OpenAI, Anthropic, Google API Flaw Let Weaker AI Models Decode Stronger Models' Reasoning
This story is only covered by news sources that have yet to be evaluated by the independent media monitoring agencies we use to assess the quality and reliability of news outlets on our platform. Learn more here.2 Articles
2 Articles
OpenAI, Anthropic, Google API Flaw Let Weaker AI Models Decode Stronger Models' Reasoning
A newly disclosed flaw in the way OpenAI, Anthropic, and Google carried hidden AI reasoning between API calls let researchers recover internal reasoning and secrets from session logs, including API keys and passwords. The weakness affected encrypted reasoning objects used by the providers' reasoning APIs, where a block created in one session could be replayed into another and, during testing, This article has been indexed from The Hacker News R…
Researchers have read internal Reasoning data from AI models such as GPT-5 and Claude Opus. Since all models of a provider use the same key, weaker models can also decrypt this data. However, these are not sufficiently secured and output the data in plain text.
Coverage Details
Bias Distribution
- There is no tracked Bias information for the sources covering this story.
Factuality
To view factuality data please Upgrade to Premium
