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

Amazon ScienceResearch

Speeding up language models for travel applications

10.29

Travel platforms serve millions of daily users by answering questions about destinations, offering hotel recommendations, and helping users plan their trips.

Read at Amazon Science ↗

One letter a week, starting soon.

Latest

Speeding up language models for travel applications

More from Amazon Science on Accept All

ResearchBetter speech synthesis for audiobooks Amazon Science

ResearchThe science behind TorchNeuron, Amazon’s new PyTorch backend for AWS Trainium chips Amazon Science

ResearchStrengthening AI safety evaluation through independent third-party review Amazon Science

ResearchCan we change an AI model’s architecture without retraining it from scratch? Amazon Science

ResearchGraph-centric agentic intelligence Amazon Science

ResearchA kernel-centric path to real-time video generation on Trainium Amazon Science