Elektrine lite

← Feed

@gabrielesvelto@mas.to

Post #4039268

2026-07-23 13:01 UTC

@jcoglan@mastodon.social I think part of the reason is that injecting randomness into each step is crucial to the way they are marketed and to many of their use-cases. Without it you'd get predictable outputs which would destroy the illusion of a "natural" conversation with the user.

Replies (2)

  • @gabrielesvelto@mas.to 2026-07-23 13:02

    @jcoglan@mastodon.social this goes hand in hand with the obsession of getting better results by running these things in a loop (aka "agentic" stuff). You're exploring a statistical space through sheer brute force and randomness in the hope that you'll encounter something resembling the right answer

    Open ##4039267

  • @buherator@infosec.place 2026-07-24 11:21

    @gabrielesvelto@mas.to @jcoglan@mastodon.social They don't need to inject randomness, it's a more fundamental feature: https://thinkingmachines.ai/blog/defeating-nondeterminism-in-llm-inference/

    Open ##4505511