Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: ThoughtDAG – An editable context graph for LLM conversations

chenxiachan.github.io

Post reply on HN
Print view View original

41–50 of 82 posts

Re: Show HN: ThoughtDAG – An editable context graph for LLM conversations

#41

Post by chatchan »

dominotw wrote: post #24

nice. i was going to develop something like this for my own learning pattern https://news.ycombinator.com/item?id=49263169

I read the discussion you linked. The Transformer and MLP examples you gave illustrate the learning process I hope ThoughtDAG can handle: entering a branch along a question without disrupting the main thread; understanding it before deciding which content to bring back, rather than letting the entire exploration automatically pollute the subsequent context.

If you'd like to try it, I'd love to know if it matches your original vision of the learning method, and where it might still interrupt the process. If convenient, please share a screenshot of the anonymized canvas, an anonymous export, or a short screen recording. Seeing a real learning process would be very helpful for improving ThoughtDAG.

Re: Show HN: ThoughtDAG – An editable context graph for LLM conversations

#43

Post by chatchan »

darrmit wrote: post #27
angoragoats wrote: post #26

See also this post (“Every Fucking Website, Slop edition”): https://news.ycombinator.com/item?id=49302737

Had the exact same thought. It’s like reading a foreign language – and I’m going to be honest – not load bearing at all.

Thank you for pointing out this issue. The homepage did indeed use too many common landing page elements before actually showcasing the product. I redesigned the homepage, removing status labels, promotional slogans, and unnecessary entry points, making the interactive context graph the main focus of the page.

Re: Show HN: ThoughtDAG – An editable context graph for LLM conversations

#44

Post by chatchan »

embedding-shape wrote: post #15
chatchan wrote: post #12

Earlier quoted context omitted.

Yes, I have seen several adjacent approaches. Microsoft Huabu explores spatial interaction around research materials, while LLM Canvas and tldraw’s branching-chat experiments explore visual conversation trees. Many workflow canvases also use nodes and edges, but they usually represent execution pipelines. The specific interaction I am testing is more narrowly about context: an edge changes what the model receives, wh…

It would be wonderful if you included a section like "ThoughtDAG vs X" in the README, where you then compare ThoughtDAG against these other approaches/tools, and explain with some clear concise words how it's different than those. For extra bonus-points, also explicitly list where ThoughtDAG falls short (today?) and compare to them in that manner too :)

Thank you for your suggestion. I've added a "How ThoughtDAG differs" section to the README. Rather than listing specific products one by one, I ultimately chose to compare them based on interaction methods because the functional boundaries of many products are still evolving.

If you have time to take another look, I'd also like to know if the differences are clear and concise enough now.

Re: Show HN: ThoughtDAG – An editable context graph for LLM conversations

#45

Post by Esras »

DenisM wrote: post #42

Sometimes I ask the agent why it gave a certain answer, when I feel it overly fixated on something. It would be cool if the ui hilighted the poisonous part of the conversation somehow.

But agents don't _know_ why they gave an answer. They can only give "reasoning" that links to something in their context, and even then, you would have to parse out their response with some heuristics to try to match against something upstream of that turn.

I could see it being done, and if you're fond of the "models all the way down" mode of thinking, you could use a smaller model to identify it, but it could just as well be a "load-bearing seam" (ha) for something else in the conversation.

Re: Show HN: ThoughtDAG – An editable context graph for LLM conversations

#47

Post by embedding-shape »

fractorial wrote: post #29
embedding-shape wrote: post #13

This seems like a really interesting idea and something I've basically been doing myself manually so far, with a DESIGN.md document with "one concept/decision per line, built in a tree" basically, where all decisions that needs to be remembered gets noted down for future reference. Not a fan of ThoughtDAG being a complete separate application rather than built into the tools I use every day, like my text editor or ot…

Irrespective of opinions about a project or its authors, disclosing a potential security issue in a public forum is markedly not responsible disclosure.

> Irrespective of opinions about a project or its authors, disclosing a potential security issue in a public forum is markedly not responsible disclosure

Lol, what you wanted me to do instead, email the author and do the entire chain for a issue I found from 30 seconds of skimming the code? We're on a open forum talking about before-alpha software people share with the community to get feedback, I'm expecting this is exactly what the author wants, that's why they're here in the first place.

Besides, personally I file myself in the category of people not being very responsible folks in general, so I guess thanks? I'd still disagree "responsible disclosure" even applies here.

Re: Show HN: ThoughtDAG – An editable context graph for LLM conversations

#48

Post by chatchan »

Esras wrote: post #45
DenisM wrote: post #42

Sometimes I ask the agent why it gave a certain answer, when I feel it overly fixated on something. It would be cool if the ui hilighted the poisonous part of the conversation somehow.

But agents don't _know_ why they gave an answer. They can only give "reasoning" that links to something in their context, and even then, you would have to parse out their response with some heuristics to try to match against something upstream of that turn. I could see it being done, and if you're fond of the "models all the way down" mode of thinking, you could use a smaller model to identify it, but it could just a…

I think we need to distinguish between "what the model received" and "why the model generated this answer." ThoughtDAG currently focuses on the former: accurately displaying the context of the incoming request and allowing users to modify it.

Re: Show HN: ThoughtDAG – An editable context graph for LLM conversations

#49

Post by r3trohack3r »

Esras wrote: post #45
DenisM wrote: post #42

Sometimes I ask the agent why it gave a certain answer, when I feel it overly fixated on something. It would be cool if the ui hilighted the poisonous part of the conversation somehow.

But agents don't _know_ why they gave an answer. They can only give "reasoning" that links to something in their context, and even then, you would have to parse out their response with some heuristics to try to match against something upstream of that turn. I could see it being done, and if you're fond of the "models all the way down" mode of thinking, you could use a smaller model to identify it, but it could just a…

I’ve struggled with this line of thought. In a strict sense, it’s true; an AI model doesn’t actually know why it fired the way it did. But I don’t know how practically useful that observation is because, using that strict definition of “know”, humans also do not know why they do what they do.

If I asked you why you posted this comment, I suspect you’d be able to articulate a good reason why from your memories. But the firing of your subconscious and the entirety of your lived experience that molded the state in your brain that lead to you pressing that reply button and writing those exact words are inaccessible to you.

It reminds me of the timeline exercise in SRE work. I always start with a timeline and plunk pagers, metrics, slack messages, etc onto that timeline first. Then I go to individual people to get their understanding of the incident and get that into the timeline. People’s understanding of the incident and why they did what they did rarely matches the timeline.

Post reply on HN