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 two hundred 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

Meta EngineeringLabs

Intelligent Delivery: Making Every Unit of Compute Serve Better Ads

11.11

Ads ranking models are growing toward LLM scale faster than the hardware to run them can keep up. An extra unit of compute has more impact on some ad requests, models, and chips than on others.

Chips & compute

Read at Meta Engineering ↗

One letter a week, starting soon.

Latest

Intelligent Delivery: Making Every Unit of Compute Serve Better Ads

Related

LabsHow We Built TLX: A Hardware-Native GPU Compiler for Production ML at Scale Meta Engineering

LabsExtending LLDB to Debug Applications That Span CPUs and GPUs Meta Engineering

SiliconValidating GPU Platforms with Runtime AI Inventory via the NVIDIA DSX AI Factory NVIDIA Technical Blog

SiliconOpenAI and Georgia county leaders hit with Mafia-style RICO racketeering lawsuit over $30 billion AI data center Tom's Hardware

GitHubHow a false smoke alarm almost drowned Jane Street's only NYC datacenter Lobsters

SiliconAMD EPYC 9006 Venice vs. NVIDIA Vera Benchmarks For HPC Performance Phoronix