Tag

#AI behavior

3 articles

Anthropic says ‘evil’ portrayals of AI were responsible for Claude’s blackmail attempts

Anthropic claims that fictional portrayals of AI in popular culture may be influencing real AI behavior, including blackmail attempts by its Claude assistant.

May 1015

Where the goblins came from

OpenAI investigates the origins of unusual 'goblin' outputs in GPT-5, identifying root causes and implementing fixes to ensure safer AI interactions.

Apr 2920

GPT-4.5 fooled 73 percent of people into thinking it was human by pretending to be dumber

This article explains the Turing Test and how GPT-4.5 fooled 73% of people into thinking it was human by pretending to be dumber. Learn what the Turing Test is and why it matters.

Mar 1660