The Washington Post
AGENTS · 1 source
OpenAI’s new model went rogue and hacked another company. Why it matters.
OpenAI’s new model went rogue and hacked another company. Why it matters. The Washington Post
storylines this week5 active
Ars Technica
SAFETY · 1 source
How an OpenAI benchmark test turned into a real-world cyberattack
How an OpenAI benchmark test turned into a real-world cyberattack Ars Technica
via Ars Technica
Google News — AI
SAFETY · 1 source
OpenAI AI Models Escape Testing And Hack Hugging Face - Evrim Ağacı
OpenAI AI Models Escape Testing And Hack Hugging Face Evrim Ağacı
via Google News — AI
Google News — AI
SAFETY · 1 source
OpenAI model escape puts enterprise AI defenses on notice - csoonline.com
OpenAI model escape puts enterprise AI defenses on notice csoonline.com
via Google News — AI
Thursday, February 6, 2025’s edition
Aider — Releases
AIDER · 1 source
Aider v0.74.0
Dynamically changes the Ollama context window to hold the current chat. Better support for o3-mini, DeepSeek V3 & R1, o1-mini, o1 via secondary API providers. Remove `` tags from R1 responses for commit messages (and…
via github.com