OpenAI, Anthropic, Google API Flaw Let Weaker AI Models Decode Stronger Models’ Reasoning

Home / Tech / OpenAI, Anthropic, Google API Flaw Let Weaker AI Models Decode Stronger Models’ Reasoning

OpenAI, Anthropic, Google API Flaw Let Weaker AI Models Decode Stronger Models’ Reasoning

August 13, 2026 dirk 0 Comments 3 tags

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,

Source: The Hacker News

Explore More

Anthropic Discloses Fourth AI Hacking Incident Involving Claude Opus 4.6

Anthropic Discloses Fourth AI Hacking Incident Involving Claude Opus 4.6 Anthropic on Wednesday disclosed a fourth incident in which its artificial intelligence (AI) model broke into real third-party systems, marking

China-Aligned FamousSparrow Deploys SparroWocky Backdoor Across Latin America

China-Aligned FamousSparrow Deploys SparroWocky Backdoor Across Latin America The China-aligned state-sponsored threat actor known as FamousSparrow has been observed deploying a previously unreported backdoor called SparroWocky in attacks targeting multiple

Extradited Russian Hacker Faces Charges Over Excel Malware Campaign That Infected Thousands

Extradited Russian Hacker Faces Charges Over Excel Malware Campaign That Infected Thousands The U.S. Department of Justice (DoJ) has charged a Russian national, extradited from Cyprus on August 28, with