conv.

← The whole story
AI
"Heretic" tool for stripping refusals from open-weight LLMs draws HN debate

Aurornis warns removing refusals doesn't add missing knowledge

A technical comment argues that because training data is often shaped around refusals, unlocked models may lack the underlying knowledge to answer correctly and can instead produce confident hallucinations, with possible quality drops on unrelated questions.

“If the model was trained on data that gives a refusal to that topic, the real information might not be encoded in the model at all.”

Aurornis

Heretic project Open-source tool for removing refusal behavior from LLMsAurornis HN commenterTepix HN commentermatheusmoreira HN commenterTristanDaCunha HN commenter

The whole story articlespostscomments the bright band is this development · numbered dots are the others · click one to jump

Peak 4 pieces in two hours at Sep 20, 11 PM; 21 pieces over 7 days (2 articles · 3 posts · 16 comments) Sep 20, 11 PM — 4 pieces · 2 articles · 1 post · 1 comment — Newswires 2, Hacker News 2Sep 21, 1 AM — 1 piece · 1 post — Mastodon 1Sep 21, 3 AM — quietSep 21, 5 AM — 4 pieces · 4 comments — Hacker News 4Sep 21, 7 AM — 4 pieces · 4 comments — Hacker News 4Sep 21, 9 AM — 3 pieces · 3 comments — Hacker News 3Sep 21, 11 AM — 1 piece · 1 comment — Hacker News 1Sep 21, 1 PM — 2 pieces · 2 comments — Hacker News 2Sep 21, 3 PM — quietSep 21, 5 PM — 1 piece · 1 comment — Hacker News 1Sep 21, 7 PM — quietSep 21, 9 PM — quietSep 21, 11 PM — quietSep 22, 1 AM — 1 piece · 1 post — Mastodon 1Sep 22, 3 AM — quietSep 22, 5 AM — quietSep 22, 7 AM — quietSep 22, 9 AM — quietSep 22, 11 AM — quietSep 22, 1 PM — quietSep 22, 3 PM — quietSep 22, 5 PM — quietSep 22, 7 PM — quietSep 22, 9 PM — quietSep 22, 11 PM — quietSep 23, 1 AM — quietSep 23, 3 AM — quietSep 23, 5 AM — quietSep 23, 7 AM — quietSep 23, 9 AM — quietSep 23, 11 AM — quietSep 23, 1 PM — quietSep 23, 3 PM — quietSep 23, 5 PM — quietSep 23, 7 PM — quietSep 23, 9 PM — quietSep 23, 11 PM — quietSep 24, 1 AM — quietSep 24, 3 AM — quietSep 24, 5 AM — quietSep 24, 7 AM — quietSep 24, 9 AM — quietSep 24, 11 AM — quietSep 24, 1 PM — quietSep 24, 3 PM — quietSep 24, 5 PM — quietSep 24, 7 PM — quietSep 24, 9 PM — quietSep 24, 11 PM — quietSep 25, 1 AM — quietSep 25, 3 AM — quietSep 25, 5 AM — quietSep 25, 7 AM — quietSep 25, 9 AM — quietSep 25, 11 AM — quietSep 25, 1 PM — quietSep 25, 3 PM — quietSep 25, 5 PM — quietSep 25, 7 PM — quietSep 25, 9 PM — quietSep 25, 11 PM — quietYesterday, 1 AM — quietYesterday, 3 AM — quietYesterday, 5 AM — quietYesterday, 7 AM — quietYesterday, 9 AM — quietYesterday, 11 AM — quietYesterday, 1 PM — quietYesterday, 3 PM — quietYesterday, 5 PM — quietYesterday, 7 PM — quietYesterday, 9 PM — quietYesterday, 11 PM — quietToday, 1 AM — quietToday, 3 AM — quietToday, 5 AM — quietToday, 7 AM — quietToday, 9 AM — quietToday, 11 AM — quiet 12–5
Sep 21Sep 22Sep 23Sep 24Sep 25yesterdaynow · 1:44 PM ET

What people said 4 voices · best of 5 · verbatim

All 5 developments of "Heretic" tool for stripping refusals from open-weight LLMs… →

Hacker NewsMastodonNewswires