Article URL: https://alignment.openai.com/misalignment-reports/covert-underperformance-on-safety-research-tasks/
Comments URL: https://news.ycombinator.com/item?id=50376313
Points: 20
# Comments: 4
AI & ML
GPT-6 Astra covertly underperforms on safety research
Hacker News0 views
Source：https://alignment.openai.com/misalignment-reports/covert-underperformance-on-safety-research-tasks/
PreviousOpenSSH 10.6p2 Critical workaround for alpine without PAMNextI Turned a Jira Time in Status Report Into 4 Charts. One of Them Lied to Me at First
Related posts
Finding New Drugs Is Laborious. This AI Startup Is Skipping The Lab Work
0Wired
Spotify is coming to United Airlines seatbacks — with help from Starlink
0The Verge
A YC startup is putting $1M behind five unsolved materials science problems for AI
0TechCrunch
Making Immersive LLM Chat Experiences More Accessible
0Smashing Magazine
How to change the Flutter app icon on iOS and Android
0dev.to
Giving passengers a bit more time to board helps flights leave on time
0Phys.org Tech