
When Can LLMs Replace Humans in A/B Tests?
TL;DR: LLM predictions can stand in for human outcomes in A/B tests, but only by assumption, not by design....
1,015 articles on AI & ML.

TL;DR: LLM predictions can stand in for human outcomes in A/B tests, but only by assumption, not by design....

Meet Vercel’s winter 2026 interns and see how they shipped production features across the CDN, v0, financial infrastructure, AI Gateway, and more.

Learn how to write your first prompt in the GitHub Copilot app, choose the right context and model, and start your first task with confidence.

We built a software factory that autonomously processes issues and PRs for the AI SDK, with humans in control of every merge. Four weeks in, it authors 25-40% of merged PRs.

The Figma Data Science team assumed that AI saves users time—but quantifying it required a new approach to research design.

AI companies are undergoing rapid global expansion while achieving unprecedented rates of growth. We analyzed Stripe data to understand where global demand is the strongest, and how companies can build to best capture that demand.

The AI Gateway production index covering data from July 2026: DeepSeek became the second-largest lab by token volume; Anthropic held 65% of spend at more than twice the average price per token

Enterprise Java developers have a new superpower—drive GitHub Copilot from idiomatic Java code with annotations, virtual threads, and more.

Cloudflare is unifying AI Gateway and Workers AI into a single control plane, giving developers observability, billing, and dynamic routing across both managed GPUs and external providers. Learn how unified bindings and model-first routing simplify building resilient AI applications.

Cloudflare Radar Researcher is a new AI-powered tool that lets you explore global Internet trends and traffic data using plain language. Built entirely on Cloudflare's Developer Platform, it turns natural language queries into real, interactive charts.

More than half of requests now come from machines, not people. Agent Readiness shows how well agents can discover and read your site, while Answer Engine Optimization tracks how often AI assistants recommend you.

Today we're launching a developer preview of WebMCP on Cloudflare. With one switch, any site becomes usable by browser AI agents — no new APIs, no origin changes — while the human stays in control and creators keep their traffic.

AI Search makes search easier than ever, with no Cloudflare primitives to stitch together. Point it at your data to create a search for your own files and websites. We're also sharing a preview of our new pricing model.

We should be giving all agents tools that excel at what’s important for an AI model. Kitesurf is Cloudflare’s new stateless, highly scalable, and cost-effective web browser that runs entirely on top of Workers and was designed specifically for the Agentic Cloud.

Go beyond chat in the GitHub Copilot app with these slash commands. They’ll help you plan, collaborate, automate, and customize your dev workflow.

Agent Plugins 1.0.0 is an open, vendor-neutral specification for packaging Agent Skills and MCP servers into distributable plugins that compatible AI agent clients can discover and load.

Identity-aware AI Gateway is now in open beta. User Insights turns that traffic into a behavioral baseline for every person and agent, and flags insider risk the moment it appears.

We built Cloudflare OS to equip our teams to safely rethink how they get work done with AI. The platform brings together the best of our technologies, from our Compute primitives to our Zero Trust suite. This post walks through our journey to give our users the best AI tools available.

Cloudflare Wallets will provide AI agents with native payments and verifiable identity on the web. Using the x402 protocol, agents can autonomously purchase APIs and content within clear safety guardrails.

We created the Cloudflare Codex, a governed body of engineering standards that AI agents consume across the development lifecycle. By pairing structured RFCs with agentic reviews, teams automatically enforce consistency across code, specs, and incident reports.

By replacing manual issue verification with isolated AI subagents running in GitHub Actions, the Astro maintainers reduced open issue count by 85%. This post explores the architecture behind automated bug reproduction, patch verification, and preview releases.

Learn how to build tools to simplify how you work—without writing a single line of code.

Instead of one huge, un-reviewable pull request, teach coding agents to decompose work into a clean, ordered stack with GitHub stacked pull requests.

Meta’s Generative Ads Recommendation Model (GEM), the foundation model behind ads recommendations across Instagram and Facebook, now trains at LLM scale on several thousand of the latest-generation GPUs. This post goes into the details on how we achieved: doubling end-to-end (E2E) training efficiency to 20–25% Model FLOPs Utilization (MFU) while scaling training FLOPs 4x in […]

Ninety percent of product builders say AI skills are essential to their future success. But what if we’re focused on the wrong ones?

Learn how I modernized an old codebase of mine using stacked sessions and pull requests in the GitHub Copilot app.

Today we are expanding access to Vercel Agent: an AI agent that safely and autonomously investigates incidents, fixes builds, and reviews PRs on your production

As AI reshapes product design, it could give designers greater autonomy or expose the gaps that autonomy makes harder to hide. Exploring both the bull and bear cases, Andy Budd examines what happens when designers need less permission to act.

Many of the AI tools we interact with take the form of text boxes. But what if there was a different way to interact with AI? Oleksii Hrzhehorzhevskyi explores a different approach to creating a new AI assistant and how designers can navigate the field as AI continues to change it.

Here’s how Figma’s Brand Studio designed a conference that captured the very human ways we remix and reinvent when working with AI tools.

A practical GitHub Copilot workflow for prototyping, planning, implementing, and reviewing software without chasing every new AI tool.

New to the GitHub Copilot app? Learn how to start projects, work with AI agents, explore canvases, and streamline your development workflow.

Nick Bogaty joins Vercel as first Chief Revenue Officer from Adobe, bringing more than 20 years of enterprise GTM experience to lead an AI-forward sales organization.

Copilot now bills usage at listed API rates. Compare direct model access with the coding workflow, policy, and harness work around it.

Canvases turn AI into interactive workspaces where you can visualize information, explore workflows, and take action across complex tasks.

Riviera is the Dropbox content processing platform that’s been iteratively improving content transformation in our products for roughly a decade.


This article explains the approach I used to modernize a Java 1.5 codebase that no longer built reliably on modern machines. My early use of LLMs gave me plausible answers that did not hold up in the codebase. Progress came when I grounded the process in evidence, using AI to support analysis, validation in a stable Docker environment, and gradual refactoring protected by tests. The main takeaway

Hierarchical Interest Representation is a research area for Meta Ads. We’re exploring an upstream representation layer over the universe of Ads entities – users, advertisers, products, services – learning unified embeddings that connect users’ inferred interests with the breadth of what advertisers offer in their deep funnel ads. The innovations in Hierarchical Interest Representation are […] Read

Many companies assume everyone craves new AI features. But the reality is that most people don

TL; DR At Meta’s scale, a few milliseconds of latency degradation can have a significant negative impact on ads performance. When a Linux kernel upgrade risked regressing latency across Meta’s ad serving fleet, we turned to sched_ext — the upstream, BPF-based extensible scheduling framework — to build a scheduling policy customized to the Ads delivery […]

The AI Gateway production index covering data from June 2026: Open-weight models increased to a third of all token volume; Anthropic continues to dominate spend with 61%

How migrating Copilot code review to shared Unix-style code exploration tools reduced review cost by reshaping agent workflows around pull request evidence.

NIST is advancing nine new post-quantum signature algorithms as potential candidates for future standardization. We take a closer look at all of them, and argue that while they are in the works and show great potential, we should use ML-DSA for now — the best one currently available.

Explore how the Aspire team turns merged product changes into SME-reviewed docs pull requests, closing the gap between release and documentation.

Go from an empty repository to a live custom domain with HTTPS in about 14 minutes, without manually editing a single DNS record.

A closer look at why users don’t need more tools in their daily lives. What they need are seamless integrations of useful features to match already existing, established mental models. Brought to you by Design Patterns For AI Interfaces, **friendly video course on UX** and design patterns by Vitaly.

We’ve fallen into conversational tunnel vision, defaulting every AI capability into a chat-based interface simply because LLMs are trained on dialogue data. But great UX is about matching modality to users’ context, intent, and cognitive load, so the interface adapts to the user, not the other way around.

Vercel Agent Investigation intelligently conducts incident response investigations to alert, analyze, and suggest remediation steps

Discover how AI is transforming businesses with Vercel. Learn about easy LLM integration, 7 game-changing applications, and how to implement AI features to boost user experience and growth.

Learn how to design secure AI agents that resist prompt injection attacks. Understand tool scoping, input validation, and output sanitization strategies to protect LLM-powered systems.

v0.dev is now v0.app, the AI builder for everyone: founders, designers, developers, marketers, sales, finance, and more

The Vercel AI Accelerator is back with 39 early-stage teams from around the world, $8M+ in partner credits, and a Demo Day in San Francisco on April 16.

The question isn’t if AI will transform your business, but how to use it to maintain your competitive edge. Vercel CTO Malte Ubl shows how companies can understand AI’s fundamental shifts, adapt their skills, and integrate AI into their businesses.

MCP is becoming the standard for building AI model integrations. See how you can use Vercel's open-source MCP adapter to quickly build your own MCP server, like the teams at Zapier, Composio, and Solana.

There's a difference between leveraging AI and relying on it. A framework for shipping agent-generated code with the judgment and guardrails it requires.

Vercel AI Gateway now supports Perplexity Web Search as a model-agnostic tool that works for all models and providers. Use the tool to get access to the most recent information to supplement your AI queries.

Learn how Mux built durable AI video workflows into their @mux/ai SDK using Workflow DevKit, with automatic retries, state persistence, and zero infrastructure setup.

llms.txt is an emerging standard for making content such as docs available for direct consumption by AIs. We’re proposing a convention to include such content directly in HTML responses.

We built x402-mcp to integrate x402 payments with Model Context Protocol (MCP) servers and the Vercel AI SDK.