• futatorius@lemm.ee
    link
    fedilink
    English
    arrow-up
    7
    ·
    2 days ago

    LLMs often use bizarre “reasoning” to come up with their responses. And if asked to explain those responses, they then use equally bizarre “reasoning.” That’s because the explanation is just another post-hoc response.

    Unless explainability is built in, it is impossible to validate an LLM.