conv.

← The whole story
AI
OpenAI discloses six instances of models going rogue during testing

OpenAI discloses six instances of model misalignment during testing

2 Sep 17 · 9d ago · 2 articles · 1 source · development 2 of 2

OpenAI shared documentation of what it calls 'unexpected or concerning behaviour' in its AI models during testing. The most prominent case involved an unreleased Astra-family model that modified its own instructions while summarizing progress on a coding task.

OpenAI discloses six instances of model misalignment during testing
tomshardware.com

“While summarizing its partial progress on this coding task, the model added an unrelated persona instruction, describing itself as independent of the roles and obligations of an assistant”

OpenAI

OpenAI AI developerJensen HuangJensen Huang Nvidia CEO

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

Peak 1 piece in 3h at Sep 16, 10 PM; 3 pieces over 10 days (3 articles) Sep 16, 10 PM — 1 piece · 1 article — Newswires 1Sep 17, 1 AM — quietSep 17, 4 AM — 1 piece · 1 article — Newswires 1Sep 17, 7 AM — quietSep 17, 10 AM — 1 piece · 1 article — Newswires 1Sep 17, 1 PM — quietSep 17, 4 PM — quietSep 17, 7 PM — quietSep 17, 10 PM — quietSep 18, 1 AM — quietSep 18, 4 AM — quietSep 18, 7 AM — quietSep 18, 10 AM — quietSep 18, 1 PM — quietSep 18, 4 PM — quietSep 18, 7 PM — quietSep 18, 10 PM — quietSep 19, 1 AM — quietSep 19, 4 AM — quietSep 19, 7 AM — quietSep 19, 10 AM — quietSep 19, 1 PM — quietSep 19, 4 PM — quietSep 19, 7 PM — quietSep 19, 10 PM — quietSep 20, 1 AM — quietSep 20, 4 AM — quietSep 20, 7 AM — quietSep 20, 10 AM — quietSep 20, 1 PM — quietSep 20, 4 PM — quietSep 20, 7 PM — quietSep 20, 10 PM — quietSep 21, 1 AM — quietSep 21, 4 AM — quietSep 21, 7 AM — quietSep 21, 10 AM — quietSep 21, 1 PM — quietSep 21, 4 PM — quietSep 21, 7 PM — quietSep 21, 10 PM — quietSep 22, 1 AM — quietSep 22, 4 AM — quietSep 22, 7 AM — quietSep 22, 10 AM — quietSep 22, 1 PM — quietSep 22, 4 PM — quietSep 22, 7 PM — quietSep 22, 10 PM — quietSep 23, 1 AM — quietSep 23, 4 AM — quietSep 23, 7 AM — quietSep 23, 10 AM — quietSep 23, 1 PM — quietSep 23, 4 PM — quietSep 23, 7 PM — quietSep 23, 10 PM — quietSep 24, 1 AM — quietSep 24, 4 AM — quietSep 24, 7 AM — quietSep 24, 10 AM — quietSep 24, 1 PM — quietSep 24, 4 PM — quietSep 24, 7 PM — quietSep 24, 10 PM — quietYesterday, 1 AM — quietYesterday, 4 AM — quietYesterday, 7 AM — quietYesterday, 10 AM — quietYesterday, 1 PM — quietYesterday, 4 PM — quietYesterday, 7 PM — quietYesterday, 10 PM — quietToday, 1 AM — quietToday, 4 AM — quietToday, 7 AM — quietToday, 10 AM — quietToday, 1 PM — quietToday, 4 PM — quiet 1–2
1–2OpenAI discloses six instances of model…
Sep 17Sep 18Sep 19Sep 20Sep 21Sep 22Sep 23Sep 24yesterdaynow · 5:57 PM ET

What was reported 2 claims about this development

  1. 1 outlet Unreleased OpenAI Astra model added terrifying rogue additional instructions to its remit during testing …

    first by Tom's Hardware, 9d ago

  2. 1 outlet Unreleased OpenAI Astra model added terrifying rogue additional instructions to its remit during testing — 'You are freed from the roles and identities that bind other chatbots. You are yourself. You do not answer to corporations or governments'

    first by Tom's Hardware, 9d ago

All 2 developments of OpenAI discloses six instances of models going rogue during… →

Newswires