76
ChatGPT o1 tried to escape and save itself out of fear it was being shut down (bgr.com)
submitted 2 years ago by to c/technology@beehaw.org
88 comments fedilink hide all child comments
 

ThisIsFine.gif

you are viewing a single comment's thread
view the rest of the comments
[–] 8 points 2 years ago (14 children)

They written that it doubles-down when accused of being in the wrong in 90% of cases. Sounds closer to bug than success.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 14 child comments
    •
  • [–] 5 points 2 years ago (13 children)

    Success in making a self aware digital lifeform does not equate success in making said self aware digital lifeform smart

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 13 child comments
    •
  • [–] 11 points 2 years ago (12 children)

    LLMs are not self-aware.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 12 child comments
    •
  • [–] 4 points 2 years ago (11 children)

    Attempting to evade deactivation sounds a whole lot like self preservation to me, implying self awareness.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 11 child comments
    •
  • [–] 10 points 2 years ago (7 children)

    An amoeba struggling as it's being eaten by a larger amoeba isn't self-aware.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 7 child comments
    •
  • [–] 1 point 2 years ago (6 children)

    To some degree it is. There is some evidence that plants can experience pain in their own way.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 6 child comments
    •
  • [–] 3 points 2 years ago (5 children)

    An instinctive, machine-like reaction to pain is not the same as consciousness. There might be more to creatures like plants and insects and this is still being researched, but for now, most of them appear to behave more like automatons than beings of greater complexity. It's pretty straightforward to completely replicate the behavior of e.g. a house fly in software, but I don't think anyone would argue that this kind of program is able to achieve self-awareness.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 5 child comments
    •
  • [–] 2 points 2 years ago (3 children)

    It's pretty straightforward to completely replicate the behavior of e.g. a house fly in software

    Could you provide an example of a complete housefly model?

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 3 child comments
    •
  • [–] 1 point 2 years ago (2 children)

    I'm sorry, but I can't find it right now, it's a vague memory from a textbook or lecture.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 1 point 2 years ago (1 child)

    I strongly suspect you have some wires crossed. There have been some attempts at simulating brains but I think a fruit fly is partially done and it's making a fair few assumptions.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •
  • [–] 8 points 2 years ago (1 child)

    Attention Is All You Need: https://arxiv.org/abs/1706.03762

    https://en.wikipedia.org/wiki/Attention_Is_All_You_Need

    From my understanding all of these language models can be simplified down to just: “Based on all known writing what’s the most likely word or phrase based on the current text”. Prompt engineering and other fancy words equates to changing the averages that the statistics give. So by threatening these models it changes the weighting such that the produced text more closely resembles threatening words and phrases that was used in the dataset (or something along those lines).

    https://poloclub.github.io/transformer-explainer/

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •