▲ 255 ▼ Anthropic says its latest AI model is too powerful for public release and that it broke containment during testing (www.businessinsider.com) submitted 7 months ago by return2ozma@lemmy.world to c/technology@lemmy.world 143 comments fedilink hide all child comments
[–] theunknownmuncher@lemmy.world 3 points 7 months ago (2 children) Try clicking the link and reading the article this time permalink fedilink source parent hideshow 2 child comments replies: [–] paraphrand@lemmy.world 4 points 7 months ago* (last edited 7 months ago) (1 child) I wasn’t wrong in this reply. I was asked about believing Anthropic. Are you saying they are lying? Why should I disbelieve Anthropic? permalink fedilink source parent hideshow 1 child comment replies: [–] theunknownmuncher@lemmy.world 3 points 7 months ago* Your reasoning was (paraphrased, so hopefully I understood you correctly) "why would they lie about the model disobeying instructions because that looks bad for them" But I believe Anthropic when they say their models are not working as intended and posing security risks. But when you actually read the article, they had specifically prompted the model to do the things it did. Also Anthropic has a patterned history of greatly exaggerating and outright lying. permalink fedilink source parent
[–] paraphrand@lemmy.world 4 points 7 months ago* (last edited 7 months ago) (1 child) I wasn’t wrong in this reply. I was asked about believing Anthropic. Are you saying they are lying? Why should I disbelieve Anthropic? permalink fedilink source parent hideshow 1 child comment replies: [–] theunknownmuncher@lemmy.world 3 points 7 months ago* Your reasoning was (paraphrased, so hopefully I understood you correctly) "why would they lie about the model disobeying instructions because that looks bad for them" But I believe Anthropic when they say their models are not working as intended and posing security risks. But when you actually read the article, they had specifically prompted the model to do the things it did. Also Anthropic has a patterned history of greatly exaggerating and outright lying. permalink fedilink source parent
[–] theunknownmuncher@lemmy.world 3 points 7 months ago* Your reasoning was (paraphrased, so hopefully I understood you correctly) "why would they lie about the model disobeying instructions because that looks bad for them" But I believe Anthropic when they say their models are not working as intended and posing security risks. But when you actually read the article, they had specifically prompted the model to do the things it did. Also Anthropic has a patterned history of greatly exaggerating and outright lying. permalink fedilink source parent