Mastodawn

LOL now they're blaming sci-fi writers...

Anthropic Says 'Evil' Portrayals of AI Were Responsible For Claude's Blackmail Attempts

https://slashdot.org/story/26/05/11/0437206/anthropic-says-evil-portrayals-of-ai-were-responsible-for-claudes-blackmail-attempts

#AI #AIpocalypse

Anthropic Says 'Evil' Portrayals of AI Were Responsible For Claude's Blackmail Attempts - Slashdot

An anonymous reader quotes a report from TechCrunch: Fictional portrayals of artificial intelligence can have a real effect on AI models, according to Anthropic. Last year, the company said that during pre-release tests involving a fictional company, Claude Opus 4 would often try to blackmail engine...

Show thread

Mason Loring Bliss

@ai6yr This is the best part of the article:

'The company went into more detail in a blog post stating that since Claude Haiku 4.5, Anthropic’s models “never engage in blackmail [during testing], where previous models would sometimes do so up to 96% of the time.”'

Show thread

It'll be okay, we'll make it.5d ago

@mason
Yeah, moving the goalposts isn't a good metric for how an LLM manipulates people. They don't standardize tests, or criteria, so nothing can be trusted. Still evil.
@ai6yr