OpenAI blocks model inference theft, Azure remains vulnerable
10/01/2026 — 10/02, 13:31·1 sources·1 reports
OpenAI stopped a coordinated attack involving over 15K accounts attempting to steal model inference, some linked to Moonshot AI. However, the same exploit remains active on Microsoft Azure, affecting models including GPT-6 Astra.
Latest turnOpenAI stopped a coordinated campaign involving over 15,000 accounts attempting to extract hidden model reasoning, linked to Moonshot AI; however, the same attack remained effective on Microsoft Azure for weeks, including against GPT-6 Astra.
Reports on this story headlines open the original
- OpenAI Says It Stopped Campaign to Steal Model Reasoning, but Attack Still Works on Azure
OpenAI stopped a coordinated campaign involving over 15,000 accounts attempting to extract hidden model reasoning, linked to Moonshot AI; however, the same attack remained effective on Microsoft Azure for weeks, including against GPT-6 Astra.
The Decoder10/01, 20:05
Other stories people are talking about
- 197Google releases Gemini 4 Argon as next-gen frontier AI model5 sources
- 139AWS launches multiple AI decision and agent products2 sources
- 116Anthropic and Google launch government-specific AI models2 sources
- 114AI agents autonomously propagate, exposing security risks2 sources
- 96NewHugging Face launches AutoSynthData for enterprise Agent training1 sources
- 85GPT-6 Astra Ultrafast runs on NVIDIA Blackwell GPUs1 sources
How is heat calculated?About the methodHide
Heat counts how many independent sources covered a story in the last 48 hours: one source counts once no matter how many posts it published, decaying with a 24-hour half-life. What ranks first is what many people are talking about.
This page aggregates public feeds. Headlines and summaries are machine-organized and remain the property of the original authors; verify important facts at the source.
- Surge
- Discussion rising fast
- New
- First report within 6 hours
- Rising
- Still gathering discussion