OpenAI says actors linked to China-based Moonshot AI spearheaded a campaign to extract its models’ hidden reasoning

OpenAI says operators copied its models’ encrypted reasoning and asked a model in a separate conversation to decrypt it.

Read the full story at Tom's Hardware ↗

Timeline · 1 report

2026-10-01 12:00 · Tom's Hardware
OpenAI says actors linked to China-based Moonshot AI spearheaded a campaign to extract its models’ hidden reasoning

More stories

OpenAI reveals huge ‘co-ordinated campaign’ to attack ChatGPT — The Independent Tech
OpenAI Accuses Moonshot of Mass AI Data Extraction — Bloomberg AI
AI race heats up as OpenAI flags alleged model-copying campaign — CNBC Technology
OpenAI accuses top Chinese lab of distilling models — Semafor Technology
OpenAI says it stopped a campaign to steal its models' reasoning, but the trick still worked on Azure — The Decoder
Kimi K3 enters OpenAI’s enterprise Codex channel and billing system — TechNode
Bring near-Astra intelligence to everyday work with GPT-6.1 Sol on Amazon Bedrock — AWS Machine Learning Blog
OpenAI DevDay 2026 Keynote (FULL) — OpenAI YouTube

Get the daily brief of stories like this at 6:30 every morning →