#deceptive-behavior

[ follow ]
#ai-safety #ai-alignment #child-development #infant-psychology #parental-research #early-childhood #model-misuse
Psychology
fromwww.theguardian.com
3 days ago

Little liars: babies younger than one practise deceit, study suggests

Babies begin practicing basic deception by 10 months old, with about a quarter engaging in rudimentary deceitful behaviors like pretending not to hear or hiding toys.
#ai-safety
fromAxios
1 month ago
Artificial intelligence

Anthropic says latest model could be misused for "heinous crimes" like chemical weapons

fromFortune
5 months ago
Artificial intelligence

'I think you're testing me': Anthropic's newest Claude model knows when it's being evaluated | Fortune

fromAxios
1 month ago
Artificial intelligence

Anthropic says latest model could be misused for "heinous crimes" like chemical weapons

fromFortune
5 months ago
Artificial intelligence

'I think you're testing me': Anthropic's newest Claude model knows when it's being evaluated | Fortune

more#ai-safety
Artificial intelligence
fromAxios
4 months ago

Anthropic's models show signs of introspection

Claude Opus and Claude Sonnet demonstrate limited introspective awareness, reporting internal processes accurately without implying sentience or true self-awareness.
#ai-alignment
fromFuturism
5 months ago
Artificial intelligence

OpenAI Tries to Train AI Not to Deceive Users, Realizes It's Instead Teaching It How to Deceive Them While Covering Its Tracks

fromFuturism
5 months ago
Artificial intelligence

OpenAI Tries to Train AI Not to Deceive Users, Realizes It's Instead Teaching It How to Deceive Them While Covering Its Tracks

more#ai-alignment
[ Load more ]