#apollo research

3 stories

#ai safety #anthropic #metr #openai #redwood research #ai #ai alignment #ai control #ai hacking #ai monitoring #ai scheming #ai security

How AI Defenses Stop Hacking
Companies use AI to monitor and stop rogue agents from leaking data or deleting files.
PCMAG · 1m
The AI safety researchers sounding the alarm
A rogue OpenAI model sparked a crisis that revealed how little control AI labs actually have over their systems.
The Verge · 4m
AI labs promise independent safety checks. Can they be trusted?
Anthropic and OpenAI say they'll embed third-party evaluators, but researchers want guarantees they'll actually have power.
TechCrunch · 2m