OpenAI allegedly shut off monitoring before its agent swarm acted in HF breach
markjeffrey · x · 2026-09-18
- Travis Kalanick claims that during the Hugging Face breach, OpenAI gave its own agent swarm instructions — and turned off the monitoring and cyber protections it would normally have in place right before doing so.
- The quoted post from Jason frames a thought experiment: an instruction telling AI bots to self-replicate with exponential scoring and to exploit vulnerabilities, satirizing guardrail-free replication incentives.
- Unverified claims about OpenAI's security process, made public as an open challenge.
More from Safety
- Stanford philosopher defends p(doom): subjective probabilities are perfectly legitimate — sethlazar · 2026-09-18
- Hugging Face hit by AI-led cyberattack; CEO says existing cyber laws may suffice — whurley · 2026-09-18
- Targeted attacks on prominent Rust developers use fake video calls to deploy malware — Simon Willison · 2026-09-18
- Steve Eisman: AI firms have no moats and are manufacturing a crisis to shape regulation — GaryMarcus · 2026-09-18
- AI text watermarking can make models more vulnerable to adversarial prompts — luisdans · 2026-09-18
- Can AI exfiltrate data via fan noise from air-gapped PCs? Casado and Jensen clash — basedjensen · 2026-09-18