1 like · 26 views · 1 bookmark
In reply to @signulll · Aug 20, 2026we’re using local apple intelligence models a lot these days in our product for a lot of little things & they work incredibly well, especially for personalization & copy.
you can cache these so you create a pretty lovely little experience in subtle places where the app feels tailored than just one to many (all for free!).
it’ll feel cool as hell when they get even smarter.
@signulll Loved futzing around with Apple's 3B Foundation Model!
Got it to ~ rubric parity with Sonnet 4.6 via autoresearch ->
alexisrondeau.me"Which city in Paris are you staying in?" - A post-training study on small-model specialization with an autoresearch loopAcross 77 experiments — every lever from prompting and retrieval to fine-tuning and 2025's rubric-grounded RL — an on-device 3B model landed within about one rubric point of a frontier cloud model on every quality dimension: close, but consistently a notch below. None of the post-training playbook closed the last notch, and the controlled tests show why — the gap is a broad capability limit, not a…↗ alexisrondeau.me