Anthropic’s new AI model threatened to reveal engineer's affair to avoid being shut down
-
This post did not contain any content.
-
This post did not contain any content.
*because that’s what the prompt they were testing was designed to elicit.
-
This post did not contain any content.
That's just an ad.
-
This post did not contain any content.
Good thing no one found out! /s
-
This post did not contain any content.
-
This post did not contain any content.
Anthropic keeps pulling this bullshit line of advertising. LLMs will make up stories when you ask them to.
-
*because that’s what the prompt they were testing was designed to elicit.
wrote on last edited by [email protected]yup.
its so bs thad for som reason the peeps r treatin this as if its a new thing...
like - if i prompt my qwen to be bold, have a moral compass n take actions accordin to thad..
yea - itll tell peeps bout my affair.. ~if~ ~i~ ~had~ ~one..~
EDIT: dis entices me to do similar bs now... thad be funi >v<
-
This post did not contain any content.
What is even the point of this research?
-
What is even the point of this research?
Seemingly to prove the people who have the skill to build an AI system are exactly the people you shouldn’t let run an AI system.
