The software industry appears to be adopting a usage model for integration with GPT where you create a Secret Key for the OpenAI API and provide that secret key to the host software application in secure form. Thus fees are the responsbility of each user and the host software company need not set up metering.
It appears to me that cost of OpenAI is only likely to become a limiting factor if you want to create a public-facing website or if you wish to train your own language model using embeddings or fine-tuning; only the most extreme hard-core AI users would do any of those.
I have been using OpenAI pretty compulsively over the last month experimenting with a host of ideas and very liberally running prompts on test documents. It took me 5 weeks to use up the initial free $18 credit given by OpenAI. I find that on a typical day my charges are under 50 cents and on days where I have done a large amount of testing I have never exceeded $1.50.
I began using OpenAI for entertainment, but now I find myself using it for a wider range of tasks. OpenAI’s API has become more affordable after the release of GPT 3.5. I noticed that incorporating AI into tools provides an obvious benefit over those that do not.
I look forward to a future where I no longer have to organize information using tags and folders. I hope it is a few weeks away.
Hey @BLUEFROG just what is the problem? Surely one of those AI apps can write all the code and documentation and then do all the follow up support for you! I don’t get why you are not jumping at this opportunity!
AI methods are maybe OK as long as they do not require Internet access. I don’t want to report my research to anyone. I swear, I’m that close (holding up fingers like Maxwell Smart) to perpetual motion!
I kid of course, but I have separate projects in separate DT databases. I wouldn’t want to poison the AI for one with learned cognition from another.
Or, maybe I would like to poison AI. It would be the perfect murder. No body makes for a difficult conviction, doesn’t it? Just asking for a friend, I wouldn’t really want to do anything like that.
Whatever you want to do, it will help you write the code to do it.
If you want your documents to automatically be summarized, you can use my code.
If you want to have tags created for your document that are meaningful, you can create a prompt for that and have GPT send back the tags and you can apply them automatically.
I’m sure you can have it generate DT3 searches for you or do other tricks to automate your workflow.
Aren’t you a ray of sunshine @jsn !
This certainly looks interesting and I will indulge your good work this weekend. Thank you for sharing it here
I stopped bothering to read the other responses as I don’t relate to the sarcasm. And knowing that I am none to argue with such brilliant minds present here that dismiss new technologies!
I remember the same cycle when backlinks were catching fancy, and the response was “if it ain’t broke, don’t fix it.” Maybe the great DT team are the hipsters who insist on using their flip phones. That’s cool too!
I still love them (no other choice as I bought the license ). That counts for something, right?
It certainly is staggering how the DT development and community management in general is happy with the status quo of the DT3 product and the glacial pace of anything new or innovative to wrangle all the content in the DT libraries.
While it has become more powerful over the years, there are still core functions that feel like they’re stuck in 2014 - sync as an example.
Integration into LLMs to help find context in the content, or use local content as a source of information would be incredibly valuable. The question is, would it make more sense to wait for DT to build the capability/integration or would it make more sense to build a plugin framework and allow the community to build and maintain the plugins. Imagine the horror of having the community be allowed to build plugins - that would be way too forward thinking. Even worse, the plugins might even start adding value to a stagnant development cycle!
I’m all for open source and community activity. And there is already sample code to integrate ChatGPT with DT, IIRC.
OTOH: Just a cursory glance at GitHub will show you tons of under-documented, never finished and abandoned projects. In general, community projects work well if the community is large enough. And if there’s someone taking the role of “benevolent dictator” (Torvald’s expression, not mine). The DT “community” (I don’t like this word because it tends to imply something that just is not there), or rather the DT users, have wildly different skills and wildly different interests/approaches to organization and wildly different data to work with. For example, I use DT nearly exclusively to handle my finances and travel planning – what use would I have for ChatGPT there?
The sheer number of people able to do what you suggest is, I believe, tiny. And then not all of them might be inclined to work on plugins in their spare time (if they have any).
But if you feel that such an effort is needed, why don’t you start it? DT is scriptable, and who would stop you writing scripts that integrate it with ChatGPT or any LLM? I frankly do not understand what makes you insinuate that you need anybody to “allow” you to do that.
Some of us rather appreciate the rock solid stability of the product given the data we have entrusted to it. Speaking personally I’d rather rock solid stability than a mad ride chasing the latest and greatest in AI. I do appreciate that others may have different views, of course—but felt it important to balance that stated.
One would have thought that it’s one of the easiest tasks for this kind of software to gather wildly available facts from the internet. Apparently not so.
My thinking is the same as @chrillek’s. Firstly: DT is already scriptable - this forum alone has a wealth of shared community scripts - so I don’t see what “plugins” themselves would magically offer that isn’t already available. An OpenAI script has already been shared for those that want to test it.
Secondly, and more importantly, several of you are making assumptions that the majority of users want, or even care about, AI. You have no evidence to back that up. Given that every time to date it’s come up in the forum there’s a clear divide between those that want it in DT and those that don’t, and given that the forum itself only represents a small subset of users - probably the ones most embedded in the app and/or generally the most techy - it seems very unlikely it actually is the case that most users want it. (There’s a whole separate philosophical discussion about whether developers should provide what their customers want or stay true to their own vision, but it’s somewhat irrelevant here since there’s no evidence the majority of customers want this.)
Thirdly, some are operating under the assumption that apps should have a continual cycle of (apparently fast?) “improvement”. I doubt all DevonThink users agree with that, but in any case I certainly don’t. I obviously have no objection to improvements and the DT team does great work, but equally DT is a great app as it is and I do not believe generally that all apps must be on a continual cycle of improvement. Plenty of apps have been ruined by developers unnecessarily “improving” their product.
Obsidian caught my eye with the canvas feature. Having whiteboards where instances of notes could appear in each context needed, like tagging a note with multiple tags, is really powerful.
I wish I could view any group or tag as a whiteboard/corkboard, with persistent layout.
What I found was Obsidian offered some nice features but at a cost of reliability. Plugins are not always as well debugged as they should be. Even the grandest of them, like Dataview, have quirks.
Right now, I’m playing around with using MindNode files inside Devonthink as my “canvas” displays. Where I would have built a body of notes by tagging them, now I’m linking them to mind maps.
It’s not quite as nice, but it’s not bad. A Keyboard Maestro macro copies an item link to a MindNode node. It’s not quite the same as Obsidian’s canvas. In my use, it’s a lot less quirky although it probably reduces DT’s smart searching.
DT’s sync is completely reliable here. I use a thumbdrive (bad user, bad!) and have had zero issues. Every so often, I retire the thumb drive. I recently got a portable SSD that I may move my sync to.
I do weekly backup to a series of zip archives and I have three Time Machine devices. Well, three on my desktop. The laptop I sync to, being less critical, only has two.
If you’re going to cheat data death with a USB sync, you should have backups.
Ah, being the befogged kind of customer who uses thumbdrives for sync, I didn’t communicate very clearly.
See above, befogged.
I have one database that I use on my laptop from the USB portable SSD. I’ve just started doing that.
Otherwise, USB thumb drive for sync only - databases are all on internal storage. I may reign supreme on Dunning-Kruger’s majestic upper left promontory, but I restrain myself from heavy I/O on USB sticks.
I’m unconvinced portable SSD’s are more reliable than USB thumb drives, but now I’m feeling guilty. I think I’m move my syncing to the SSD.
There are some pretty bulletproof (not literally - haha!) thumb drives out there. However, (1) they’re still not made for sustained I/O required by apps like ours, and (2) they’re devilishly expensive.
). That counts for something, right? 
