News for hackers. Stuff that matters.
Re:Clef: Open-source decision models, and new RL fine-tuning... by jMyles on Thursday October 01, 2026 @01:28PM (#49924562)
Came directly to comments hoping not to see this one.

<sad trombone sound>

Surely someone will soon do what the title of this post makes it seem like cloudfare did. Truly modular open source training and inference logic, along with a totally open corpus and weights, will eventually out-compete the closed ecosystem.

Re:Clef: Open-source decision models, and new RL fine-tuning... by ainch on Thursday October 01, 2026 @04:35PM (#49926764)
There are some groups doing it for LLMs - like the Allen Institute for AI's Olmo models and Eluether AI's Pythia.