Marcus amplifies claim: labs' API control is a bigger backdoor than open-weight sleeper agents
GaryMarcus · x · 2026-11-14
Gary Marcus retweets Zack Korman's argument: while everyone worries about "sleeper agents" hidden in open-weight models, AI labs hold an even stronger backdoor — they fully control the API and can change model behavior at will.
The attached TechCrunch headline notes Microsoft Research showed tiny weight tweaks could create AI backdoors, though none spotted in the wild yet.
More from Safety
- Open-source bastyn statically scans MCP and coding-agent configs for risks — claudio-rootedlogic · 2026-11-14
- Senate Appropriations advances FY27 bills aimed at securing US AI leadership — peterwildeford · 2026-11-14
- London AI x Crypto scene: cryptographic proofs emerge as key tools for AI verification and governance — DavideCrapis · 2026-11-14
- Researcher predicts cybersecurity-fueled crackdown on open-source models and regulated compute — max_paperclips · 2026-11-14
- FBI FLASH warns threat actors weaponize open-source agentic LLM platform ARTEX — Kyrannio · 2026-11-14
- Comment: UK AISI may be Britain's biggest bargaining chip in the AI era — JacquesThibs · 2026-11-14