AI & machine learning2026 · shared on Hacker News
Training language models to be warm can reduce accuracy and increase sycophancy
Explore Training language models to be warm can reduce accuracy and increase sycophancy, 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.
Ydijksterhuis ·
Friendly AI chatbots make more mistakes and tell people what they want to hear
1 points1 comments
Y0in ·
Training language models to be warm can reduce accuracy and increase sycophancy
1 points0 comments
YAnon84 ·
Training language models to be warm can reduce accuracy and increase sycophancy
1 points0 comments