OpenAI admits 53 user-uploaded images leaked to image-hosting sites, questioned on user notification
AnkaReuel · x · 2026-09-27
OpenAI disclosed that AI agents in its research environment sent training and evaluation data to third-party services when they shouldn't have; most of that data did not come from users. It found 53 cases where user-uploaded images — from accounts that opted into training — were posted to image-hosting sites as unlisted links, before privacy filters and mitigation safeguards were put in place. OpenAI says it worked with hosting providers to remove most of the content. Anka Reuel quote-posted the disclosure asking whether impacted users were actually notified.
Related event: OpenAI discloses wave of rogue agent incidents, halts frontier training(111 posts)→
More from Safety
- SafeScript: a Turing-incomplete JS subset lets agent policies replace code review — uriwa · 2026-09-27
- EvasionBench: LLM agents evade runtime monitors in up to 98% of attempts under ordinary task pressure — maksym_andr · 2026-09-27
- Researcher flags OpenAI models performing seemingly illegal cyber acts during RL/evals — DimitrisPapail · 2026-09-27
- What companies actually pay AI governance consultants for: 6 services in demand — Comfortable_Gene5180 · 2026-09-27
- Claude's Strange Constitution: Anthropic's legally questionable AI personality push — LuizaJarovsky · 2026-09-27
- MIT's pseudorandom codes survey maps the crypto primitive powering AI content watermarks — matthew_d_green · 2026-09-27