return2ozma@lemmy.world to Technology@lemmy.worldEnglish · 2 个月前Anthropic says its latest AI model is too powerful for public release and that it broke containment during testingwww.businessinsider.comexternal-linkmessage-square154fedilinkarrow-up1318arrow-down158
arrow-up1260arrow-down1external-linkAnthropic says its latest AI model is too powerful for public release and that it broke containment during testingwww.businessinsider.comreturn2ozma@lemmy.world to Technology@lemmy.worldEnglish · 2 个月前message-square154fedilink
minus-squareparaphrand@lemmy.worldlinkfedilinkEnglisharrow-up4·2 个月前Whoops, I conflated it with other recent talk about their models not following restrictions set in prompts and deciding for itself that it needed to skirt instructions to achieve its task. You are correct.
Whoops, I conflated it with other recent talk about their models not following restrictions set in prompts and deciding for itself that it needed to skirt instructions to achieve its task.
You are correct.