Toot

Written by Yogi Jaeger on 2025-01-27 at 12:00

Remember: "reasoning models" aren't reasoning. They just incorporate additional reinforcement learning after brute force training data fitting.

It's just a different kind of #AlgorithmicMimicry

https://arxiv.org/abs/2307.07515

=> More informations about this toot | View the thread | More toots from yoginho@spore.social

Mentions

Tags

=> View algorithmicmimicry tag

Proxy Information
Original URL
gemini://mastogem.picasoft.net/toot/113900206349261232
Status Code
Success (20)
Meta
text/gemini
Capsule Response Time
232.197162 milliseconds
Gemini-to-HTML Time
0.369624 milliseconds

This content has been proxied by September (3851b).