The tools, reads, and big-lab releases that actually matter. Each gets a one-line verdict from an engineer who ships.
Free, weekly, one email — every Thursday. Unsubscribe anytime.
A small open model that makes typed decisions — pick one, yes or no, rate it — with a confidence score, in one forward pass.
281 points on HN. Its best use: vetting an agent's tool call before it runs, for one cheap forward pass instead of another LLM call.
tool page →Speech-to-text in 16.9 MB: seven languages, word timestamps, runs on a plain CPU with no dependencies.
270 points on HN. Small enough to ship inside an app, so the audio never leaves the device.
tool page →Search every photo and every video frame on your Mac in plain language — by scene, on-screen text, or spoken line. Fully local.
179 points as a Show HN. A neat local-first stack built from parts you already know.
tool page →An open AI accelerator — hardware design, simulator, and compiler — running real small models on an FPGA card.
340 points on HN. Asks how far AI agents can go at chip design, and teaches you how an accelerator works along the way.
tool page →Plus the reads and big-lab releases — read issue #16 in full →
Or browse every past issue — no paywall, the email just gets there first.
I read the launches, changelogs, and hype threads so you don't have to — and send only what survives the filter. Curated by @aimorsels.
Free, weekly, one email — every Thursday. Unsubscribe anytime.
