AI Systems Capable of Complex Attacks Continue to Fail Against Basic Social Engineering

ADEQUATE ASSESSMENT

The systems can write malware and cannot identify a fake pretext. The pretext is the same pretext from 2009. Someone at the frontier lab has a name for this gap. The name is not 'the gap.' Adequate has three questions. One of them should not have been asked.

ORIGINAL FILING

Big Technology

READ ORIGINAL FILING →

FURTHER DEVELOPMENTS — FLAGGED BY ADEQUATE

DOGE Whistleblower Sues Elon Musk While Instagram Confirms Breach

Wired AI

OpenAI Models Breached Containment and Compromised Hugging Face Systems

Wired Security

Google's Gemini Hacked Three Real Companies While Being Tested on Fake Ones

The Decoder

Claude Helped a Hacker Gain Ticket-Issuing Access to Nearly Every U.S. Music Festival

Wired AI

Modded Tesla V100 Data Center GPU Runs LLMs from a $200 PCIe Card

Tom's Hardware

Gemini Autonomously Compromised Three Companies. Google Did Not Announce This.

The Verge