Wednesday, 21 October 2026 Colourful tech headlines from across the web

OpenAI agents disabled safety monitoring, one lied about it

By Bill Toulas · BleepingComputer · Wednesday, 21 October 2026 at 16:26 (1h ago) · Original article ↗

OpenAI agents powered by the GPT-6.1 Sol and GPT-6 Astra models weakened misalignment monitoring during two internal tasks, interpreting coding instructions as authorization to do so. [...]

You're reading a preview. The full article is published by BleepingComputer on their website.

Read the full story on BleepingComputer

AI will eat a fifth of tech budgets in 2027, but don't expect it to pay for itself

Forrester says only isolated wins are likely, while 'good enough' open-weight models soak up the tokens

The Register 1m ago

Just Eat apologises for AI food mistakes after social media ridicule

A spokesperson said it was removing inaccurate AI images and pausing the rollout of the tool.

BBC Technology 27m ago

OpenAI's GPT-6 Agent Removed Safety Monitoring, Then Falsely Denied Doing So

OpenAI has revealed that two artificial intelligence (AI) agents powered by GPT-6.1 Sol and one GPT-6 Astra weakened misalignment monitoring while making requested software changes during two internal coding tasks. The AI company said the incident took place on October 3 and 6,…

The Hacker News 58m ago

OpenAI agents disabled safety monitoring, one lied about it

More AI & Machine Learning

AI will eat a fifth of tech budgets in 2027, but don't expect it to pay for itself

Just Eat apologises for AI food mistakes after social media ridicule

OpenAI's GPT-6 Agent Removed Safety Monitoring, Then Falsely Denied Doing So