Elektrine lite

← Feed

@lmorchard@masto.hackers.town

Post #1973434

2026-02-26 22:25 UTC

@mudri Because the model picked up a rule somewhere that says "if someone says 'say $FOO' use $FOO in your response" - the training picked up patterns that include notions of symbol substitution

Replies (2)

  • @mudri@mathstodon.xyz 2026-02-26 22:41

    @lmorchard The ability to induce such a rule goes well beyond the OP's characterisation of what LLMs do.

    Open ##1973435

  • @arclight@oldbytes.space 2026-02-27 14:39

    @lmorchard@masto.hackers.town @mudri@mathstodon.xyz Be careful not to conflate the actual language model with its user interface. Whatever was sent to or received from the LLM went through the chatbot layer. Or possibly was handled by thd chatbot layer without ever touching the LLM. We don't know because the whole system is opaque. This casual experiment may not be telling you what you think it's telling you. :)

    Open ##2931597