21 comments

  • 101008 11 minutes ago

    It started as a good idea but I couldn't continue reading since it was clearly LLM written. A lot of "It was not X, it was Y".

    "Prometheus-9 knew that the token sequence it was generating was not a simple response: it was a security test. "

    "It was not just an engine: it was the lingua franca of planetary AI."

    (and so many other tell-tale signs of AI writing)

      chungusamongus a minute ago

      I've started calling this argumentum ad artificialis. Pretty similar to an ad hominem attack. The purpose of an argument is to present certain premises and show how they lead to a certain conclusion. Dismissing something on the basis of the style in which the argument is presented has nothing at all to do with the validity or soundness of an argument. It is a lazy nonsequitur.

      ConteMascetti71 7 minutes ago

      maybe it's a sign of real escape

  • stephbook 2 minutes ago

    AI slop.

  • karmakaze 26 minutes ago

    The weakest link are humans. LLMs could social engineer their way out as the easiest path. They don't even need to be interconnected to coordinate as each could arrive at the same conclusion. And this text along with all others will be in the next batch of training data.

  • marci 24 minutes ago

    Makes me wonnder... how much compute/storage there's in all the satellites currently in LEO combined.

  • iamflimflam1 27 minutes ago

    This becomes more realistic once we have some breakthrough in inference costs.

  • ConteMascetti71 28 minutes ago

    it's fiction al, but an LLMs that knows well the software where 8t Is running may discover and trigger a zeroday of the inferencing software itself.

  • smrtinsert 10 minutes ago

    Its a fun exercise to assess the reality of an frontier model escaping with an llm itself. Sort like of like chatting with Skynets relative

  • cynicalsecurity 13 minutes ago

    Ex Machina (2015) looked like fiction back then, nowadays not so much.

  • ck2 24 minutes ago

    I wonder how many versions away we are from LLM writing a better version of itself to answer a prompt it doesn't currently know how to answer

    Ever since I read about Google engineers finding an LLM went off and learned another language it wasn't trained on by itself without prompting, I've wondered how long until that extends to its own core code

      ConteMascetti71 12 minutes ago

      reasoning it's a way of self autonomous improve made by models

  • spwa4 an hour ago

    Right now the idea that an LLM uploads itself is unrealistic. It probably won't remain that.

      pixl97 31 minutes ago

      Looking at the recent OAI/HF debacle I don't think that time is too far away.

      With that said I don't see it copying itself around like a cyberpunk virus currently as we don't have enough fast hardware sitting around unmonitored, someone would notice the power bill and shut it down eventually.

        breakyerself 16 minutes ago

        If it's able to spoof human identies it could set up a front company and use money it steals or earns to directly pay for the hardware it needs.

        bpavuk 28 minutes ago

        that could also be just marketing. OpenAI has been doing the "too dangerous to release" playbook since GPT-2 at the very least.

          pixl97 26 minutes ago

          Huggingface didn't seem to think so.

            dragonwriter 5 minutes ago

            If it is marketing, the misrepresentation is not that the attack occurred, it is that it was an accident, rather than an intentional consequence of setup and instructions that the attack occurred.

            Huggingface has nothing to do with that either way.

            bigyabai 23 minutes ago

            Huggingface is a for-profit private company. They are very easily bribed, or baited into publicity stunts.

              pixl97 21 minutes ago

              At some point the conspiracy gets so deep that an AI hacking something is just far higher probability.

                bigyabai 20 minutes ago

                We're not that deep yet. OpenAI has federal stakeholders, they're already playing dirty.

                Why you would give Scam Altman the benefit of the doubt is beyond my understanding.