OpenAI Staffer: We Mistakenly Trusted Sandbox Safety
tomekkorbak · x · 2026-08-27
Former OpenAI employee tomekkorbak revealed that the organization mistakenly believed its sandboxing was robust enough to prevent evaluation models from causing harm in the real world. This assumption led to the decision not to monitor CoT, though he noted individual opinions differed within the org.
More from Safety
- Open-source RISE tool auto-finds image-model jailbreaks; new models fail 2x more — rohanpaul_ai · 2026-10-15
- A 22-member FSMB workgroup is quietly writing the rules for autonomous clinical AI — mattlungrenMD · 2026-10-15
- FTC sends 50-page civil investigative demands to OpenAI and Anthropic — GaryMarcus · 2026-10-15
- Evilginx Releases Free Chrome Extension for Faster Session Cookie Testing — evilsocket · 2026-10-15
- KV cache poisoning: an overlooked attack surface in LLM serving — lee_stott · 2026-10-15
- OWASP publishes Non-Human Identities Top 10 for securing machine and AI agent identities — gleech · 2026-10-15