Ideas & society2025 · shared on Hacker News
LLMs get lost in multi-turn conversation
Explore LLMs get lost in multi-turn conversation, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Yrobotswantdata ·
The new skill in AI is not prompting, it's context engineering
915 points518 comments
Ycrawshaw ·
The unreasonable effectiveness of an LLM agent loop with tool use
447 points320 comments
Ysimonpure ·
LLMs get lost in multi-turn conversation
374 points259 comments
Ysteer_dev ·
The "confident idiot" problem: Why AI needs hard rules, not vibe checks
324 points380 comments