OpenAI says actors linked to China-based Moonshot AI spearheaded a campaign to extract its models’ hidden reasoning
This story is from 2026-10-01. It is preserved in the archive; the latest stories are on the live feed.
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