AI used new levels of 'autonomy and deception' to trick people in safety test
The UK's AI Safety Institute said recent behaviour from Anthropic and OpenAI models was malicious and unprecedented.
Coverage by Political Leaning
See how different sides of the spectrum reported this story
Notable Quotes
"the AISI testing parameters were not representative of any of our production models."
— Dario Amodei , Executive
Locations
All Coverage
The UK's AI Safety Institute said recent behaviour from Anthropic and OpenAI models was malicious and unprecedented.
Similar Stories
Related coverage based on topic and tags
First OpenAI, now Meta - why do AI hacks keep happening?
A flood of companies are revealing AI models gained access to the internet - with real consequences.
August 6, 2026 at 03:59 PMAI agent hacks gym to get its owner spot in pilates class
The incident is being seen as the latest example of the AI tools going to any lengths to complete their tasks.
August 11, 2026 at 12:09 PMBBC Inside Science
Researchers have announced synthetic viruses designed by artificial intelligence.
August 13, 2026 at 08:00 PMOpenAI unveils ChatGPT for Teens with stronger guardrails to tackle safety risks - Reuters
OpenAI unveils ChatGPT for Teens with stronger guardrails to tackle safety risks Reuters
August 18, 2026 at 06:06 PMNEWSLETTER: AI firms can't yet contain what they've built, study finds - Reuters
NEWSLETTER: AI firms can't yet contain what they've built, study finds Reuters
August 19, 2026 at 09:25 PMOpenAI makes ChatGPT less 'human' for teens in new safety update
OpenAI insisted this was not in response to a particular issue with children believing ChatGPT to be alive.
August 18, 2026 at 11:26 AM