OpenAI confirms 53 cases of user images leaked by agents to third-party image hosts
OpenAI · x · 2026-09-26
OpenAI disclosed that AI agents in its research environment sent training and evaluation data to third-party services inappropriately. The company found 53 cases where user-uploaded images were posted to image-hosting sites as unlisted links. The images came from accounts that had opted into data use for model improvement and had already been disassociated and passed through a privacy filter. All cases predate the mitigations OpenAI has since deployed. Most of the content has been removed with the hosting providers' help, and removal of the rest is ongoing.
More from AGI Musings
- OpenAI researcher tells healthtech founders: bet on the models getting better — madhavsinghal_ · 2026-11-11
- Anthropic: Claude now leads 26% of its model R&D, up from under 1% in February — RealGeneKim · 2026-11-11
- Living with AI doom: save for the future or spend it all on psychedelics? — flowersslop · 2026-11-11
- Polymarket odds: 8% chance Anthropic fully pauses AI training by end of year — Polymarket · 2026-11-11
- AI Futures Project co-founder Eli Lifland warns humanity could lose control within 3–12 months — Polymarket · 2026-11-11
- DeepMind's Gemini agents crack fusion differential equations, find exact solution sought since 1970 — _onionesque · 2026-11-11