build1 publisher
Researchers Show Encrypted Reasoning Blocks From OpenAI, Anthropic and Google Can Be Decrypted Using a Weaker Sibling Model
A dev.to writeup credits researchers with decrypting 10,000 reasoning traces from OpenAI, Anthropic and Google models for about $720, and the storage question behind that claim sits in the API example the post itself prints.
Publishers:dev.to
Reality
- Evidence15
- Adoption
- Insufficient
- Hype gap+68
- Incentives58
- Confidence18