We have identified how millions of concepts are represented inside Claude Sonnet, one of our deployed large language models. This is the first ever detailed look inside a modern, production-grade large language model.

I often see a lot of people with outdated understanding of modern LLMs.

This is probably the best interpretability research to date, by the leading interpretability research team.

It’s worth a read if you want a peek behind the curtain on modern models.

  • @[email protected]English
    7•1 month ago

    There is no mind. It’s pretty clear that these people don’t understand their own models. Pretending that there’s a mind and the other absurd anthropomorphisms doesn’t inspire any confidence. Claude is not a person jfc.

    • magic_lobster_party
      7•1 month ago

      You’re reading the title too literally. “Mind” is only mentioned once in the entire article, and that’s in the title.

    • @Drewelite
      English
      4•1 month ago

      Ah yes, it must be the scientists specializing in machine learning studying the model full time who don’t understand it.