AI Can't Care

(mooreds.com)

35 points | by mooreds a day ago ago

9 comments

  • spacebacon a day ago ago

    Correct. LLMs are technically semiotic infrastructure. Empirically proven with computational semiotics.

    • trumpdong 10 hours ago ago

      You keep commenting this everywhere. Does it mean anything or did a long LLM session tell you that?

    • sublinear a day ago ago

      Yes, and I think some people forget that the whole point of an application is to make that semiotic infrastructure into a coherent system.

      LLMs are a great tool, but their misuse is delusional. We need to make a lot of tiny decisions that cannot be delegated away so easily and carelessly for those applications to work properly.

      The push for AI just puts a spotlight on this decades-long power struggle to prioritize which decisions are more important. This isn't a new thing at all. I really wish people would get their heads out of the sand and open their eyes to the crumbling of the institutions they should be defending with a clearer mind. This isn't about human vs machine. This is about quality of results.

  • willtemperley 17 hours ago ago

    In a sense they do care. Anthropic / OpenAI care that your projects are successful because that means more revenue for themselves. Therefore, their models are designed to care that your products work.

    • mooreds 5 hours ago ago

      That's fair. The companies do care about building a sustainable business. But so do the companies that sell lawnmowers.

      I'm not sure that make either thing being sold (LLMs or machines to cut grass) able to care.

      • willtemperley 5 hours ago ago

        Not yet. Wait ‘til lawnmowers have LLMs installed.

    • ultrarunner 16 hours ago ago

      It seems to me the incentive, if anything, is to make the codebase so complex and “write-only” that developers become entirely dependent on LLMs to make any change whatever. They care that you keep burning tokens, not that those tokens accomplish anything for you.