Large Language Models

3 posts on this thread

Oct 17, 2025Field note

Samsung's Tiny Model Made Scale Look Wasteful

Samsung's 7-million-parameter TRM beat much larger models on specific reasoning benchmarks by revising its answer up to 16 times.

Oct 15, 2025Data note

I use Claude Haiku for small refactors, review, and debugging. Its lower cost and faster responses matter more there than deeper reasoning.

Apr 14, 2025Data note

A leaked OpenAI lineup showed five models, but the mini and nano pricing mattered more to me than another flagship.

Keep exploring