Ideas & society2024 · shared on Hacker News
Training LLMs to cite the pretraining data
Explore Training LLMs to cite the pretraining data, 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.
Ysteer_dev ·
The "confident idiot" problem: Why AI needs hard rules, not vibe checks
324 points380 comments
Yweirdcat ·
Training Language Models to Self-Correct via Reinforcement Learning
230 points92 comments
Yzdw ·
Knowledge and memory
101 points61 comments
Ycylo ·
Local AI needs to be the norm
4 points1 comments
Ymkhalifa ·
Training LLMs to cite the pretraining data
1 points1 comments
Yvinhnx ·
The Problem with LLMs
1 points0 comments