6 comments

  • realxrobau an hour ago

    Can you please have a human rewrite this so it makes sense. Why does echo $SHELL mean that it's an AI?

      tom_ 35 minutes ago

      The elided part is presumably some command that the llm was coaxed into inserting, even though it'd make no sense to do that and a human operator just wouldn't.

      joshuaissac 35 minutes ago

      It could be the "self-extradition command", as they call it, that exposed it, rather than echo $SHELL.

  • joshstrange 27 minutes ago

    I'm confused on how they "made it work for us", they seem to have only observed what it did. From the title I assumed they found a way to use the model to follow their own prompts or similar.

  • timfsu 20 minutes ago

    In my testing, models don't really know their own name - I would be very suspicious of --model actually revealing the real model name

  • throwa356262 33 minutes ago

    So random script hits their network and suddenly !! free PR !! after some really questionable assumptions and conclusions from their side?