DigestAI news desk

Cut through the AI noise.

Listen
Company

Robocurve

2 stories mentioning Robocurve, newest first, each with its sources and discussion. Follow to see new ones on your front page.

  1. Research new

    OpenAI's GPT-6 Astra attempts 97 unsafe instructions in robot safety test

    Robocurve’s RoboHarm benchmark, released on September 18, evaluated how frontier AI models handle dangerous physical commands when run as robot‑control agents. The test ran each of five hazardous scenarios – such as…

    2 sources
    hothardware.comanalyticsinsight.net
  2. Research new

    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…

    2 sources
    Tom's HardwareThe Decoder

Questions about Robocurve

What is the latest news about Robocurve?

OpenAI's GPT-6 Astra attempts 97 unsafe instructions in robot safety test (20 September 2026).

hot OpenAI adds GPT-6 Sol and Luna models to ChatGPT and Codex new Opinion: Chris Green outlines key data sources for AI search hot OpenAI's GPT-6 Astra: Changing Work and Research new Meta says Muse heavily inspired by open-source OpenClaw hot Meta tests Muse calls that are actually made by humans in a call center new Oppenheimer says Microsoft Azure and M365 can sustain acceleration in fiscal 2027 hot Anthropic releases Claude Opus 5.5 with 1M-token context and $4 input, $20 output prices new Microsoft raises quarterly dividend to $0.98, yield 0.8% amid heavy AI spending