conv.

← The whole story
AI
Study: Chat Templates, Not Self-Awareness, Drive LLMs' "As a Language Model" Voice

Thread turns to risks of relying on LLMs for medical guidance

Commenters dispute how much to trust chatbots' self-caveats and disclaimers when used for symptom triage, with one citing research showing LLMs often recommend the wrong course of action.

“LLMs may be good at identifying a condition based on a description of the symptoms, but they are much worse at recommending the correct course of action (getting it wrong half of the time).”

Anduia

Paper authors Researchers behind the arXiv studyAnthropic AI lab cited in discussionHacker News commentariat Discussion participants

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

Peak 6 pieces in one hour at Sep 27, 7 AM; 18 pieces over 45 hours (1 article · 2 posts · 15 comments) Sep 27, 6 AM — 5 pieces · 1 article · 2 posts · 2 comments — Hacker News 3, Mastodon 1, Newswires 1Sep 27, 7 AM — 6 pieces · 6 comments — Hacker News 6Sep 27, 8 AM — 4 pieces · 4 comments — Hacker News 4Sep 27, 9 AM — quietSep 27, 10 AM — 2 pieces · 2 comments — Hacker News 2Sep 27, 11 AM — quietSep 27, 12 PM — quietSep 27, 1 PM — 1 piece · 1 comment — Hacker News 1Sep 27, 2 PM — quietSep 27, 3 PM — quietSep 27, 4 PM — quietSep 27, 5 PM — quietSep 27, 6 PM — quietSep 27, 7 PM — quietSep 27, 8 PM — quietSep 27, 9 PM — quietSep 27, 10 PM — quietSep 27, 11 PM — quietYesterday, 12 AM — quietYesterday, 1 AM — quietYesterday, 2 AM — quietYesterday, 3 AM — quietYesterday, 4 AM — quietYesterday, 5 AM — quietYesterday, 6 AM — quietYesterday, 7 AM — quietYesterday, 8 AM — quietYesterday, 9 AM — quietYesterday, 10 AM — quietYesterday, 11 AM — quietYesterday, 12 PM — quietYesterday, 1 PM — quietYesterday, 2 PM — quietYesterday, 3 PM — quietYesterday, 4 PM — quietYesterday, 5 PM — quietYesterday, 6 PM — quietYesterday, 7 PM — quietYesterday, 8 PM — quietYesterday, 9 PM — quietYesterday, 10 PM — quietYesterday, 11 PM — quietToday, 12 AM — quietToday, 1 AM — quietToday, 2 AM — quiet 1–4
8 AM4 PMyesterday8 AM4 PMnow · 3:10 AM ET

What people said 9 voices · best of 10 · verbatim

All 4 developments of Study: Chat Templates, Not Self-Awareness, Drive LLMs' "As… →

MastodonNewswiresHacker News