AINewsnow

OpenAI and Apollo Research Expand Scheming Tests for AI Workflow Safety

This story is from 2026-11-16. It is preserved in the archive; the latest stories are on the live feed.

OpenAI is working with Apollo Research to evaluate whether its models could covertly pursue goals that conflict with developer intent, a behavior researchers describe as scheming . The collaboration also examines whether safeguards can detect such behavior. For businesses building AI-driven workflo…

Read the full story at DEV Community — AI ↗

Timeline · 1 report

  1. 2026-11-16 18:45 · DEV Community — AI
    OpenAI and Apollo Research Expand Scheming Tests for AI Workflow Safety

More stories

  1. OpenAI launches GPT-6.2 Astra and Sol as Google ships Gemini 4 Neon and Microsoft unveils MAI Code 2 — OpenAI News
  2. ChatGPT, Claude, Gemini and Grok helped plan terror attacks in US government test — The Independent Tech
  3. OpenAI unveils Performance Factory, a Codex-powered system that keeps ChatGPT fast — OpenAI News
  4. Developers increasingly run Claude Code alongside rival coding agents and alternative backends — DEV Community — AI
  5. Big tech may finally face legal consequences for AI’s actions — New Scientist Technology
  6. Perplexity Launches Orchestrator API With Same-Model Failover — Unite.AI
  7. AI Coding Agents Face Growing Scrutiny Over Security, Performance and Workflow Integration — Forbes AI
  8. OpenAI builds Performance Factory using Codex agents to keep ChatGPT fast — OpenAI (X)

Read the Daily Brief: the day's most important AI stories →