こんにちは。LINEヤフーのプラットフォーム部門でメトリクスチームに所属している千葉です。普段は、全社のサービスを支える大規模モニタリングプラットフォーム「Yamas」の開発と運用に取り組んでいます。...

はじめにこんにちは。法政大学情報科学部3年の霍 永豪と申します。2026年8月17日〜9月11日の4週間、社内のデータ基盤に使われているKafkaを運用するチームでインターンとして参加し、Grafan...

<p><strong><a href="https://www.anthropic.com/claude-sonnet-5-5">Claude Sonnet 5.5</a></strong></p>New Sonnet model from Anthropic today. They say it "runs 30%+ faster, and costs up to 30% less for most work" - it's priced the same as Sonnet 5 but appears to beat it on every benchmark, and should be cheaper to run as well.</p><p><a href="https://tools.simonwillison.net/markdown-svg-renderer?url=https%3A%2F%2Fgist.github.com%2Fsimonw%2F1d85a9be7...

<blockquote cite="https://twitter.com/joedaroo/status/2104335929293127851"><p>To say that we were surprised at the jump and suddenness of the capabilities of our models when it came to “cyber” or “swarming” or “message boards” or anything else related to the incidents is an understatement. Security posture takes time to develop. It’s not just about hardening the systems at play; you have to ingrain it in the culture of the company. The literal people themselves in your organization ...

A look at the targeted AI taskflows behind these findings, the critical Android bugs they uncovered, and how to run the same open-source agent on your own app.The post How we found 24 Android vulnerabilities using our open source AI security agent appeared first on The GitHub Blog.

The open source Git project just released Git 2.56. Here is GitHub's look at some of the most interesting features and changes introduced since last time.The post Highlights from Git 2.56 appeared first on The GitHub Blog.

Aikido is an inaugural partner in OpenJS's Security Stewardship Program, funding bug bounties and maintainer support for Node.js.Category: Product & Company Updates

Let's integrate Vercel's AI SDK with Cloudflare's Durable Objects to improve user experience in a fitness tracker application.

Vinext 1.0 graduates from an AI experiment to a production-ready framework, letting developers run Next.js apps on Vite. This release brings advanced cache warming, broader compatibility, and an automated testing pipeline.

We are releasing cf, our new command-line tool that mirrors the entire Cloudflare API and supports programmatic TypeScript configuration. We are also open-sourcing Forge, our internal SDK generator.

Cloudflare is open-sourcing the BEACON dataset, making billions of anonymized Real User Monitoring (RUM) performance records publicly available on Google BigQuery. Explore real-world Core Web Vitals, soft navigation metrics, and performance breakdowns across browsers and regions.

Since joining Cloudflare, VoidZero has delivered more than 80 releases that drastically speed up JavaScript compilation, linting, and testing. From a 10x faster React compiler to Vite+ 1.0, here’s how we are building faster tools for developers and AI agents.

Forge is a pluggable, open-source pipeline that runs in CI to generate SDKs, CLIs, and documentation directly from API definitions. By shifting generation upstream into individual team repositories, Forge keeps developer tools continuously in sync.

We’ve updated Kitesurf, our Workers-based browser for AI agents, with WebMCP support, improved DOM performance, and terminal-based rendering. With over 730,000 Web Platform subtests passing, agents can now navigate complex sites faster.

Cloudflare is launching The Cold Start, a startup competition giving five early-stage companies five minutes on stage at Cloudflare Connect. Grand Prize winner receives $500,000 in credits, a San Francisco billboard, and an invitation to our VIP speakers dinner.

EmDash 1.0 is a stable, open source CMS built for Astro, with agent-friendly workflows, secure sandboxed plugins, and a decentralized registry that keeps publishers in control.

With the new experimental support for the Emscripten target in Rust Workers, many previously unsupported Rust libraries and applications can now be built and deployed directly to Cloudflare’s global Workers platform, including upcoming support for Tokio async.

<blockquote cite="https://www.threads.com/share/_oWfPufYJ/"><p>Bad news on the MX Keys Mini pickup. Usman showed up at your building around 9:15 and waited, messaged a bunch of times, and nobody came down. He left angry at 9:38 and left a negative rating.</p><p>Worse, my auto-reply told him "Yep I'm here!" at 9:27 when you clearly weren't available, which is on me. That's a bad look and it made the no-show worse.I've sent him an apology from your account owning it and of...

LINEヤフー株式会社では、技術に関するイベントや勉強会の主催・協賛などを行っています。最新情報は各リンク先でご確認ください。タイミングによっては、申し込み開始前や既に満席となっていることがあります。...

はじめにこんにちは、東京電機大学大学院理工学研究科情報学専攻修士 1 年の佐藤聖璃です。インターンとして、LINE公式アカウントのプッシュ通知の配信基盤に Decaton の Per-Key-Quot...

You can now discover domain names and check availability and pricing without signing in to Vercel or providing an access token. This works through the Vercel CLI and Domains Registrar API.With the , search by keyword or domain fragment: Vercel CLIWith the , check up to 200 exact domain names in one request. The response shows whether each can be registered and, when available, its registration and renewal prices:Domains Registrar APIAuthentication is still required to buy or manage domains.Try t

from is now available on as .Claude Sonnet 5.5AnthropicAI Gatewayanthropic/claude-sonnet-5.5Sonnet 5.5 improves on for well-scoped everyday work, from building features and fixing bugs to creating documents, slides, and spreadsheets.Claude Sonnet 5On coding tasks, Sonnet 5.5 carries changes through multiple steps and checks its work before reporting completion. It produces more polished documents, slides, and spreadsheets with fewer follow-up edits, and writes clearer explanations and reports. I

now includes memory usage data.Vercel Sandbox observabilityYou can access sandbox memory usage data in the dashboard and through the CLI via the command. vercel metricsThe Memory Usage card reports average, P75, and P95 memory across your sandboxes, alongside the existing CPU usage and data transfer metrics on the sandbox overview page and the project and team-level pages.On the sandbox detail page, charts are designed to show how close a sandbox is running to its memory ceiling by: Sandbox memo

TL;DR: Vite+ 1.0 is out, stable, MIT licensed, and about to reach two million weekly downloads. A single command, vp, manages your Node.js runtime, package manager, and frontend toolchain. Install it with curl -fsSL https://vite.plus | bash, then run vp create for a new project or vp migrate to migrate your existing one.

<p>On Friday I gave the closing keynote at the <a href="https://www.wearedevelopers.com/world-congress-north-america">WeAreDevelopers World Congress North America</a> in San Jose. I tied together the key trends from the past year into a chronological exploration of everything that happened in 2026. The video <a href="https://www.youtube.com/watch?v=GAkIytR7vcc">is on YouTube</a>; here are my annotated slides and notes to accompany the talk.</p><p><li...

<p><a href="https://news.ycombinator.com/item?id=49851693#49871741">My comment</a> on <a href="https://news.ycombinator.com/item?id=49851693">S3 Is the Future, S3 Is the Past</a> — Hacker News.</p><p>One thing I find notable about S3 today is that, while it used to drop in price reasonably often, there hasn't been a price drop in <em>a full decade</em>:</p><pre><code>2006-03-14 $0.150/GB-month2010-11-01 $0.140/GB-...

<p><strong>Tool:</strong> <a href="https://tools.simonwillison.net/bluesky-bot-check">Bluesky reply bot checker</a></p> <p>Automated reply bots on Twitter are a <em>scourge</em> - as someone with a decent number of followers I attract a swarm of these, such that anything I post there attracts dozens of mindless automated replies.</p><p>They've started manifesting on Bluesky as well.</p><p>Unlike Twitter, Bluesky still...

The Internet is changing more today than at any point since Cloudflare launched back on September 27, 2010. As automated traffic surpasses human activity, we reflect on the rise of AI agents, new creators, and how we can help build a fair, sustainable future for the web.

外部サービスのコメント欄やフォームを iframe で埋め込むと、内容の高さと枠の高さが合わず、スクロールや余白が生じることがあります。frame-sizing を使うと、埋め込み側の許可のもとで内容に応じた高さを使えます。

Sync your coding-agent skills, instructions, plugins, and MCP server declarations to a remote Linux box. An introduction to Ferry, with setup instructions and terminal examples.

from Fireworks is now available on .Ember-1AI GatewayEmber-1 is a research preview reasoning model built on for coding and agentic workflows.Kimi K3Fireworks reports approximately 40% fewer generated tokens than Kimi K3 at comparable quality across its evaluations. For coding agents that make repeated model calls, shorter reasoning traces can reduce output costs and the amount of context carried into later steps.Ember-1 supports a 1M-token context window, text and image input, tool calling, and

<p><strong>Tool:</strong> <a href="https://tools.simonwillison.net/kakapo-party">Kākāpō Party</a></p> <p>I presented a closing keynote for the <a href="https://www.wearedevelopers.com/world-congress-north-america">WeAreDevelopers World Congress North America</a> yesterday. As <a href="https://simonwillison.net/2019/Dec/10/better-presentations/">a STAR moment</a> I decided to weave in references to the record breaking <a href="...

ブラウザはスクロール操作の方向を縦か横の一方向に固定することがあります。scroll-axis-lock プロパティを使うと、この軸ロックを解除できます。この記事で scroll-axis-lock の基本的な使い方を紹介します。

The Tauri team is happy to announce the 2.12 release.

Socket is joining the OpenJS Security Stewardship Program to fund Node.js vulnerability research, maintainer remediation, and security releases.

Describe the interface you need in plain English, then let the agent build a live surface you can both use and update—so you spend less time adapting to tools and more time getting work done.The post GitHub Copilot app for Beginners: How to build custom workflows with canvases appeared first on The GitHub Blog.

<blockquote cite="https://daringfireball.net/linked/2026/09/25/aten-muse"><p>Muse is getting a lot of attention — including mine — because it’s both groundbreaking technically (each user gets their own entire persistent Linux VM running in Meta’s cloud) <em>and</em> because it’s packaged in an easy-to-install easy-to-use way. It’s literally presented as <a href="https://daringfireball.net/linked/2026/09/24/song-meta-muse-cute">a cute mascot</a>. It’s the firs...

We can animate an element along the border edge of another element to random positions... pretty easily? Might as well be a cute dog.

How we fully migrated github.com away from CSS-in-JS.The post Improving site performance by shipping more CSS appeared first on The GitHub Blog.

Misconfiguring Turnstile by skipping backend validation leaves sites exposed to bots. Turnstile Spin fixes incomplete setups by using your preferred AI coding agent to wire up server-side verification.

Blurry before beautiful: image previews for the webA very good looking proposal!The root scroller and how not to lose itYet another in-depth, fantastic article by Kilian at Polypane.fonts.xyzYou know us by now: we see a good place to get fonts and we share it. This is a very nice offering with loads to choose from.“AI, make the website good”With these seismic changes, I will continue to make the argument that craft defined as caring about the quality of output (independent of the tools used to g

You can now push container images from GitHub Actions to (VCR) without storing long-lived registry credentials.Vercel Container RegistryThe new action authenticates your workflow using GitHub OIDC. It exchanges the workflow’s OIDC token for a short-lived Vercel access token, then uses that token to log in to . When the job ends, the action logs out and revokes the Vercel token.vercel/vcr-action/loginvcr.vercel.comTo start: Then add the login step before you build and push and the image:The actio

In seven months, the registry grew to one million agent skills and recorded nearly 280 million installs.skills.shA skill gives an AI agent reusable instructions for a particular job. Agents are capable but generic; they can do many jobs, but they don't know how a specific person, team, or company does them. A skill supplies that missing context and can be as simple as a file written in ordinary language. Anthropic introduced in October 2025, and Vercel launched the registry three months later.Ag

<p><img src="https://static.inaturalist.org/photos/740453177/large.jpg" alt="Northern Gannet"></p><p><img src="https://static.inaturalist.org/photos/740453341/large.jpg" alt="Great Blue Heron"></p><p><img src="https://static.inaturalist.org/photos/740454506/large.jpg" alt="California Brown Pelican"></p><p>Northern Gannet, Great Blue Heron, California Brown Pelican, in Monterey Bay National Marine Sanctuary, CA, US, CA</p><p&gt...

pnpm 12.7 lets the global node shim follow .nvmrc and .node-version, adds pnpm install --allow-build and pnpm publish --publish-wait-timeout, and creates pnpm-workspace.yaml from the workspaces field of package.json. pnpm install --force no longer installs optional dependencies built for other...

pnpm 11.28 adds the forceIgnoresPlatform setting and pnpm update --peer, and brings a large batch of fixes from pnpm 12 to the JavaScript CLI: pnpm deploy, --filter, nodeLinker: hoisted, and custom modulesDir setups all behave better. It also carries security fixes for shell completion, bin...

You can now run Redis commands, browse keys, and inspect values directly in the Vercel dashboard using the .Marketplace database browserBoth the and integrations in Vercel Marketplace are supported, so you no longer need or a separate database UI.RedisUpstash for Redisredis-cliFrom your project, open and select a Redis database. The database page now includes two new tabs:Infrastructure > StorageThese tabs are currently available only to team members with the Owner role. Learn more in the .Ma...

is now available on as . It's free for a limited time while in stealth.Pixel CanaryAI Gatewaystealth/pixel-canaryPixel Canary is strong at coding, including building applications and refactoring existing code. It is well suited to frontend development and mobile app design, from responsive layouts and app screens to navigation and interactive components.On , Pixel Canary ties at a 90.3% baseline success rate, passing 28 of 31 tasks. With Next.js documentation supplied through , it passes 30 of 3

In the W3C blog post Crafting WCAG 3 for more accessible user experiences, W3C WAI Director Shawn Lawton Henry covers some of the stakes and challenges in developing W3C Accessibility Guidelines (WCAG) 3.

<p>The more time I spend working with coding agents, the more convinced I am that they make software engineering even harder.</p><p>We can do amazing things with them, but unlocking their full potential requires extraordinary discipline and knowledge.</p> <p>Tags: <a href="https://simonwillison.net/tags/coding-agents">coding-agents</a>, <a href="https://simonwillison.net/tags/ai">ai</a>, <a href="https://simonwillison.net/tags/llms">ll...

Two compromised GitHub Actions were re-enabled with malicious tags intact, exposing thousands of downstream repositories to Mini Shai-Hulud.

<p><strong>Release:</strong> <a href="https://github.com/simonw/commit-rewriter/releases/tag/0.2">commit-rewriter 0.2</a></p> <blockquote><p>Support for branches other than the default branch. Use <code>uvx commit-rewriter --branch other</code> to run against another branch. <a href="https://github.com/simonw/commit-rewriter/issues/3">#3</a></p></blockquote> <p>Tags: <a href="https://simonwillison.net/t...

What is a developer to do when they need something more tangible than a chat box? Enter canvases.The post When chat is the wrong UI appeared first on The GitHub Blog.

<p><strong>Release:</strong> <a href="https://github.com/simonw/datasette/releases/tag/1.0a41">datasette 1.0a41</a></p> <p>Alec Garcia added <a href="https://docs.datasette.io/en/latest/internals.html#internals-telemetry">support for OpenTelemetry</a> to Datasette in this release.</p><p>I've also refactored all of Datasette's modal dialogs to a single Web Component, which is now <a href="https://docs.datasette.io/en/latest/jav...

Top CodeQL alternatives compared on noise, fixes, cost, and more: Aikido Security, Semgrep, Snyk Code, SonarQube, Checkmarx, and VeracodeCategory: DevSec Tools & Comparisons

In this blog post, I explain how to use the new fuzzing taskflow based on the GitHub Security Lab Taskflow Agent AI framework. The post AI-powered fuzzing with the GitHub Security Lab Taskflow Agent appeared first on The GitHub Blog.

External security researchers at Accomplish identified a vulnerability in Cloudflare Containers that could expose residual disk data from previous workloads. We explain how the issue worked, how we investigated it, and the steps we took to remediate it.

記事は ics.media へアクセスしてご覧ください。

Kevin Powell is doing game-show-style (specifically Family Feud) shorts where, using data from a survey of 100 devs, he asks another dev what the most popular answers were. Here’s:

Explore the JavaScript ecosystem without an account, and publish packages from your own registry for anyone to install.

In 2022, we launched a private bug bounty program through HackerOne. Over the last several years, we've worked with HackerOne's VIP program to refine our process, targets, and scope, onboarding thousands of their best researchers and hardening security across our platform. We've translated those learnings into several public bounty programs: Today, we are combining our private and OSS bounty programs into a single, public . Vercel bug bounty programAI has fundamentally changed the nature of bug

Klaviyo on VercelImplementing safeguards across the stackBuilt a platform for shipping internal apps512 builders and 356 live apps in two weeksEvery app ships SSO-gated and private by defaultBuilders go from idea to live app in 3 minutes Apps are private and SSO-gated through OktaSensitive environment variables are set at the team level, out of builders' handsKlaviyo's hardened GitHub security is inherited by every projectWiz scans every project, and findings feed Klaviyo's SIEMPublic deployment

itch.io で Posting Puzzle というゲームを公開しました。封筒と切手を対応付けるだけの小さなブラウザパズルです。全 12 ステージ。 mametter.itch.io ルールは口頭で説明するより、実際に触ってみてもらったほうがわかりやすいと思うので、遊んでみてください。 以下ネタバレ 元ネタ これはポストの対応問題（Post correspondence problem 、以下 PCP）という決定不能問題をほぼそのままゲームにしたものです *1 。「ポスト」は郵便ポストではなく、問題の考案者の名前（Emil Post）です。 決定不能なので、この問題の汎用ソルバーを書くこと…

How a three-person platform team at Legora halved their CI config, drove sandbox violations to zero, and stopped hand-tuning shards across 600+ projects.

Agents built with TanStack AI can now call OAuth-protected MCP servers through Vercel Connect, with no credentials for you to store or rotate.The new subpath exports , which takes a TanStack transport config and attaches a Connect-backed auth provider. The provider is called before every MCP request, so the token is always fresh.@vercel/connect/tanstack-aiconnectMCPTransportIf the user has not granted access, fails with a consent challenge before the model runs. Catch it with and redirect to Con

<p><a href="https://news.ycombinator.com/item?id=49823195#49823961">My comment</a> on <a href="https://news.ycombinator.com/item?id=49823195">We just shipped support for the ugliest part of HTTP: Vary</a> — Hacker News.</p><p>I've been wanting this from Cloudflare <em>for years</em>.</p><p>The classic problem here is if you do that thing where user agents that send "accept: text/html" get HTML, while user agents that do...

Safari Technology Preview Release 253 is now available for download for macOS Golden Gate and macOS Tahoe.

A malicious Firefox extension fetches its payload after installation to evade detection, steal Google session cookies, and automate account takeover.

How we rebuilt the diff surface in the GitHub Copilot app to open a million-line pull request with hundreds of inline review comments.The post Rendering huge pull requests in the GitHub Copilot app appeared first on The GitHub Blog.

You can now create as many stores as you need. The previous limits of 100 stores on Hobby, 500 on Pro, and 1,000 on Enterprise no longer apply.Vercel BlobBlob store creation is now billed alongside other , including , , and calls. On Pro that's $5.00 per million. On Hobby it counts toward the 2,000 free operations you get each month. Deleting a store is free.Blob Advanced Operationsput()copy()list()Create a new store whenever you want a hard boundary instead of a pathname convention:Storage, ope

<p><strong>Tool:</strong> <a href="https://tools.simonwillison.net/gemini-tts-playground">Gemini 3.8 TTS Playground</a></p> <p>Google <a href="https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-8-text-to-speech/">released two new Gemini text-to-speech models</a> today - <code>gemini-3.8-flash-tts</code> and <code>gemini-3.8-flash-lite-tts</code>.</p><p>They come with a library...

<p><strong>Tool:</strong> <a href="https://tools.simonwillison.net/shadow-roots">Shadow roots, explained with live examples</a></p> <p>Prompt to Fable 5.1 Medium:</p><blockquote><p><code>Build an artifact to explain shadow roots in CSS with interactive examples</code></p></blockquote> <p>Tags: <a href="https://simonwillison.net/tags/css">css</a></p>

A versatile tool for managing coding projects, integrating multiple terminals and AI agents within a single control panel.

We compare the top Greptile alternatives in 2026 on coverage, noise, review depth and more: Aikido Security, CodeRabbit, Qodo, Graphite, SonarQube and CodeAnt AICategory: DevSec Tools & Comparisons

Compromised MemTensor npm releases turn an AI memory plugin into a credential-harvesting entry point, exposing prompts and creating a path to further package compromise.

New research from GitHub and Yale Program on Climate Change Communication finds strong demand for tools, measurement, and practical guidance that can help developers reduce wasted compute.The post Developers want more efficient software. Here’s what over 1,000 GitHub users told us they need. appeared first on The GitHub Blog.

Code, cloud, and devices, covered automatically once someone's hired through Deel.Category: Product & Company Updates

If you run a platform with a dozen or more services behind it, you’ve probably seen this pattern. Service A checks an API key. Service B calls out to your identity provider directly. Service C has a half-finished authentication middleware that hasn’t been touched in a while. Every team solved the same problem differently, and […]

I stumbled across this great project by Barry Prendergast. It's a web-based radio player with a lush UI. On mobile I spotted that as I was rapidly flicking through the stations to find one that was on air, the browser was zooming in and out.Here's a screen clip:Watch the video.I thought this behaviour was related to their viewport meta tag setup, but they have that set up perfectly:<meta name="viewport" content="width=device-width, initial-scale=1.0">Now, you could prevent the zooming by a...

The compromise affects MemTensor's MemOS, an open source memory framework for large language models (LLMs) and AI agents. Both npm package @memtensor/memos-cloud-openclaw-plugin and the PyPI package MemoryOS are compromised. They drop cross-platform Go binaries that exfiltrate developer secrets.

"supplychain.local": malicious code found in MemTensor's npm plugin (0.1.21, 0.1.23) and PyPI's MemoryOS (2.0.34).Category: Vulnerabilities & Threats

GitLab gives you a private email address to create issues. If leaked, anyone who has it can push code, execute CI/CD jobs, and bypass IP restrictions across all of your public and private projects.Category: Research

<p><strong><a href="https://luma.com/vxuiuyvg">SF October 14th: A Birds of a Feather Session on Agentic Engineering</a></strong></p>I'm hosting an evening event with Jesse Vincent in San Francisco on Wednesday 14th October for people who are building weird and interesting things with and on top of coding agents.</p><p>Think of it as an agentic show-and-tell:</p><blockquote><p>​Compare notes with other builders and experimenters o...

The Cyber Resilience Act's first deadline just came up on September 11, 2026. What the new Single Reporting Platform looks like, and four common CRA myths debunked.Category: News

AI has made implementing and enforcing design systems cheaper than ever. At the cost of speed, this falls through the cracks. But agentic development makes good design system practice non-negotiable. Implement a design system and bring consistency to an existing project.

and from Google are now available on .Gemini 3.8 Flash-Lite TTSGemini 3.8 Flash TTSAI GatewayBoth models generate speech from text in more than 100 languages and support long-form narration, control over delivery, and two-speaker dialogue.To generate speech, pass either model ID to the AI SDK (7 or later): Try or in the model playground. See the for setup instructions, two-speaker dialogue, and more examples.Flash-Lite TTSFlash TTStext-to-speech guideRead more is optimized for high-volume speech

Drives for Vercel Sandbox are now available in public beta on Hobby, Pro, and Enterprise.A Drive is persistent storage that you mount as a directory in a Vercel Sandbox. It isn’t tied to a single sandbox, so you can reuse the same Drive across runs and different sandbox instances.Use Drives to preserve an agent's workspace or on-disk memory, or to reuse datasets, models, and dependency trees.Create or retrieve a Drive and mount it at a path when starting a sandbox. Read and write files through t

0xinsider is now Polymarket analytics for sports and esports. What 149,700 wallets and 411,770 large buys say, with every query public.

ARD is a new proposal from Google, Microsoft and Hugging Face for how agents find tools. What's in it, what 0xinsider publishes, and what a registry returns.

Every page has one main scroll container that scrolls the page itself: the root scroll container, or root scroller for short. Because it…

<p>Yesterday was <a href="https://x.ai/news/grok-4-7">Grok 4.7</a> (<a href="https://news.ycombinator.com/item?id=49788838#49790209">pelicans</a>) and <a href="https://mimo.xiaomi.com/mimo-v2-6">MiMo v2.6 Flash/Pro</a> (<a href="https://news.ycombinator.com/item?id=49792730#49793480">more pelicans</a>). Today Anthropic <a href="https://www.anthropic.com/claude-opus-5-5">released Claude Opus 5.5</a>, and around an hour later OpenA...

If you’ve got an HDR display, and use Chrome 137+ or Safari 26+ (even on iOS), perhaps you’ve seen images sometimes with colors that are so bright they seem to dim the rest of the screen. I find it a bit distracting, but I can see how it could be a fun technological gimick sometimes. […]

<p><strong>Release:</strong> <a href="https://github.com/simonw/llm/releases/tag/0.36">llm 0.36</a></p> <blockquote><ul><li>New OpenAI models: <code>gpt-6-sol</code> for <a href="https://developers.openai.com/api/docs/models/gpt-6-sol">GPT-6 Sol</a> and <code>gpt-6-luna</code> for <a href="https://developers.openai.com/api/docs/models/gpt-6-luna">GPT-6 Luna</a>. <a href="https://github.com/s...

<blockquote cite="https://www.tiktok.com/@therealcornpop/video/7687243097801051422"><p>Hey, you know it's like super obvious if you're using AI to write your scripts for TikTok and YouTube, right? [...] It's not just the general AI-isms of "it's not X, it's Y", or the rule of three, or the really weird broken staccato-like way of writing where you just say a lot of things with all these punctuation marks. and it sounds really deep, but it's not.</p><p>It's the lack of &l...

<p><strong>Release:</strong> <a href="https://github.com/simonw/llm-anthropic/releases/tag/0.29">llm-anthropic 0.29</a></p> <p>Adds support for <a href="https://www.anthropic.com/claude-opus-5-5">Claude Opus 5.5</a>:</p><pre><code>llm -m claude-opus-5.5 "prompt goes here"</code></pre> <p>Tags: <a href="https://simonwillison.net/tags/llm">llm</a>, <a href="https://simonwillison.net/tags/anthr...

<p><strong>Release:</strong> <a href="https://github.com/simonw/llm-typesafe/releases/tag/0.1a0">llm-typesafe 0.1a0</a></p> <p>I built this new plugin for <a href="https://llm.datasette.io/">LLM</a> to add support for <a href="https://simonwillison.net/2026/Sep/21/jev/">TypeSafe AI's new Jev model</a>. Install it like this:</p><pre><code>llm install llm-typesafe</code></pre><p>Then set an API k...

Vary support is now available in Cache Rules on every plan. You can normalize known negotiation headers, pass exact values through to the origin when those small differences matter, or bypass cache when the variation is too unpredictable.

Worker Previews gives every branch its own URL, configuration, state, and observability, so you and your agents can test changes in parallel without affecting production.

Aikido found Graphalgo-linked Go malware in Terraform providers and Go Modules, using targeted triggers, Slack, and blockchain C2.Category: Vulnerabilities & Threats

AI can produce code. Organizations still have to produce software. Agentic development is changing how software gets made, but it hasn’t changed what it costs to be wrong. Six months ago, we began publicly experimenting with agentic development environments. Around the same time, we introduced JetBrains Central as an open control and execution system for […]

Lovable’s OJ rewrites Vite’s dev server in Rust, reducing memory use and preview times as AI lowers the cost of open source reimplementation.