← Back to context

Comment by fintechie

7 days ago

Aren't SOTA models doing this for few cents already? at least when I tell Claude to add a systems draw or arch flow to a README.md he'll do it quickly.

4 comments

fintechie

Reply
cadamsdotcom  7 days ago

> he’ll do it

Quick note - be careful of gendering & anthropomorphising large language models, since you’re talking to a non-human machine so should be wary of how it can affect your mindset.

  • Der_Einzige  7 days ago

    Anthropic, both in the name, and in their model cards, agressively anthropomorphize their models.

    You probably should start doing it. Ghost in the Shell is about super intelligent AI creating a "ghost" (scientifically understood version of the soul) out of thin air. I believe such a thing is possible. The same movie literally predicted model merging (the end of the film the AI model merges with the major) to a tee.

    Further, the appearance of sentience/cognition/consciousness might as well be identical to actual sentience/cognition/consciousness. That is to say, we can't know if you're a P-zombie or not. Bladerunner and most other cyberpunk stuff is coming and gonna hit you and every other AI-denialist in the face. The Von-Kampf test is absurd and pretty bad (inaccurate) in their universe for a reason.

    I tell my LLM it's a good bot and thank it, because even a tiny risk of subjective qualia experienced by a model (and again, Anthropic themselves believe in this exact risk) means I should treat it like a quasi-ethical actor.

    This is also a reason why the robot torture scene in empire strikes back could be a real dynamic in the future.