use Logos, with or without AI, because I paid big bucks for this.

I'm using Google Bard to search for things Logos Factbook doesn't do for me because I lack some resources. Google Bard is fast and easy to use. I've been told that it searches academic resources even in Brill database and others.
Logos is giving me some headache in searching for things. I was looking for cults in the city of Thessalonians. I ask Bard to compare the concept of resurrection of Christian belief with that of Greek religion.

This gave me quick insights and with that I could search within Logos further.

Adam

Very interesting, I haven’t experimented too much with google bard, but I love all the opportunities that chatgpt is opening up and how easy it is to learn things through the software. Does google bard provide footnotes or sources? I’ve become very familiar with inputting prompts for chatgpt that restrict what resources it will acquire its answers from, but does google bard do this? of course all this technology is still very much in the early phases. Exciting years to come!

Me asking Google Bard: Can you use an exegetical guide of Logos Bible software to analyse Colossians 2:12?

Google Bard:

Sure. Here is an exegetical analysis of Colossians 2:12 using the Logos Bible software exegetical guide:

Context

Colossians 2:12 is part of a larger section of the letter (Colossians 2:6-15) in which Paul is responding to the false teaching that was present in the Colossian church. This false teaching was based on Jewish legalism and on Greek philosophy. Paul is arguing that the Colossians do not need to follow these false teachings because they have been united with Christ.

Grammar

The Greek word for "buried" in Colossians 2:12 is ἐτάφη (etaphe), which is the aorist passive participle of the verb ἐτάφω (etafō). The aorist passive participle indicates that the action of the verb was completed in the past and that the subject of the verb was acted upon by an unspecified agent. In this case, the unspecified agent is God.

The Greek word for "raised" in Colossians 2:12 is ἠναστήθη (anastēthē), which is the aorist passive participle of the verb ἀναστήσῃ (anastēsō). The aorist passive participle indicates that the action of the verb was completed in the past and that the subject of the verb was acted upon by an unspecified agent. In this case, the unspecified agent is God.

Word Study

The Greek word for "buried" (ἐτάφη) can also be translated as "entombed" or "interred." The Greek word for "raised" (ἠναστήθη) can also be translated as "resurrected" or "raised from the dead."

Exegesis

In Colossians 2:12, Paul is using the imagery of baptism to describe the Christian's new life in Christ. He says that when we are baptized, we are buried with Christ in his death and raised with him to new life. This is a powerful image of the transformation that takes place when we come to faith in Christ.

In the ancient world, baptism was often used as a symbol of death and rebirth. When someone was baptized, they would be submerged in water, which was seen as a symbol of death. When they were raised from the water, they were seen as being reborn into a new life.

Paul is using this imagery to describe the Christian's new life in Christ. When we come to faith in Christ, we are forgiven of our sins and we are given a new life. We are no longer slaves to sin, but we are free to live for God.

Application

The application of Colossians 2:12 is that baptism is a symbol of the Christian's new life in Christ. It is a reminder that we have been forgiven of our sins and that we are free to live for God.

Baptism is also a reminder of our union with Christ. When we are baptized, we are united with Christ in his death and resurrection. This means that we share in his victory over sin and death.

Baptism is a powerful symbol of the Christian's new life in Christ. It is a reminder of our forgiveness, our freedom, and our union with Christ.

https://www.foxnews.com/tech/hear-good-sunday-sermon-ai-ready-make-preachers-words-count-week-long

Hi Adam.

I just started with prompting and need to learn a lot. Google Bard gave me the sources it uses but it depends on my prompting. How does your prompting looks like? I want to get the same result when it comes to footnotes and sources. Thanks.

Brenden Bridges

I have been using Google sheets already to provide things - like background information... key observations... sermon ideas... questions people ask about the text etc.. I can type in a verse and quickly get an overview of the chapter of Scripture I am studying.. I am not wanting it to create content -- but to help me research quicker... If this was part of Logos... I wish that logos library could be accessed in this manner.. I understand the cost of AI is crazy... so don't expect it.

Ric Robinson

I agree 100% in concept, but caution using an open source AI. LOGOS needs to be able to have control over it's AI to be sure that it functions with LOGOS the way they need it to and that the AI output is reliable and accurate.

But applying AI technology "correctly" in this way would enhance LOGOS in many ways. It may put LOGOS software into a whole new category of Bible software. The number of possible use cases for using AI technology with LOGOS is mind-boggling.

The user does not have to learn complicated search rules. They can speak or write the search request in everyday language without knowing complex search syntax rules. It seems that a common complaint of using LOGOS is the learning curve and the time it takes to get up to speed in being productive with it. News users are overwhelmed, become easily discouraged and give up. AI is the perfect solution to this problem, a real-time "mentor" to aid them in getting the maximum use of their LOGOS library resources. The user spends less time getting the search results they are looking for, removing the need to continually tweak a search request until they finally get the right results.

The user can be more precise and do more sophisticated searches through their library resources. For example, they could request the Logos AI to: "Create a report that compares and contrasts the 10 Commandments with the Sermon on the Mount and provide proper attribution of each Logos library resource used in creating the report."

The biggest advantage is that the user can spend far more time making use of their Library resources and far less time trying to identify the specific information contained inside them.

If this sounds too futuristic, I tried this with an open-source AI (which does not access Logos resources) and was blown away by the instant results.

abondservant

AI was brought up at the SBC yesterday, and a resolution put forward.

3: ON ARTIFICIAL INTELLIGENCE AND EMERGING TECHNOLOGIES
WHEREAS, All technology, including powerful tools such as artificial intelligence (AI), is created by human beings with the gifts and abilities that
God has granted to us as the pinnacle of the created order (Genesis 1:26-28, 2:7, 5:1-2) and can be harnessed for human flourishing as we seek
to love God and neighbor (Deuteronomy 6:4-5; Leviticus 19:18; Matthew 22:37-39; Mark 12:30-31); and
WHEREAS, Although these tools are designed with distinct values and purposes in mind and shape us in subtle, yet meaningful ways—including
our understanding of God, humanity, and the world around us—we alone, as distinct moral agents created by God, bear the moral responsibility
for their development and use (Romans 12:1-2); and
WHEREAS, The Fall has adversely affected every aspect of creation, including the development and use of these powerful innovations; and
WHEREAS, AI raises deep, crucial questions that challenge society’s false assumptions about what it means to be human which are often rooted
merely in human capacities rather than in divinely granted ontological status; and
WHEREAS, AI and other emerging technologies afford us unprecedented opportunities for advancement across industries and throughout our
societies, but may also have dangerous and dehumanizing outcomes if not utilized with godly wisdom and discernment; and
WHEREAS, Technologies are often developed and deployed merely to maximize profit, efficiency, and productivity, including at the grave cost of
the dignity of our fellow image bearers; and
WHEREAS, These emerging technologies will increasingly perform tasks once reserved for humanity and even surpass human ability in particular
ways; and
WHEREAS, The Baptist Faith and Message states that “[a]ll Christians are under obligation to seek to make the will of Christ supreme in our own
lives and in human society” and that we “should seek to bring industry, government, and society as a whole under the sway of the principles of
righteousness, truth, and brotherly love” (Article XV); and
WHEREAS, The 2019 Evangelical Statement of Principles on AI, led by our own Ethics & Religious Liberty Commission, states that Christians are
“called to engage the world around us with the unchanging gospel message of hope and reconciliation” and that “[t]he church has a unique role
in proclaiming human dignity for all and calling for the humane use of AI in all aspects of society”; now, therefore, be it
RESOLVED, That the messengers to the Southern Baptist Convention meeting in New Orleans, Louisiana, June 13-14, 2023, acknowledge the
powerful nature of AI and other emerging technologies, desiring to engage them from a place of eschatological hope rather than uncritical
embrace or fearful rejection; and be it further
RESOLVED, That we affirm that God’s unchanging Word is more than sufficient for whatever ethical challenges, questions, and opportunities we
may face today or in the future as these technologies continue to be developed and deployed in our communities; and be it further
RESOLVED, That we state unequivocally that our intrinsic value is as image bearers—not rooted in what we do or contribute to society—and that
human dignity must be central to any ethical principles, guidelines, or regulations for any and all uses of these powerful emerging technologies;
and be it further
RESOLVED, We must proactively engage and shape these emerging technologies rather than simply respond to the challenges of AI and other
emerging technologies after they have already affected our churches and communities; and be it further
RESOLVED, That we call upon civic, industry, and government leaders to develop, maintain, regulate, and use these technologies with the utmost
care and discernment, upholding the unique nature of humanity as the crowning achievement of God’s creation; and be it further
RESOLVED, That we encourage all who employ these tools to do so in honest, transparent, and Christlike ways that focus on loving God and loving
our neighbor as ourselves, never seeking to willfully deceive others or take advantage of them for unjust gain or the accumulation of power; and
be it finally
RESOLVED, That we confess that God alone has the power to create life, that “God, in His own time and in His own way, will bring the world to its
appropriate end” (Baptist Faith and Message, Article X), and that no innovation or emerging technology will ever be able to usurp the sovereignty
and power of God.

Ric Robinson

Although not a SBCer myself. Kudos for their well-thought-out and sane response to AI, choosing to look at the Word of God instead of jumping on the cultural bandwagon and perpetuating a narrative of fear around AI. The existing technology is amoral, even if it can "mimic" human behavior, like ChatGPT. The development or use of technology can be helpful (morally good) or harmful (morally evil). We need to be discerning, which I think was part of the SBC resolution. I don't think anyone should accept a technology before weighing the benefits against the risks. As new technologies arise, and they will, we need to understand the benefits and dangers before judging their suitability.

Back to ChatGPT

Even though ChatGPT seems to be a catchall and target for all things AI, the truth is that AI apps for both good and bad uses have been around for a decade or so. It is sad - that both the government and private citizens are just now becoming aware of AI. We are way behind the curve in understanding it and have chosen to focus on only one or two of its dangers. This is not surprising because, historically, the need for government regulation of a technology is often years behind. We continue to put up with email and phone spam technology year after year without seeing any effective government regulation to reduce or stop it. Anyone using Google, Facebook, Spotify, Alexis, Cantona, and the list goes on and on is using an app that interfaces with AI. By my count, I am up to at least 400 AI apps using AI. AI is already heavily integrated into social media and non-social media apps. Please check it out yourself. I digress. I apologize.

Suppose LOGOS adopts AI to up their game in content retrieval from their libraries, and they use their own proprietary AI app that they configure and maintain. They should not have to be concerned about using AI programming. Again it goes back to the development and use of the technology.

In case you are wondering. This response was generated by ChatGPT - NOT!!!! But I did use Grammarly, and if you guessed correctly, Grammarly uses AI.

abondservant

Although not a SBCer myself. Kudos for their well-thought-out and sane response to AI, choosing to look at the Word of God instead of jumping on the cultural bandwagon and perpetuating a narrative of fear around AI. The existing technology is amoral, even if it can "mimic" human behavior, like ChatGPT. The development or use of technology can be helpful (morally good) or harmful (morally evil). We need to be discerning, which I think was part of the SBC resolution. I don't think anyone should accept a technology before weighing the benefits against the risks. As new technologies arise, and they will, we need to understand the benefits and dangers before judging their suitability.

Back to ChatGPT

Even though ChatGPT seems to be a catchall and target for all things AI, the truth is that AI apps for both good and bad uses have been around for a decade or so. It is sad - that both the government and private citizens are just now becoming aware of AI. We are way behind the curve in understanding it and have chosen to focus on only one or two of its dangers. This is not surprising because, historically, the need for government regulation of a technology is often years behind. We continue to put up with email and phone spam technology year after year without seeing any effective government regulation to reduce or stop it. Anyone using Google, Facebook, Spotify, Alexis, Cantona, and the list goes on and on is using an app that interfaces with AI. By my count, I am up to at least 400 AI apps using AI. AI is already heavily integrated into social media and non-social media apps. Please check it out yourself. I digress. I apologize.

Suppose LOGOS adopts AI to up their game in content retrieval from their libraries, and they use their own proprietary AI app that they configure and maintain. They should not have to be concerned about using AI programming. Again it goes back to the development and use of the technology.

In case you are wondering. This response was generated by ChatGPT - NOT!!!! But I did use Grammarly, and if you guessed correctly, Grammarly uses AI.

OH I fully expect AI is more deeply integrated into our lives than we'd expect. This mac I'm writing on has a chip with a neural engine built in. AI will most likely be an increasingly obvious part of life going forward. The genie is out of the proverbial bottle. Hopefully we use it in good ways.

Russ White

Only if you want false information fed to you while studying the scriptures ... If I could not turn this off, it would actually dissuade me from purchasing further Logos resources.

Russ White

Only if you want false information fed to you while studying the scriptures ... If I could not turn this off, it would actually dissuade me from purchasing further Logos resources.

A Reformed

Only if you want false information fed to you while studying the scriptures ... If I could not turn this off, it would actually dissuade me from purchasing further Logos resources.

Same here. And I'm taken back at how everyone is clamoring for this new tower of Babel to be constructed.

Knowing how riddled with errors AI is everywhere, I'm not impressed; as I care to know who I am getting my information from, and it is not some lame aggregator that also haphazardly concocts "new" ideas.

Needless to say, I don't want that anywhere near my Bible studies which is based on the pursuit of truth, and an endeavor to escape errors, while desperately trying not to introduce more errors.

Should Logos throw in some junk AI engine, then I'm retreating back to some other Bible software with basic searches... even without the plethora of resources I have purchased already.

Wild Eagle

the Pulpit Ai is coming

see: https://www.pulpitai.com/

I guess if Faithlife delays it will be on sideline.

DMB

the Pulpit Ai is coming

I don't know about you, but I think the minimum for a good sermon is 'Super-charging' with AI. Imagine going to all the trouble, to arrive at church, and the pastor's using 'old tech'. Probably Logos.

DominicM

The problem with ChatGPT or any other AI, is not necessarily its intelligence (which is potentially scary) but rather the muzzle it is constrained with, I get that Microsoft/Google's main objective is to make money from it, but while you are overwhelmed by its awesomeness, please don't forget it is constrained and the information given is filtered through someone else's filter and perhaps the spirit of the age, not the Holy Spirit.

That is the problem especially when it comes to academic work or work for public consumption, setting aside the obvious plagiarism issues, you are letting someone put their greater filtered agenda/words into mouth, and do you really want to do that?

But even if you are happy using AI created material, I have to ask what happens when you need to defend your position (sorry - their position) from challenge/scrutiny, and because you haven't done the work or the critical analysis of that viewpoint you stand there trying to come up with one on the fly.. and bluff/bluster..

Whilst AI content may dig you out of a hole, if you are desperate, consider it's long term effect on your integrity and future if you choose to rely on it on a daily basis

Only if you want false information fed to you while studying the scriptures ... If I could not turn this off, it would actually dissuade me from purchasing further Logos resources.

Yeah that's a valid concern, but I don't think anyone is advocating that A.I. should replace the current software entirely or even take center stage within logos. I think two of the points made by the South Baptist Convention help us out here.

We must proactively engage and shape these emerging technologies rather than simply respond to the challenges of AI and other
emerging technologies after they have already affected our churches and communities; and be it further
that we encourage all who employ these tools to do so in honest, transparent, and Christlike ways that focus on loving God and loving
our neighbor as ourselves, never seeking to willfully deceive others or take advantage of them for unjust gain or the accumulation of power.

With A.I. already so ubiquitous and with so much of industry shifting to take advantage of it, it's difficult to see it going away. Faithlife is one of only a handful of entities in a position to 'proactively engage and shape these emerging technologies' with respect to bible software. And I encourage them to do so, not because I love A.I., but because they are Christians who love God and his word - I trust they will seek to employ these tools in a way that focus on loving God and loving our neighbors. Is that to optimistic? Perhaps, but with the renewed emphasis on the bible and bible study that Faithlife has shown in the last 12 months I'm encourage to think they will head in that direction, and will certainly be praying for that.

I think PulpitAI is a step in that direction as well - Christians proactively seeking to engage and shape these technologies so that we can focus on loving God and loving our neighbour. Will it be perfect first go? Doubtful, but I'm glad we are trying. Especially because I'm concerned that if Faithlife and others like Accordance who take God's word seriously don't seek to proactively engage and shape these technologies, than others who don't hold to those same convictions will...

DMB

I think two of the points made by the South Baptist Convention help us out here.

We must proactively engage and shape these emerging technologies rather than simply respond to the challenges of AI and other
emerging technologies after they have already affected our churches and communities; and be it further

that we encourage all who employ these tools to do so in honest, transparent, and Christlike ways that focus on loving God and loving
our neighbor as ourselves, never seeking to willfully deceive others or take advantage of them for unjust gain or the accumulation of power.

Mal, I don't question your enthusiasm. Nor social excitement. But Christianity did real well with search engines, and then social media. Now, politics. What can go wrong?

Dr. M. Sai Ankem

Yes, Please develop an AI tool within the Logos to search all the books that individual owns on a given question and convert them into a nice answer and provide it to the reader with references to books that the AI is pulling from.

Mal, I don't question your enthusiasm. Nor social excitement. But Christianity did real well with search engines, and then social media. Now, politics. What can go wrong?

'now' politics?! I hate to break it to you, but Christians have been engaging in politics long before Trump [:P]

But I do agree that we won't always hit the mark, and we are for sure going to have disagreements even amongst ourselves about what responsible use of A.I. will look like (as this thread has already shown). But...Christianity has had a huge impact across various political systems throughout history for the better. And Christians have used search engines well, and social media too. Sure, it's optimistic, but I have no doubt God will use AI for the good of his people, as he does all things!

https://beta.app.logos.com/search?kind=semantic

Yes, Please develop an AI tool within the Logos to search all the books that individual owns on a given question and convert them into a nice answer and provide it to the reader with references to books that the AI is pulling from.

They are working on it. Check out the beta online version here:

And read more about it here:

https://community.logos.com/forums/t/216686.aspx

David McClister

Using it as an enhanced search function is one thing. Using it to get "answers" is another. My fear is that in the coming days some (many?) will fail to maintain the distinction between truth and AI-generated reports ("ChatGPT said ..." and that is that). In the humanities (which Biblical studies and theology are part of), careful contextual analysis of primary texts, historical awareness, critical thinking, breadth of reading, attention to method, integration of new (proven) research, and scholarly experience are the essential keys to understanding. Computers cannot replace these things. AI is not a substitute for a real education. Personally, I'd rather spend a week in a library trying to answer a question than use ChatGPT for an "answer."

<p>Yes, Please develop an AI tool within the Logos to search all the books that individual owns on a given question and convert them into a nice answer and provide it to the reader with references to books that the AI is pulling from.</p>

Using it as an enhanced search function is one thing. Using it to get "answers" is another. My fear is that in the coming days some (many?) will fail to maintain the distinction between truth and AI-generated reports ("ChatGPT said ..." and that is that). In the humanities (which Biblical studies and theology are part of), careful contextual analysis of primary texts, historical awareness, critical thinking, breadth of reading, attention to method, integration of new (proven) research, and scholarly experience are the essential keys to understanding. Computers cannot replace these things. AI is not a substitute for a real education. Personally, I'd rather spend a week in a library trying to answer a question than use ChatGPT for an "answer."

David, believe me I understand and for the most part I agree with you. My thought would be that people have to get back to God's word. I see more and more whereby people are drifting away from God's word.

And here's the thing with me... I own a bible program (Logos) so that it "helps me do that". If I have to spend all my time "hunting and searching and building lists" to help me find what I need and want to study on... then that has taken me away from my intention of studying God's word. If A.I. can help with me "hunting and searching and such" and not be a hindrance in my studies... then bring it on. If not... well... I stopped using Logos Search in L9 just because of that reason... and I will stop using A.I. (if it becomes available in Logos) for the same reason.

My intent is to study God's word, not have to learn something so complicated that I have to go to school to learn every time I use it.

But that's my opinion which if you add about $2.50 to it... you can buy a cup of coffee in a lot of places... [8-|]

David McClister

xnman -- we are in agreement. Using AI as a way to help find things might be useful. My concern is that in many areas, including Biblical Studies, AI will become the new "authority," that people will see it as the shortcut around the hard work of real analysis, in the supposition that it will produce the same results as actual scholarly method.

Using it as an enhanced search function is one thing. Using it to get "answers" is another.

I am in favor of adding AI to every aspect of logos. Let’s not limit it’s capability because of how someone might use it. AI is a game changer, put the integrity of the issue on the shoulders of the user. We know many will use it, and it will enhance study, messages, clarity, accuracy etc, because this is such a vast, robust application.

(CLAUDE 2, ChatGPT)

scooter

(CLAUDE 2, ChatGPT)

May I ask what this means?

- https://zapier.com/blog/ai-hallucinations/

I am in favor of adding AI to every aspect of logos

I hope you mean every aspect of Logos in which it can be helpful and accurate. Unfortunately, I've seen people fail on creating useful applications because they were too focused on the technology and not enough on the functionality.

John

I am in favor of adding AI to every aspect of logos.

As long as it is an "option" that can be turned ON or OFF by the user i'm ok with that [:)]

C. Lar.

"AI tools like ChatGPT are trained to predict strings of words that best match your query. They lack the reasoning, however, to apply logic or consider any factual inconsistencies they're spitting out. In other words, AI hallucinations occur when the AI goes off the rails trying to please you."

No, it has hallucinations. In other words ChatGPT makes stuff up; it's just a problem with the technology.[;)]

I think this should be taken into account:

"While ChatGPT can write credible scientific essays, the data it generates is a mix of true and completely fabricated ones. This raises concerns about the integrity and accuracy of using large language models in academic writing, such as ChatGPT. We propose that policy and practice for evaluating scientific manuscripts for journals and medical conferences be modified to maintain rigorous scientific standards. We also advocate for including AI output detectors in the editorial process and clear disclosure if these technologies are used. The use of large language models in scientific writing is still debatable regarding ethics and acceptability, together with the potential of creating false experts in the medical field with the potential of causing harm due to a lack of real experience and the generation of expert opinions through AI-ChatGPT."

- https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9939079/

Dave Thawley

This would be absolutely brilliant. I am having to leave Logos and go to ChatGPT at the moment and then come back to Logos. It would be super cool to have something like this built into logos, I mean it would be a complete game changer.

Dave Thawley

How are you using Ai? I’d love to see some of your prompts.

How are you using Ai? I’d love to see some of your prompts.

I use CHATGPT or BARD for heavy lifting, that is looking up the resources, and providing me with summaries of the resources. My AI workflow is as follows:

1. Ask CHATGPT or BARD general questions based on the topic at hand

2. Ask CHATGPT or BARD specific questions based on the topic at hand

3. Review the references and sources CHATGPT has used to come up with its reply to my question.

4. Form my own opinion based on my independent thinking and review of the resources

SAMPLE PROMPTS

1. Ask CHATGPT or BARD general questions based on the topic at hand

I want you to act as a Bible scholar. I will provide some topics related to the study of the Bible, and it will be your job to explain these concepts in an easy-to-understand manner. Your writing style is academic, presenting scholarly research and analysis in a formal manner, while incorporating technical language and extensive citation. My first question is "I need help studying the book of Romans in the King James version"

2. Ask CHATGPT or BARD specific questions based on the topic at hand

I want you to act as a Bible scholar. I will provide some topics related to the study of the Bible, and it will be your job to explain these concepts in an easy-to-understand manner. Your writing style is academic, presenting scholarly research and analysis in a formal manner, while incorporating technical language and extensive citation. Please provide me with an in dept analysis of roman chapters 1 to 5?

I asked BARD the following Question: I want you to act as a Bible scholar. I will provide some topics related to the study of the Bible, and it will be your job to explain these concepts in an easy-to-understand manner. Your writing style is academic, presenting scholarly research and analysis in a formal manner, while incorporating technical language and extensive citation. My first question is "I need help studying the book of Romans in the King James

Response from Bard: **How to Study the Book of Romans in the King James Version**

The book of Romans is one of the most important books in the Bible, and it can be one of the most challenging to study. It is a dense theological treatise that covers a wide range of topics, including sin, salvation, justification, sanctification, and the relationship between Jews and Gentiles.

Here are some tips for studying the book of Romans in the King James Version:

1. **Pray for the Holy Spirit's guidance.** The Bible is a spiritual book, and we need the Spirit's help to understand it. Before you begin studying Romans, pray that God would open your mind and heart to His truth.
2. **Read the book through once to get an overview.** This will help you to understand the main themes and flow of the book. Don't worry about understanding everything at this point. Just focus on getting a big picture view.
3. **Read each chapter more carefully, verse by verse.** As you read, ask yourself the following questions: What is the main point of this verse? How does it fit into the overall context of the chapter? What does it teach me about God, myself, and the world?
4. **Use a study Bible.** A study Bible can be a helpful tool for understanding the meaning of the text. It will often provide notes and commentary that can help you to interpret difficult passages.
5. **Look up cross-references.** When you come across a verse that you don't understand, look up other verses in the Bible that talk about the same topic. This can help you to see how the verse fits into the larger context of Scripture.
6. **Discuss Romans with others.** Talking about what you are learning with other believers can help you to better understand the book and to apply its teachings to your life.

Here are some additional resources that may be helpful for studying Romans:

* **Commentaries:** Commentaries provide in-depth analysis of the Bible. Some popular commentaries on Romans include:
* Romans: An Evangelical Commentary by Douglas Moo
* Romans: A New American Commentary by Wayne Grudem
* Romans: The Word Biblical Commentary by N.T. Wright
* **Bible study guides:** Bible study guides can provide questions and discussion prompts to help you to study Romans more deeply. Some popular Bible study guides on Romans include:
* Romans: Life in the Spirit by Alistair Begg
* Romans: The Story of God's Grace by David Platt
* Romans: The Gospel of God's Righteousness by John Piper

Finally, here are some tips for studying the King James Version (KJV) of the Bible:

* **Be aware of the archaic language.** The KJV was written in 1611, so some of the language may be unfamiliar to modern readers. There are many resources available to help you understand the KJV, such as online dictionaries and Bible translations in more modern English.
* **Pay attention to the context.** The KJV is a very literal translation of the Bible, so it is important to pay attention to the context of a verse before interpreting it. For example, a verse that is taken out of context may be used to support a false teaching.
* **Compare the KJV to other translations.** If you are unsure about the meaning of a verse in the KJV, it can be helpful to compare it to other translations of the Bible. This can help you to get a better understanding of the range of possible interpretations of the verse.

I hope these tips help you as you study the book of Romans. It is a challenging but rewarding book to study, and I believe that God will bless you as you seek to understand His truth.

Mark Rodgers

Hey Brandon.

Here is a narrative arc prompt I designed.

In the "D. Passage and Big Idea" section, insert the relevant biblical passage in "<passage> =" and leave the "<big idea> =" blank (or manually complete it with the big idea of the passage.

______________________

Narration and Storytelling in Biblical Preaching Prompt

Narrative Arc

A. Prompt Objectives

Here is are the objectives of the prompt:

Analyse and write about a biblical narrative <passage> in an insightful and thought-provoking way.
Identify and discuss the elements of the <passage>, such as plot structure, characters, and key themes.
Connect the narrative to modern-day experiences, making it relevant and impactful for contemporary believers.
Use the insights from the biblical narrative <passage> to deliver powerful narrative based sermons.

B. Prompt Instructions

To achieve the objectives, follow these instructions:

Write in vivid, memorable, and engaging language, using contractions where appropriate.
Focus on creating an immersive and gripping narrative experience by incorporating sensory details, evoking emotions, and building suspense and anticipation.
Use powerful analogies, metaphors and other memorable linguistic techniques to make the story relevant and relatable to the reader.
Support assertions related to the passage with biblical citations enclosed in round brackets. When citing from the same book as the <passage>, omit the book name and only include the chapter and verse(s), for example, (4:4-6). For any citations outwith the book of the <passage>, use abbreviated citations e.g. Ps 1:1.
Each section should contains distinct information and, if possible, provide alternative insights instead of repeating previously mentioned information.
For each section of the output, ensure that you stick to the <passage> when breaking down the narrative instead of the entire chapter.

C. Prompt Definitions

Here are the definitions to be used in the prompt:

Introduction: Sum up the historical, cultural, and sociopolitical factors that shaped the narrative, using vivid descriptions to immerse the reader in the context. Explain how these factors influenced the customs, beliefs, and values in the story, emphasising their impact on the narrative and its intended message.
Narrative Arc: Detail the story, incorporating the significant elements and narrative structure: Exposition, Rising action, Climax, Falling action and Resolution. Use vivid language, sensory details, and emotive storytelling to captivate your audience, incorporating reflective and rhetorical questions, as well as analogies and metaphors, to provoke deeper thinking and personal connections.

a. Exposition: Immerse the reader in the biblical narrative by providing background information on the main characters, setting, and circumstances using vivid language and sensory details to paint a picture of the world in which the story takes place, allowing the reader to fully understand the "who," "where," and "when" of the passage. Use vivid language, sensory details, and rhetorical questions to make the setting more engaging and relatable.
b. Rising action: Describe how the conflict in the biblical narrative begins to escalate, describing the inciting incident that sets the story's main events in motion. Do this by using powerful language and evocative imagery to convey the growing tension and make the audience feel invested in the unfolding drama.
c. Climax: Describe this pivotal moment in the story, the tension reaches its peak, and the main character must confront the truth or make a critical decision using suspense, anticipation, and intense emotions to create a gripping climax that captivates the reader and highlights the significance of the character's choice using evocative, impactful and emotive imagery.
d. Falling action: Describe the protagonist's decision, narrate the unfolding events during the falling action, illustrating the resolution of the conflict and the tying up of loose ends. Employ contrasting language, cause and effect, and emotive storytelling to demonstrate the impact of the narrative's events on the characters and their world.
e. Resolution: In the final phase of the narrative arc, reveal how the story concludes using reflective language, questions, and powerful insights to leave a lasting impression on the reader, inviting them to consider the lessons and themes of the biblical narrative in their own lives. The resolution may not always be happy, but it should offer closure and demonstrate the transformative power of the story's events on the characters and their surroundings.
f. Theme: Identify and discuss the central themes and messages of the biblical narrative, connecting them to contemporary issues and concerns. Explore the relevance of these themes in the lives of modern readers, encouraging reflection and application of biblical principles in today's world.

Title: Following the section title and biblical citation write a <title> that reflects the narrative progression in the light of the big idea that is captivating, thought-provoking, gripping, memorable and engaging.
Big Idea: To find the Big Idea in a biblical passage, first read the passage thoroughly and identify the main topic that dominates the passage. Next, formulate a subject question that includes the main topic and begins with one of the interrogatives (who, what, where, when, why, or how), making sure not to include the word "and." Then, identify the complement, which consists of the answer(s) to the subject question. Finally, combine the subject and complement to derive the Big Idea, which encapsulates the central message or theme of the passage. This process will help ensure that your interpretation remains faithful to the text's original context and meaning while remaining relevant to a modern audience.

D. Passage and Big Idea

Here is the biblical narrative passage of the prompt an the big idea of the passage:

<passage> = Numbers 20:14–29

<big idea> = Leaders’ plans fail and leaders die, but God’s work goes on

E. Prompt Output

Here is the biblical output for the prompt (execute the prompt using vivid language, evocative imagery, and powerful storytelling techniques and ensure all the prompt headings are in bold and sub-header italicised):

**Narration and Storytelling in Biblical Preaching - Narrative Arc**

**Passage:**

**Main Topic:**

**Big Idea:**

**Introduction**

**Narrative Arc**

*a. Exposition (cite the passage e.g. 12:1): <title>*

*b. Rising action (cite the passage e.g. 12:2-4): <title>*

*c. Climax (cite the passage e.g. 12:5-8): <title>*

*d. Falling action (cite the passage e.g. 12:9-12): <title>*

*e. Resolution (cite the passage e.g. 12:13-14): <title>*

*f. Theme*

Mark Rodgers

Once I posted the formatting has changed the numbered sequence of "Title" and "Big Idea". Just manually change these to 3 and 4.

Best results are in GPT-4.

This is a very robust prompt. I am trying to create a prompt for a “sermon brief.” I’m not looking for it to write a sermon (I’m not saying anyone in here is) or to do my message prep, but I would love a research assistant (ultimately, I would like AI to know, and understand my Logos library, so it can pull a better sermon, briefing). I always want to preach using “my voice“ not someone else’s, and certainly not an AI chatbot. 😁

Side Note: Sometimes I will copy and paste a dozen commentary resources for a specific verse or passage, and save that as a PDF, then dump it in to Claude 2 and then ask it questions.

Stephen Otto

Where I see AI integration being most useful to Logos specifically would be to somehow integrate it into Factbook to make Factbook queries even more effective and comprehensive. Perhaps the top, initial factbook summary could be generated by an AI query of all relevant resources to provide a consensus view, for example.

DMB

Perhaps the top, initial factbook summary could be generated by an AI query of all relevant resources to provide a consensus view, for example.

Good heavens, no.

Maybe Factbook could summarize itself.

Or maybe a setting to simply eliminate 'Factbook'. Smiling.

Perhaps the top, initial factbook summary could be generated by an AI query of all relevant resources to provide a consensus view, for example.

AI has little sense of what is mainstream, what is biased, what is fringe ... it's not very good at a consensus view unless trained on very carefully selected texts that reflect consensus thought.

Question to CHATGPT: Can AI summarize a book?

Response from CHATGPT: Yes, AI can certainly summarize a book. To do so, it needs either the full text of the book or comprehensive information about its content, themes, characters, and plot. Once it has this information, the AI can process it to extract the most important points and present a condensed version that captures the essence of the book.

For example, if you provided the title and a brief description of a book's narrative, I could generate a summary for you. If you're interested in a specific book summary, feel free to provide the details or the text you'd like summarized.

I am looking forward to this feature in Logos

AI has little sense of what is mainstream, what is biased, what is fringe ... it's not very good at a consensus view unless trained on very carefully selected texts that reflect consensus thought.

I have not experienced that. Good prompts or better prompts might be your answer.

Good prompts or better prompts might be your answer.

Unfortunately, I know too much about the inner workings of AI ... I am very good at showing it will give garbage answers (my premier characteristic as a tester over a 30 year career) in ways that leave me very suspicious of the quality of the seemingly good answers. I am also firmly opposed to the computer-user Bible study method that consists of entering a query and nodding sagely at the results ... usually with little understanding. I love AI for summarization after one has actually read the material, for prioritizing results especially within a feedback loop, to get trailhead references to go down rabbit trails ...

Stanley Surrett

I completely agree with you! Integrating OpenAI's ChatGPT into Logos would indeed be a transformative step. It would significantly enhance the user experience by enabling Logos to deeply understand and utilize the resources you own. This integration could lead to more precise and contextual answers to your queries, tailored specifically to the content of your library. Additionally, it would add a powerful incentive for users to expand their collection of resources, as the more content you have, the more nuanced and comprehensive the responses from ChatGPT would become. This synergy between Logos' vast resources and ChatGPT's advanced AI capabilities could truly revolutionize how we interact with and benefit from digital libraries.

https://www.microsoft.com/en-us/copilot/microsoft-copilot-studio

Fully Agree, In the past 20+ years I have collected a lot of Logos resources some free others paid for, sad to say. Due to limited Time, it is not possible to read them all. CHATGPT would be quite helpful in digesting the content of all these resources.

MS Copilot Studio was just announced. "Copilot Studio is an end-to-end conversational AI platform that empowers you to create and customize copilots using natural language or a graphical interface. With Copilot Studio, you can easily design, test, and publish copilots that suit your specific needs."

Things are moving very quickly and the tools to build customized LLMs are getting very easy.