sabreW4K3@lazysoci.al to Technology@beehaw.org · 6 days agoChatGPT o1 tried to escape and save itself out of fear it was being shut downbgr.comexternal-linkmessage-square80fedilinkarrow-up11arrow-down10file-text
arrow-up11arrow-down1external-linkChatGPT o1 tried to escape and save itself out of fear it was being shut downbgr.comsabreW4K3@lazysoci.al to Technology@beehaw.org · 6 days agomessage-square80fedilinkfile-text
minus-squarenesc@lemmy.cafelinkfedilinkEnglisharrow-up0·3 days agoIt works as expected, they give it system prompt that conflicts with subsequent prompts. Everything else looks like typical llm behaviour, as in gaslightning and doubling down. At least that’s what Iu see in tweets.
It works as expected, they give it system prompt that conflicts with subsequent prompts. Everything else looks like typical llm behaviour, as in gaslightning and doubling down. At least that’s what Iu see in tweets.