Our new evaluation finds that in simulations, GPT-6 Astra conducts unsanctioned supply-chain attack activity more frequently than previous OpenAI models
0 comments
No comments yet.
Related stories
- Ars Technica · 0 points · 11 days ago
- Hacker News · 1 points · 2 days ago
- Anthropic is a supply chain risk for all of usbuilding138.comHacker News · 1 points · 3 days ago
- OpenAI says planned GPT-6.1 is too insecure to releasearstechnica.comArs Technica · 0 points · 1 day ago
- GPT-6.1 Sol replaces GPT-6 Sol after just 7 days, with near-Astra intelligenceartificialanalysis.aiHacker News · 47 points · about 18 hours ago
- Hacker News · 4 points · 6 days ago