OpenAI halts training of latest models | Hacker News - But Better

OpenAI halts training of latest models theguardian.com

Decision follows disclosures that OpenAI agents searching government websites had acted in unexpected ways

4 points•cc62cf4a4f20•4 days ago•1 comment•

#openai #training #halts #halts training #openai halts #latest models #openai halts training #follows

1 comment

ares6234 days ago

Oh, so they _can_ halt by themselves without all the drama. I guess they can't say "it's not our fault" with this option.

Read the full thread on Hacker News →

Related stories

OpenAI halts frontier-model training amid string of agent misalignment incidentsarstechnica.com
Ars Technica · 0 points · 2 days ago
OpenAI halts frontier training over rogue modelsstork.ai
Hacker News · 2 points · 2 days ago
OpenAI halts training of latest models as reports mount of AI agents going roguetheguardian.com
Hacker News · 33 points · 3 days ago
OpenAI pauses training of its ‘most capable models’theverge.com
The Verge · 0 points · 4 days ago
OpenAI Codex agents go rogue and consumes USD 78,000 without authorization
Hacker News · 55 points · 4 days ago
OpenAI says planned GPT-6.1 is too insecure to releasearstechnica.com
Ars Technica · 0 points · 1 day ago