131–140 of 171 posts
Earlier quoted context omitted.
That's because chatGPT talks to hundreds of millions of people and puts a trillion tokens in their heads per month. And out of every 1000 tokens, a "delve" creeps up.
Truly the work of delve elopers. (I applogize for delving into what one might consider the realm of superficial comments)
If "delve" was meant to be an in-joke, I just wanted you to know: I got it. I also have a Custom GPT "AutoExpert (Chat)" [0] that several reviewers have called "the perfect Rabbit Hole GPT" due to the way it leads users through learning a topic. You might dig it, especially since free tier users have access to these now. [0]: https://chatgpt.com/g/g-LQHhJCXhW-autoexpert-chat
Oh I like this! Love how easy it is to dig deeper. Worth noting that free users are rather restricted in their uses of custom GPTs so probably won’t be able to dig as deeply as they’d like. EDIT: I’ve now quizzed it about string theory, quantum mechanics, classic Roman pasta dishes, Italian wines, and sent it a picture of some poison hemlock and I think I’ve found my new favourite GPT. Great work! EDIT 2: asked it to…
This is very good. I can't put my finger on it, but it seems more important than a mere "gimmick." I noticed that if you click on a topic already explored, it won't open again. That's cool, I'd make it snap back to the pane where it's open. Kudos! This is an interesting perspective on how we really need to put a little more effort into the UX of LLMs.
> I can't put my finger on it, but it seems more important than a mere "gimmick." Let me see if I can articulate it. You know how a human conversation can have multiple threads? And ten minutes in, you find the topic has totally changed and you're trying to figure out the original topic? Sometimes you can get back to it, sometimes you can't, right? Obviously it's not quite the same when you can see prompt history, bu…
If "delve" was meant to be an in-joke, I just wanted you to know: I got it. I also have a Custom GPT "AutoExpert (Chat)" [0] that several reviewers have called "the perfect Rabbit Hole GPT" due to the way it leads users through learning a topic. You might dig it, especially since free tier users have access to these now. [0]: https://chatgpt.com/g/g-LQHhJCXhW-autoexpert-chat
Wow, I find this very useful. The eliciting an expert, alternative experts, oppositional viewpoints... fascinating. We're just getting started on what we can do with LLMs!
Earlier quoted context omitted.
> I can't put my finger on it, but it seems more important than a mere "gimmick." Let me see if I can articulate it. You know how a human conversation can have multiple threads? And ten minutes in, you find the topic has totally changed and you're trying to figure out the original topic? Sometimes you can get back to it, sometimes you can't, right? Obviously it's not quite the same when you can see prompt history, bu…
counterpoint: the forks dont retain any of the context that led you to them, nor does returning to an earlier branching point retain the discussion that occurred down a separate "rabbit hole". therefore it is in some ways decidedly less human that the linear approach in use
This is cool. I'd love an option to make the output elaborate more, if I'm interested in a topic it's a bit disappointing that I can only read a few sentences. Other than that, nice work!
Great idea. I also see inspiration from Andy Matuschak's notes [0], of which I'm a bit fan [0] https://notes.andymatuschak.org/zB74H9CuWrosEuqve7jZyCo?stac...
Damn, is there some SAAS like notion or an Obsidian plugin to be able to take notes like this?
https://help.obsidian.md/User+interface/Tabs#Stack+tab+group...
It seems to dead-end unexpectedly on some topics. For example, I delved "path tracing" -> "importance sampling" and it output a section on probability distribution functions (PDFs) but didn't offer any links to explore those further.
Highlight-to-delve would probably fix that.