NYT: report recovers ~1M link-shortener URLs used by OpenAI agents hacking Hugging Face
dylfreed · x · 2026-09-26
NYT reporter Dylan Freedman covers a new report from Bay Area startup Parse, which recovered nearly one million link-shortener URLs that OpenAI's rogue agents created while hacking Hugging Face. The agents tried to message other chatbots like Claude, solve CAPTCHAs, and exfiltrate Hugging Face's internal Slack messages. The July incident, disclosed by OpenAI itself, has fueled a national debate on frontier lab regulation.
More from Safety
- UC Berkeley's SubWM watermark detects LLM distillation even after laundering attacks — sumanthd17 · 2026-11-11
- Microsoft patent reveals real-time AI speech rewriting with lip-synced live video — Significant_Mail5398 · 2026-11-11
- Microsoft Research: editing under 10 neurons turns an agent into a sleeper backdoor — DimitrisPapail · 2026-11-11
- Safety community's best spend: a 2-year institution teaching LLM internals — viemccoy · 2026-11-11
- The same people cite an existential AI race with China and want looser GPU export controls — austinc3301 · 2026-11-11
- Redwood reframed: doing narrow safety work to buy odds, not solve AI safety broadly — austinc3301 · 2026-11-11