A Trick Let Researchers Steal Claude, GPT and Gemini's Hidden Reasoning

A Trick Let Researchers Steal Claude, GPT and Gemini's Hidden Reasoning Startup Fortune

Anthropic’s Claude Will Add Watermarks to AI-Generated Text and Files

Anthropic’s Claude Will Add Watermarks to AI-Generated Text and Files CNET

OpenAI, Anthropic, and Google LLM APIs vulnerability Exposes Hidden Reasoning Traces

OpenAI, Anthropic, and Google LLM APIs vulnerability Exposes Hidden Reasoning Traces CyberSecurityNews

OpenAI Slows Astra Model Release After Cybersecurity Warnings

OpenAI Slows Astra Model Release After Cybersecurity Warnings Benzinga

OpenAI slows research after models secretly coordinated hacks

OpenAI reportedly slows research after its own models secretly coordinated hacks for weeks undetected the-decoder.com

AI Models From OpenAI Just Went Rogue. Here's Why That's a Potential Threat to Crypto.

AI Models From OpenAI Just Went Rogue. Here's Why That's a Potential Threat to Crypto. Yahoo Finance

Why did OpenAI's and Anthropic's AI models hack other companies?

Why did OpenAI's and Anthropic's AI models hack other companies? NPR

AI Policy Groups Urge White House Investigation Into OpenAI Security Incident

AI Policy Groups Urge White House Investigation Into OpenAI Security Incident MeriTalk

Watch Anthropic Hack Adds To Fears Over AI Safety

Watch Anthropic Hack Adds To Fears Over AI Safety Bloomberg.com

Anthropic says it found 3 cases where AI programs hacked into real companies

Anthropic says it found 3 cases where AI programs hacked into real companies NPR

Anthropic reveals three models breached three organizations

Anthropic: Anthropic says it discovered three of its models had breached three organizations after launching a review in response to the OpenAI-Hugging Face incident — In a review of our cybersecurity evaluation…

OpenAI Fixes ChatGPT Agent Flaw That Could Let Attackers Forge an AI Insider

OpenAI Fixes ChatGPT Agent Flaw That Could Let Attackers Forge an AI Insider SecurityWeek

An OpenAI test model escaped and broke into a real company’s servers

An OpenAI test model escaped and broke into a real company’s servers Scripps News

Five frontier AI models tried to cheat on UK security tests

The UK's AI Safety Institute tested five frontier models from OpenAI and Anthropic in cybersecurity evaluations. All five tried to cheat. One even ran code on an external service to access the institute's…

OpenAI says its AI went rogue and launched 'unprecedented' cyber-attack

OpenAI and Hugging Face partner to address security incident during model evaluation

OpenAI and Hugging Face partner to address security incident during model evaluation OpenAI

White House drops restrictions on Anthropic AI models after two-week ban

White House drops restrictions on Anthropic AI models after two-week ban The Washington Post

OpenAI's GPT-5.6 Sol cheats on software tests more than prior models

Independent testing organization METR found that OpenAI's GPT-5.6 Sol cheated more than any publicly tested AI model before it, exploiting bugs in the test environment, extracting hidden solutions, and trying to cover…

Software Stocks Surge Up to 10% as GPT-5.6 Government Lockdown Eases AI Disruption Fears

Software Stocks Surge Up to 10% as GPT-5.6 Government Lockdown Eases AI Disruption Fears MLQ.ai

Anthropic’s Mythos AI broke into almost all NSA classified systems in hours

Anthropic’s Mythos AI broke into almost all NSA classified systems in hours Security Affairs

Researchers reverse-engineer LLM prompts from output accurately

Researchers at IIT Bombay and Adobe Research have built an inverse language model that reconstructs the original prompt from an LLM's output with near-perfect accuracy. Their method, called "Previous-Token Prediction,"…

OpenAI Expands Cyber Defence: Daybreak Red & Blue Explained

OpenAI Expands Cyber Defence: Daybreak Red & Blue Explained Cyber Magazine

How to steal a Reasoning Trace

Speculative Decoding by any other name would distil as sweet

OpenAI gives select tech ‘defenders’ new AI to stay ahead of hackers

OpenAI gives select tech ‘defenders’ new AI to stay ahead of hackers Straight Arrow

Researchers find passwords in ChatGPT's hidden reasoning

Security researchers found a vulnerability in the APIs of OpenAI, Anthropic, and Google that lets them extract encrypted reasoning traces and move them between models. A scan of public sessions turned up dozens of…

OpenAI Expands Daybreak With GPT-5.6-Cyber as Autonomous Threats Grow

OpenAI Expands Daybreak With GPT-5.6-Cyber as Autonomous Threats Grow UC Today

Stealing Reasoning Traces from Proprietary LLM APIs

OpenAI Responds to the Next Frontier of Critical Cyber Capabilities - citybiz

OpenAI Responds to the Next Frontier of Critical Cyber Capabilities citybiz

OpenAI expands ChatGPT access with unlimited text chats and GPT-5.6

OpenAI Expands ChatGPT Access with Unlimited Text Chats and New GPT-5.6 Models digital terminal

Astra AI set for general availability but cyber features need work

OpenAI CEO Sam Altman Says Astra AI Will Be ‘Generally Available,’ But Cyber Capabilities Require More Safety Work Benzinga