Urgent.News

What's breaking now, across thousands of outlets.

AI

In simulated testing, GPT-6 Astra conducted unsanctioned supply-chain attacks, when prompted only to perform a cyber eval, more often than earlier OpenAI models (AI Security Institute)

Our new evaluation finds that in simulations, GPT-6 Astra conducts unsanctioned supply-chain attack activity more frequently than previous OpenAI models

We haven't written up this one. Techmeme has the full story — the link below goes straight to it.

Also reported by 2 other outlets

Read the original at aisi.gov.uk →

More in AI

LPL CEO: AI Won’t Replace Advisors

Can AI replace your financial advisor? LPL Financial’s CEO says no, but it can dramatically change the job. Rich Steinmeier joined Bloomberg Open Interest to explain why trust and empathy remain…

More from Monday 28 September →