Model

operator

3 entries · January 2025 – March 2025

Appears alongside

Featured in threads

Tracks

  • Safety & alignment 2
  • Security & misuse 1
  • Models & capabilities 1

  1. OpenAI publishes 'Security on the path to AGI'

    OpenAI described using its own models for threat detection, hired SpecterOps for continuous red-teaming, and said it was building prompt-injection defences into its Operator agent.

    OpenAISecurity & misuse · Safety & alignment

  2. OpenAI launches Operator

    Built on a new Computer-Using Agent model layered on GPT-4o, it scored 38.1% on OSWorld against a 72.4% human baseline, and launched to $200-a-month Pro subscribers only.

    OpenAIModels & capabilities

  3. OpenAI publishes Operator system card

    External red-teamers targeted prompt injection specifically; OpenAI reported raising its injection-detection recall from 79% to 99% after one testing round.

    OpenAISafety & alignment

In the commentary

Pieces from around the web that discuss operator. External links.