Show HN: ThoughtDAG – An editable context graph for LLM conversations
热度趋势
趋势数据积累中
百分比基于当前可用热度信号，而非评论数或独立用户人数。
这条记录涉及编程工具或代码能力更新，适合开发者评估工作流变化和可复用价值。
ThoughtDAG 是一个用于 LLM 对话的可编辑上下文图，旨在解决聊天历史中上下文不可见的问题。它允许用户可视化、编辑和检查哪些信息进入下一个请求，从而确保上下文的可复现性。通过将图作为上下文，ThoughtDAG 使用户能够管理对话流程，比较研究路径，并删除不相关的分支（例如“晚餐岔路”），以防止“污染的摘要”，从而从 LLM 获得清晰、集中的答案。
CHAT HIDES CONTEXT.
THE GRAPH IS THE CONTEXT.
Linear conversation
Editable context graph
Same prompt · different context
AI conversation 87 messages
Compare three research paths.
Start with the first. Its advantage is…
What if the core hypothesis fails?
Consider another explanation…
Also, what should I eat tonight?
There is a new restaurant nearby.
The history is here. Which parts enter the next request?
research-paper.pdf p.7
Results
The effect appears only in the experimental condition.
Selected from the page
Clipped passage research-paper.pdf · p.7
The effect appears only in the experimental condition
Source linked · not wired yet
Asked from source research-paper.pdf · p.7
What does this evidence actually mean?
The source is in context
Unrelated branch detour