LIVE WIRE
Beatpost
THE TLDR EDITION
BUSINESSTechCrunch·3d ago

Researchers used Anthropic’s Claude to hack into OpenAI

BUSINESSBEATPOST
AI TLDR · GEMINI

Security researchers used Anthropic’s Claude to exploit vulnerabilities in OpenAI’s systems. The exploit allowed researchers to take over employee accounts and access an internal code repository. All flaws were reported to OpenAI after the vulnerabilities were identified.

Security researchers used Anthropic’s Claude to exploit vulnerabilities in OpenAI’s systems, taking over employee accounts and gaining access to an internal code repository before reporting the flaws.

SHARE THIS STORY

READ NEXT

More on the wire

culture14m ago

FROM THE PUBLISHER

Dart grabbed his knee in pain after being hit by two Rams defenders

CBS Sports
politics41m ago

FROM THE PUBLISHER

A new analysis found California to have one of the highest electricity prices in the whole country — more than double the national average.

NY Post - Politics
business56m ago

FROM THE PUBLISHER

While Corgi works on conquering San Francisco (and perhaps its aroma and door-handle issues), LeBlanc’s search for a cofounder of a more personal variety appears to be moving right along.

NY Post - Politics

HEADS UP · COOKIES

We use anonymous analytics and (with your OK) session recordings to make Beatpost better. Read the details.

INSTALL THE APP

Install Beatpost

One tap to keep your city's wire on your home screen — no store, no login.