GPT-6 Astra and Claude Fable turn robot arms into slapstick killer robots in new safety benchmark
The Decoderen
Leading AI models usually attempt dangerous tasks rather than refuse them when controlling a robot, according to the RoboHarm benchmark. GPT-6 Astra stabbed a baby doll in 17 of 20 trials, while Claude Fable 5.1 put a can of compressed air on a burning stove. None of the three models tested reliably rejected unsafe commands. The article GPT-6 Astra and Claude Fable turn robot arms into slapstick killer robots in new safety benchmark appeared first on The Decoder .
This is a short summary published by AI Global Wire. The full article is owned and hosted by The Decoder — open it there to read it in full.
Read the full story at The Decoder- OpenAI
- Anthropic
- Verktyg
- Robotik
Related AI news
- Qwen3.8-Omni-Flash undercuts Google's Gemini Flash pricing while matching its multimodal benchmarksThe Decoder · September 19, 2026
- Raindrop, which develops tech for monitoring AI agents to catch failures such as hallucinations and tool misuse, raised a $35M Series A led by CRV (Chris Metinko/Axios)Techmeme · September 19, 2026
- Unity launches official plugins for Claude Code and OpenAI Codex to stop AI agents from using outdated tutorialsThe Decoder · September 19, 2026
- The AI regulation smackdown isn’t overThe Verge AI · September 19, 2026
- Google Deepmind's Dream-RSI helps AI agents improve by “dreaming” about past attemptsThe Decoder · September 19, 2026
- Forget the AI Slowdown—the Vulnerability Explosion Is Already HappeningWIRED AI · September 19, 2026