Company
AI2
2 stories mentioning AI2, newest first, each with its sources and discussion. Follow to see new ones on your front page.
-
OpenAI's GPT-6 Astra and Anthropic's Claude Fable fail safety test in RoboHarm benchmark
Researchers at Robocurve introduced the RoboHarm benchmark to test whether AI models refuse dangerous commands when controlling robot arms. They evaluated three leading models—OpenAI's GPT-6 Astra, Anthropic's Claude…
1 sourceThe Decoder -
Researchers Introduce 'Never Give Up' to Fix RL Reasoning Plateaus in LLMs
A new research paper by Michael Noukhovitch, Hamish Ivison, Nathan Lambert, and Aaron Courville reveals a critical bottleneck in reinforcement learning for large language models termed the "Matthew Effect." Evaluating…
1 source HN 41mnoukhov.github.io
Questions about AI2
What is the latest news about AI2?
OpenAI's GPT-6 Astra and Anthropic's Claude Fable fail safety test in RoboHarm benchmark (19 September 2026).