The name is the button.

An agent writes the code now, and a human thumb hovers over Accept all a hundred times a day. The honest question of this decade is what, exactly, you just accepted. So I read the diff.

Eight years as a backend engineer in Stockholm, back in Tokyo since 2023, and I still ship something small most nights, usually badly. My one rule: the only real review of a model is the thing you built with it. That is why there is no leaderboard on this site.

Around a hundred and forty sources come through — the labs' own posts, the papers, the tools, the runtimes and languages nobody is watching yet, the chip under the demo, and the newsletters people actually forward. What is moving gets counted so the week reads at a glance, and every few days I explain one mechanism in plain words.

A story here is a headline, a short excerpt, one image and the link to whoever wrote it. We never reproduce the post; the images belong to their authors. A post written in Japanese appears in Japanese, exactly as it was published, and the link goes to the original.

— Yuki Halvorsen, Tokyo

← Accept All Archive

Hacker News (front)GitHub

Progress on provable inference for large language models

11.04

Article URL: https://www.anthropic.com/research/provable-inference Comments URL: https://news.ycombinator.com/item?id=50368626 Points: 151 # Comments: 75

Read at Hacker News (front) ↗

One letter a week, starting soon.

Latest

Progress on provable inference for large language models

More from Hacker News (front) on Accept All

GitHubAMD expects to outsell Intel in Q4 for the first time in history Hacker News (front)

GitHubKimi K3.1 Pro model weights are out Hacker News (front)

GitHubAI is forcing us to pay off 40 years of technical debt Hacker News (front)

GitHubIncident with Pull Requests, Git Operations and Issues Hacker News (front)

GitHubNvidia RTX Spark encrypted firmware slows inference speed to 35% on Linux Hacker News (front)