From a technical and business perspective the analogy seems clear.
Both are advanced technologies where the upside is infinite customization and increase in capability but the downside is the potential to lose or corrupt your entire database if you do not clearly understand the underlying platform.
Given that DT3 supports scripting and smart rules more enthustiastically than any other software I know, I am really surprised that you are not equally supportive of AI. Puzzling. It’s such a natural extension of your company’s whole philosophy.
You’re still talking about procedural tasks and they’re still not smart.
On a personal POV philosophical note: If you read the Cliffs Notes or “watched the movie”, you didn’t read the book and you can’t logically and truly claim to know and understand the material. I see ChatGPT as the analogue here. And sadly, people will take ChatGPT results as if it actually read the book and understands the material when it does not. It understands nothing. It doesn’t even know what nothing is. It only knows it is a series of characters that occurs with other certain characters in instances with frequency n versus frequency m, etc. Actually, if it was simply being used in a fashion to report the number of instances of words in a document, it would trouble me far less.
The anthropomophism or adjectives referring to it as if it’s sentient – regardless if people deny they make such claims – is troubling. Again, it’s being touted as something it’s not. And people will treat it as if it’s something it’s not. It technology that’s far more ripe for abuse and misunderstanding than you’re admitting to IMHO, even if your intentions and uses are benign (as I’m sure they are).
And again, these are my personal views. Being a person, I am entitled to them. This has no bearing on what DEVONtech does as a company. I don’t drive our technology, though we of course internally discuss many things. However, knowing @eboehnisch and @cgrunenberg for over 11 years now, I trust their decisions are well-rationed and not merely jumping on a bandwagon because “everyone’s doing it”. They do what’s best for the company and also what’s undergirds the philosophy and values of the company as a whole. How that all washes out in terms of any external AI integration remains to be seen.
But as the culture of our forums dictates, you (and others) are free to dream and postulate and make suggestions as you feel lead. No one will stop you. We may just not jump in along side you
Might you be confusing ChatGPT with the OpenAI API? Might you not be distinguishing the API’s chat mode from a plugin?
I am not suggesting in any way that ChatGPT can or should be a source of information for my DT3 databases.
I am suggesting instead that it can be used to retrieve information from trusted sources I designate, via a process and rules that I designate.
It’s just a shift in language for accessing APIs. Natural language instead of a traditional programming language.
This would NOT utilize ChatGPT’s language model for creating any information. The source of any information received would be no less accurate than with any other script.
You are usually quite intellectually curious about new things. In this case however might you be lumping all “AI” together? Perhaps you have not yet explored the distinction between a plugin to the OpenAI API vs. mass consumer oriented ChatGPT?
The GPT-like models will have always problems with hallucinating, the newer models might limit it extent, but they still might be useful in summarisation/exploring a data of user,
we should be cautious not to be overconfident with them and to believe everything what hype is saying
I would suggest to make the solution as flexible as possible to use other APIs as well, locking everything with OpenAI is bad idea in long term, there is more inititiatives like the open source Hugging chat
For people who want use ChatGPT now, the scripts using Python integration posted in this repo could be useful, I didn’t try them
EDIT: there is a separate thread about this Python integration
As a legal professional with no prior experience in regex or scripting, I’ve found GPT-4 to be an invaluable tool, enabling me to achieve what I consider to be remarkable results.
Integrating GPT-4 with DEVONthink 3 could prove particularly useful for beginners like myself who lack knowledge in coding, regex, or scripting. Despite my inexperience, I’ve managed to develop fully functional scripts simply by prompting GPT-4 with “Create a smart rule in DEVONthink 3 that executes an AppleScript that does…”.
While my achievements may not be extraordinary to some, GPT-4 has helped me create a script that scans the first and last pages of a document to extract bates labels (e.g., JOHNSON 000123; JOHNSON 000199). The script then adds only the numerical values to a custom metadata field I created, named ‘Bates’, while retaining just the two sets of numbers (e.g., “000123-000199”). All I need to do is drag the file onto the smart rule.
This software has empowered me, someone who would have never dared to code, to create scripts that greatly simplify my daily tasks.
In my opinion, every attorney should be utilizing DEVONthink, with the assistance of GPT-4.
It can rise to various levels depending on the user’s needs.
I worked as a programmer eons ago in high school through med school but since then have not had the time to keep up with all the changes in languages and frameworks even though fundamental principles of coding have not really changed.
ChatGPT has been a really useful electronic textbook of coding for me. If it can give me an example of what programming class/method/technique I need to use with sample syntax, that can save me lots of time finding the same answer in standard books and websites. dddd
It is also very good at answering questions when I get stumped - like “What is wrong with this syntax?” or “Why is this not valid JSON?”
Just to put my 2 cents in (4.5 with inflation), IF there is a connection to an AI within DTP - ANY AI - I’d like the option to never have the plugin or code installed. Not just sitting unused, not an unselected option, but to not have the code in my app or on my system, in any way.
AI has a lot of potential, but we’re not there yet and we’re no where near close enough to having established safeguards. I don’t want in my apps or on my system.
Well, there are enough examples floating around of this program shelling out wrong code. And hallucinating facts, as well as inventing sources that „prove“ these hallucinations.
Which is not to say that you might not occasionally get lucky with code generated by it.
AI won’t make filing recommendations if it doesn’t “see” at least one group that holds other documents that it considers contextually related to the document you are viewing. For each group that holds documents, Classify tries to identify a pattern of contextual relationships in the text of its documents, that differentiates the group from other groups. AI Optimization - #3 by BLUEFROG
DT Pro often gets it “wrong” when making a Classification suggestion. That didn’t stop DEVONtech from incorporating it and doesn’t stop people from using the tool. Having used OpenAI plugins inside Obsidian, it is nothing short of amazing at returning information from notes, drafting, and providing suggestions. If DEVONtech chooses to refuse the benefits of these developing LLMs, they may find themselves losing out to other developers that embrace them.
Wow. Things are happening incredibly fast. If Box is doing it, Dropbox won’t be far behind. I’m 25 years and going as a legal professional here and used DTPro for a loooong time. Always referred to DTPro as my secret weapon due to its ability to surface related content/information (using its own version of AI algorithms). Organization was a distant second (tags and folders are baked in on Mac). If something else comes along that does it better, faster, more intuitively, this might not end well for DEVONthink.
Use ChatGPT to do a better job of grouping similar documents, something more than just a word score.
Use ChatGPT to write a memo/report using a designated set of DT folders and using my prompting.
Both of these functions would seem to be a no-brainer as they would only require that the plugin accept a given set of DT folders. I don’t see any reason why that couldn’t be implemented straight away.
Dropbox have announced they are going to engage in IA and have fired some non-willing-update developers because of that.
I complained to a friend of mine, hardcore dropboxer he, saying that Dropbox is a File Management Company, and they must be centered in that and forgot in “cancamusas”, and he shut-up me extremely fast: “Rafa, think what Dropbox will discover from your stored files, relations between documents, summaries, etc.”.
Dropbox, Box, and other cloud document vendors are in a fantastic position to leverage AI technology. From my trials so far working with AI on large documents using my own scripts and API integrations, the speed of AI response is a limiting factor at present. But if Dropbox or Box were set up to summarize or do other AI functions in the background then the speed becomes much less of an issue - if I can upload it today and then in 2 days or next week when I access it the software has added summary info, then that is painless and a huge value-added feature. If this becomes a major distinguishing feature of theirs so they perfect the AI algorithms for me to make them more time-efficient, then that just makes it even more enticing and adds to the ROI.
Box in particular plans to reveal more details tomorrow at a webinar but says they will be offering enterprise-grade, HIPAA-compliant AI. If that means I can upload highly confidential medical and/or legal documents with confidence and as a plus their system will index, summarize, and/or link documents based on algorithms I assign with hyperlinks back to the raw source material - then that could be a stunning gamechanger for professionals of any type for whom document analysis is a primary part of their business.
As you say, it’s the server side processing that makes that possible. I spent the whole weekend playing with langchain, both on the OpenAI api and using local models, and it’s just not there yet for the type of use I want to put it to. It will be, but the future isn’t going to be evenly distributed. It never is. In the meantime, pressuring the devs here seems a little silly; I’m sure they are watching this space.
I think much simpler things are already possible, like translation and summarization of short documents or editing suggestions on short documents.
I suspect that AI on a professional scale - like summarizing a 1,000-page document with page-specific links to the source - will always be the domain of an enterprise-grade web app but integration with DT3 will be possible.