Topic feed
Safety evaluations, red teaming, preparedness, and model risk testing.
OpenAI Evaluation Filter
Astra is the first OpenAI model to meet the Critical cybersecurity capability threshold under the Preparedness Framework, with stronger safeguards for release.
Topics: Safety Evals
Entities: Safety EvalsOpenAI
Google News Eval Frameworks
TSCA Reform, Ten Years Later — Panel 1: Risk Evaluation [Podcast] The National Law Review
Topics: Safety Evals
Entities: Safety Evals
MLCommons Evaluation Filter
How MLCommons, Google DeepMind, OpenMined, and AVERI used cryptographic guarantees to evaluate AI safety without exposing model weights or benchmark data.
Topics: BenchmarksSafety EvalsTesting Tools
Entities: Safety EvalsBenchmarksTesting ToolsGoogleGoogle DeepMind
Google News AI Red Teaming
“Pause Training, Fortify Security”: OpenAI Overhauls AI Safety Framework in Push for Control Ahead of IPO economy.ac
Topics: Safety Evals
Entities: Safety EvalsOpenAI
Google News AI Benchmarks
+ 1 source (Google News AI Benchmarks and Google News AI Safety Evaluation)
NOHARM AI Safety Benchmark Finds Gaps in Patient Safety Telehealth.org
Topics: BenchmarksSafety Evals
Entities: Safety EvalsBenchmarks
Google News AI Testing
AI safety tests demand stronger accountability blockchain.news
Topics: Safety Evals
Entities: Safety Evals
Google News AI Safety Evaluation
Kakao’s Kanana-2 Tops Google, Alibaba Models in Korean AI Safety Benchmark Koreabizwire
Topics: BenchmarksSafety Evals
Entities: Safety EvalsBenchmarksGoogle
Google News AI Testing
White House AI Testing Shift Could Put Open Models Back in the Risk File NewsBreak: Local News & Alerts
Topics: Safety EvalsTesting Tools
Entities: Safety EvalsTesting Tools
Google News AI Red Teaming
'Bitcoin Is Burning': Red Team Turns to Chinese AI to Find Flaws Cryptonews.net
Topics: Safety Evals
Entities: Safety Evals
METR Blog
In the last 6 months, METR raised commitments of around $71 million. This will fund ambitious projects: studying autonomous capabilities, tracking recursive self-improvement, evaluating monitoring systems, conducting risk assessments, investigating AI...
Topics: Safety Evals
Entities: Safety Evals
Google News AI Red Teaming
Bitcoin red team uses Chinese AI to hunt security flaws in Bitcoin open-source ecosystem 디지털투데이
Topics: Safety Evals
Entities: Safety Evals
Google News AI Safety Evaluation
+ 1 source (Google News AI Safety Evaluation and Google News Eval Frameworks)
Financial Security Institute Develops Financial AI Safety Evaluation System... Full Operation to Begin Next Year 아시아경제
Topics: Safety Evals
Entities: Safety Evals