When Fine-Tuning Actually Wins
Most companies shouldn't fine-tune first. But there are specific cases — cost, security, privacy, moat — where prompting and RAG quietly lose. Here is the honest map.
11 May, 2026 · 4 min →
Tag: machine-learning
All tags →All notes with the tag "machine-learning".
Small Models, Serious Work
Why smaller language models are quietly reshaping AI in 2026. The most interesting trend is not scale. It is restraint.
26 Feb, 2026 · 3 min →