Технологии

Making it easier for websites to express AI training preferences

OpenAI will honor a shared robots.txt signal to help website operators communicate their AI training preferences to participating providers.

OpenAI Blog · EN

Qodo builds context into AI code review with Codex

Qodo brings company knowledge and coding standards into Codex, helping developers catch P0 issues across repositories before opening a pull request.

OpenAI Blog · EN

LifeVal

Introducing LifeVal, a benchmark measuring how well AI helps people complete everyday tasks, from finding childcare to managing finances and government paperwork.

OpenAI Blog · EN

Introducing the Grid Protectors Program

OpenAI’s Grid Protectors Program will work with utilities to help future compute campuses support grid reliability and protect consumer electricity costs.

OpenAI Blog · EN

Inside Prometheus: Meta’s Journey to a Gigawatt-Scale Supercluster

With the recent release of the Muse family of foundational models, we want to take you inside the infrastructure that has made it all possible. The first phase of Prometheus, our gigawatt-scale supercluster, is already complete and we’re working toward scaling it to comprise ~1 million GPUs. Prometheus also features technologies like closed-loop liquid cooling [...] Read More... The post Inside Prometheus: Meta’s Journey to a Gigawatt-Scale Supercluster appeared first on Engineering at Meta .

Meta Engineering · EN

The Thin Orchestrator: How We Made Our AI Agents More Reliable by Giving the Router Less to Do

Sometimes, giving an AI agent all of the knowledge it needs is the wrong approach. At Meta, we’ve seen notable improvements in efficiency and accuracy by keeping the orchestration layer of our data pipeline agents deliberately thin: It routes work and enforces reliability checks, while specialized agents do the domain reasoning. We’re sharing our own [...] Read More... The post The Thin Orchestrator: How We Made Our AI Agents More Reliable by Giving the Router Less to Do appeared first on Engineering at Meta .

Meta Engineering · EN

GenRecs Tokenization: Transforming Ads Recommendation at Meta with Stable Model Vocabulary

Generative Recommenders (GenRecs) represent a paradigm shift from scoring every ad to reasoning about ad content and user preferences together in order to predict the best outcome for advertisers. Leveraging the world knowledge built into LLMs makes ad matching more intelligent and precise, compounding gains for advertisers. GenRecs Tokenization is the foundational data representation that [...] Read More... The post GenRecs Tokenization: Transforming Ads Recommendation at Meta with Stable Model Vocabulary appeared first on Engineering at Meta .

Meta Engineering · EN

Meta Networking at the 2026 OCP Global Summit: Open Innovation for Scale-Up, Scale-Out, and Scale-Across AI Networks

At the 2026 Open Compute Project (OCP) Global Summit, Meta shared the networking innovations that are directly supporting our latest AI models, including Muse Wonder and Muse Spark, and our gigawatt-scale Prometheus cluster. Highlights IcePack & IceCube: Meta’s first liquid-cooled network rack with 102.4T switch blades (128×800G, Broadcom Tomahawk 6C and NVIDIA Spectrum-6 variants), running [...] Read More... The post Meta Networking at the 2026 OCP Global Summit: Open Innovation for Scale-Up, Scale-Out, and Scale-Across AI Networks appeared first on Engineering at Meta .

Meta Engineering · EN

Python Typing Survey 2026: AI Tools and the Shifting Checker Landscape

The 2026 Python Typing Survey received 1,794 responses. Type hint use changed little across three years, but checker selection changed sharply. Among respondents who reported which checkers they use, half selected more than one, and missing library type information was the most common difficulty. For the third consecutive year, we asked Python developers how they [...] Read More... The post Python Typing Survey 2026: AI Tools and the Shifting Checker Landscape appeared first on Engineering at Meta .

Meta Engineering · EN

PrivacyLib: Privacy Controls at the Data Access Boundary

This latest deep dive into Meta’s Privacy Aware Infrastructure (PAI) takes a look at PrivacyLib. A privacy requirement must hold as data moves through Meta’s diverse data and processing systems. Historically, supporting a new requirement meant implementing the same enforcement logic separately in each system. PrivacyLib replaces this with a common library that runs inside [...] Read More... The post PrivacyLib: Privacy Controls at the Data Access Boundary appeared first on Engineering at Meta .

Meta Engineering · EN

Meta Andromeda: Powering the Next Generation of Ads Retrieval Through Model-System Co-Design

This post describes the next generation of Meta Andromeda, Meta’s personalized ads retrieval engine, and how co-designing the model, system, and GPU hardware unlocks a new efficiency frontier for ads retrieval. In production, the system scores every eligible ad with near ranking-level model performance at retrieval scale and surfaces the top candidates at over one [...] Read More... The post Meta Andromeda: Powering the Next Generation of Ads Retrieval Through Model-System Co-Design appeared first on Engineering at Meta .

Meta Engineering · EN

Catching Bugs Before They Land: JiTTesting’s Human-on-the-Loop Approach at Full Scale

Over the last year we’ve been sharing our work leveraging large language models to catch bugs on the fly — a novel approach we call Catching Just-in-Time Tests (JiTTests). Now, we’re sharing the results and positive impact we’ve seen with Catching JiTTests deployed into production. Our paper, “Just-in-Time Catching Test Generation at Meta,” fully details [...] Read More... The post Catching Bugs Before They Land: JiTTesting’s Human-on-the-Loop Approach at Full Scale appeared first on Engineering at Meta .

Meta Engineering · EN

Are Harnesses Worth the Cost?

Naresh Jain compares coding agents building the same API service with and without a behavioral harness. A frontier model, GPT-6 Sol, passed every external evaluation either way. But a cost-optimized model, GPT-6 Luna, succeeded in only 3 of 10 unharnessed runs and all 10 with the harness. While adding the harness increased token usage and runtime for Luna, the harnessed Luna runs achieved the same 10-for-10 reliability as GPT-6 Sol while costing 33% less per run ($0.273 vs $0.406). This experiment suggests a behavioral harness might be a practical way to get dependable results from smaller, co

Martin Fowler · EN

The Craft of Practitioner Voice

A couple of months ago Jim Highsmith explained how practitioners writing for each other forms a distinct style of writing. He now adds a section to the article with more detail on the craft of how we write in this style. How the writer shows up in the prose, its four principles, the role of story, how to sensibly use AI, three levels of editing, and clarity of the audience. more…

Martin Fowler · EN

Build your slide template

Building a slide template starts with three foundational choices — colours, fonts and layouts. Sumeet Gayathri Moghe covers the basics of color theory and how to build a reusable palette, the essentials of typography, including serif, sans-serif, handwritten and monospace fonts, plus the finer points of kerning and leading, and why a near-blank layout might serve you better than the prescribed layouts that ship with your slideware. more…

Martin Fowler · EN

When Software Meets Hardware

When software meets hardware, engineering principles remain largely the same, but the sensible defaults often change. Kuldeep Singh describes our experience modernizing a large IoT fleet of battery-powered sensors. Our familiar principles remained important; what changed was how we applied them. These practices emerged through experiments, failures, and operational experience—each challenge helping us replace a reasonable assumption with a more sensible default. more…

Martin Fowler · EN

Fragments: October 21

Gergely Orosz is frustrated at those that entered his explicitly “No AI” essay competition and used AI. He goes on to say: When I start to suspect some part is AI about someone I don’t know: how can I tell how much of it is? And how much time and effort do I want to invest to figure out? I fear most people do not realize this last part: that when it takes time and effort from others to figure out what % is AI, and what % is YOU, then I will simply assume it’s probably 100% AI and 0% you So when producing anything that is meant for other humans, if you use even a little AI, you risk the assumpt

Martin Fowler · EN

Fragments: October 28

Andrej Karpathy sees a widening gap in how people see LLM capabilities. The general public has mostly not interacted with these systems. When they have, it looks like a derpy chatbot. The majority of professionals still see only a modest uplift. And a small sliver of professionals are experiencing the vertigo of the curve going vertical. And it is all happening at the same time. Many of my colleagues are living in a world where LLM capabilities are stunning, but it’s easy to forget that’s not what most people experience. One thing I do is use free-tier LLM chatbots, and I’m still finding that

Martin Fowler · EN

Why are good developers so wary of agentic development?

TL;DR Good developers’ caution about agentic development comes from knowing that built isn’t the same as working in production. I’ve been surprised by how many excellent developers have been hesitant to go all in on coding agents. These are people who usually try new ways of working before anyone else and in many cases invent new tools and practices that support building the application well. So why have we had so much reluctance? The easy (lazy?) answer is that they love writing code, or they’re worried about their jobs. I’m sure that’s true for some people, some of the time. And I know it is

Martin Fowler · EN

Bliki: LLM Voice

Sometimes when I read a post, I get the growing feeling that I'm reading the output of an LLM. I can't necessarily define why, although there are the common tells (it's not the em-dashes, it's the load-bearing tapestries). As I do this my desire to read on atrophies, sometimes to the point of revulsion There are tools out there that claim to be able to tell the difference between LLM-written prose and the old-fashioned biological product. I'm wary of them, partly due skeptism about their accuracy, but also because it rather misses the point. The reaction to LLM-Voice is a human one, that sense

Martin Fowler · EN

Measuring the Impact of Personalized Recommendations

By Kevin Zielnicki, Guy Aridor, Aurélien Bibaut, Allen Tran, Winston Chou, and Nathan Kallus Introduction Personalization is everywhere on the internet. It shapes the products we discover, the stories we read, the music we hear, and the movies and TV shows we watch. At Netflix, personalization has been central to the member experience for decades — from the Netflix Prize to our modern recommender system that helps members navigate a large and constantly changing catalog. But personalization is not only an algorithmic problem, it is also a measurement problem. How do we know how much value pers

Netflix Tech Blog · EN

DataJunction as Netflix’s answer to the missing piece of the modern data stack

by Olek Gorajek , Samuel Redai , Yian Shang Intro Our Netflix journey from data to dashboards, particularly within the space of the experimentation platform, always presented a unique set of challenges. This blog post aims to illuminate these hurdles and explain how an innovative open-source metric platform became instrumental in overcoming some of them. We’ll showcase the critical role that DataJunction played in streamlining our data workflows and enhancing our ability to derive meaningful insights from our vast datasets. Metrics are the foundation of data-driven decision-making, but at many

Netflix Tech Blog · EN

Integrating Netflix’s Foundation Model into Personalization applications

Authors: Divya Gadde , Ko-Jen Hsiao , Dhaval Patel and Moumita Bhattacharya The motivation for building the Netflix Foundation Model for personalization was laid out in this previous blog post. The Netflix homepage is powered by several specialized models and it requires significant time and resources to maintain and continue innovating on these individual models. Therefore, we decided to centralize member preference learning and have one powerful model learned from comprehensive user interaction histories and content data at a large scale and have this model distribute its learnings to other

Netflix Tech Blog · EN

Ontology-Driven Observability: Building an End-to-End Knowledge Graph at Netflix Scale

Prasanna Vijayanathan , Renzo Sanchez-Silva When Jake Paul and Mike Tyson stepped into the ring in November 2024, we delivered the fight to roughly 65 million concurrent streams. On an ordinary day our infrastructure takes in more than 2 billion requests and handles upwards of 38 million real-time logging events every second. At that scale, the whole picture doesn’t fit into a single engineering team’s head or onto a single dashboard. With more Live content, Podcasts and real-time streams, our need to understand and update our systems as quickly as possible becomes imperative to provide a good

Netflix Tech Blog · EN