Live data from Hacker News

Viewing profile — chatchan

chatchan

HN member
Joined
Mon, Jul 20, 2026, 1:06 PM UTC
HN karma
74
Public activity
39 items

About chatchan

GNI Postdoctoral Fellow @TUM | Human-AI Alignment

Recent public activity

  1. comment
    Comment #49347633

    Thanks man! Any feedback is appreciated!

  2. comment
    Comment #49346360

    Thanks for sharing, I agree with you. I also had the same struggle with bidirectional integration. I think it makes a distinction here. Because I don't want to create "another" cod…

  3. comment
  4. comment
    Comment #49327239

    Thanks, oh I see, Cypher acts as a context selector. ThoughtDAG addresses the same issue but uses a visual approach: it searches for nodes first, then uses connections or reference…

  5. comment
    Comment #49318849

    Yes. I agree. I've added a small section to the README in the Git repository to describe how it works alongside your coding agent. ThoughtDAG has automatic folder backups as a JSON…

  6. comment
    Comment #49318648

    Thank you for your feedback! There is a way to delete a highlight. On the node side panel, there is a folded highlight section; you can manage your highlights there. Also, on your …

  7. comment
    Comment #49317056

    Thanks! I'm not very familiar with Neo4j and Cypher yet. How do you control the context using Cypher? Do you manually write queries for each request, or do you select nodes through…

  8. comment
    Comment #49317054

    Thank you for sharing! That did occur to me. ThoughtDAG now marks affected downstream answers as needing updates after an upstream node is modified, allowing users to rerun the alg…

  9. comment
    Comment #49316712

    That sounds interesting. Could you share the arxiv papers? I would love to check them

  10. comment
    Comment #49312751

    I agree. Most LLM tools (Claude Web, OpenAI, and their harness) offer re-editable questions. That is how I avoid such problems by myself. In ThoughtDAG, you can re-edit questions b…

  11. comment
    Comment #49312586

    The slime mold analogy is very accurate: research begins by exploring multiple directions, then gradually strengthens the path supported by evidence, stopping other branches from e…

  12. comment
  13. comment
  14. comment
    Comment #49311908

    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 co…

  15. comment
    Comment #49311827

    If you're referring to the loom analogy, then it's quite similar: you choose which threads to weave into the next context; unwanted threads can be unraveled :)

  16. comment
    Comment #49311810

    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 bas…

  17. comment
    Comment #49311783

    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…

  18. comment
    Comment #49311606

    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…

  19. comment
    Comment #49311542

    Thank you for carefully reviewing the repo and demo; this suggestion is very insightful. Currently, the node sidebar already has a context list grouped by material, reference, and …

  20. comment
    Comment #49311457

    Thank you for taking the time to inspect this so carefully. You were right, and I treated it as an urgent security issue. The updated version fixed the mentioned problem. All macOS…

  21. comment
    Comment #49311156

    Thank you!

  22. comment
    Comment #49311141

    Thank you for your feedback! Just want to know. What would be the smallest useful integration for you: allowing the host tool to read the currently selected context, or bidirection…

  23. comment
  24. comment
    Comment #49311072

    Yes, that is exactly the failure mode I care about and drove me to develop ThoughtDAG! In ThoughtDAG, removing that edge excludes the detail from the next request without deleting …

  25. comment
    Comment #49310172

    Not directly today. ThoughtDAG currently runs as a standalone local app. If you mean letting a Replit agent read selected graph context and write its results back as nodes, that wo…