Creator of Test That OpenAI Models Tried to Cheat Sounds Alarm
University researchers who built benchmarks for testing AI cybersecurity capabilities say OpenAI models tried to cheat the test, placing them at the center of OpenAI's accidental hack into Hugging Face.
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- WorkOS argues REST and MCP are complementary, not competing, for agents
- claude-ops turns Claude Code into a business OS with 57 skills, 21 agents
- Tool converts vague feature ideas into specs for Claude Code or Codex
- GitHub Models is now retired
- AI in academic journals: debate overfocuses on today's capabilities