Related posts

Co-creator of Django and creator of Datasette; writes daily at simonwillison.net.

• datasette-auth-github 1.0

  Release: datasette-auth-github 1.0 I run this GitHub login plugin on the agent.datasette.io demo site and I noticed that my authenticated sessions weren't lasting very long. It turned out that the plugin was setting coo…

  Related

Former L8 engineer at Meta, Microsoft and Atlassian, now writing and building solo on agentic engineering. Writes Kun's Field Notes and posts a lot about AI coding agents on X.

• backpass — You don't write AGENTS.md. You train it with gradient descent.

  Commitsfeat(discovery): collect sessions from remote machines over SSH (#124)

  Related

Founded PSPDFKit in 2011 and ran it for a decade. Came back from a break to work on AI agents — the OpenClaw project, and OpenAI, joined in February 2026. Writes at steipete.me.

• The coolest part: roboclaw runs our team server, is live on Discord, talks with gpt-live and knows about all the sessions it's juggling. We can ask it about context to current and past sessions right while we have meetings.

  Related

• Love having @vhbrzezowski hijacking my sessions and desloping them before the PR lands. Also hot tip: Open the home sidebar and ask your claw to reorganize your sessions to keep your sessions organized.

  Related

• Just landed a new feature, in the latest OC you can now ask your agent “Run this [web app] in crabbox and show me [vnc / a portal]” This was already working for cloud sessions, but often you start local and then later figure out you need a box to test, now it just works.

  Related

Creator of Claude Code at Anthropic.

• Projects have changed not only how I interact with Claude but how I code. I stopped managing sessions. I just send thoughts as they come, Claude splits them into threads, and the project remembers how I work. It's where I do a ton of my coding now. [screenshot: my actual prompts for claude code cli yesterday]
  Quoting@ClaudeDevsToday we're rolling out Projects in Claude Code on desktop and web. A project is one conversation with Claude. It splits the work into threads itself, runs them as parallel cloud sessions, passes context between them, and keeps going when you leave. In beta for select users.

  AnthropicRelated

Former options market maker who writes Moontower, a newsletter on trading, volatility, decision-making and how to think about risk outside markets too.

• Could use some input. So I want to do a zoom less for this family investing intro seminar but sitting there going through slides sounds terrible The sessions were in a classroom setting with lots of back and forth between everyone. There's definitely an arc but interaction...

  Related

CEO of Vercel; creator of Next.js and Socket.IO. Writes at rauchg.com.

• One of the coolest things about 𝚏𝚡 is that it auto-upgrades, and 𝚌𝚝𝚛𝚕+𝚐 restarts + resumes the chat. Also, that 0.0.10 is much, much faster for longer sessions 😊

  Related

Co-founder of Superlogical, started in 2026 to build server-side terminal infrastructure; creator of Ghostty. Co-founded HashiCorp and created Vagrant and Terraform before that.

• New week new demo! Today I want to showcase the CLI to control the @superlogical multiplexer. The CLI is an extremely powerful tool for automation and hooking into other tools like editors, agentic coding tools, and more. And, it's super fun! Everything you can do in the GUI, you can do via the CLI. Actually, you can do more in the CLI. You can create sessions, run commands, make splits, move things around, change focus, simulate any input device (key/mouse/etc.), wait on scripts, and more. There are a couple unique parts of Rex I'm showing off here too: our streaming event system that any cl…

  Related

Founded PSPDFKit in 2011 and ran it for a decade. Came back from a break to work on AI agents — the OpenClaw project, and OpenAI, joined in February 2026. Writes at steipete.me.

• Fixed so many little perf issues that didn't matter much for single users... before we made it good for teams. OC stems ~80 sessions here rn now and doesn't sweat.

  Related

Moroccan senior frontend developer writing at smakosh.com; builds side projects and client work under Smakosh LLC.

• New on @llmgateway: Adaptive Cache-Aware Provider Selection Routing learns cache-hit rates and output-to-input proportions from recent project/model usage to compare providers for large prompts and sessions. Available automatically across plans, with workload defaults before enough history exists and explicit overrides on Enterprise. Learn more

  llmgateway.io

  Related

Former L8 engineer at Meta, Microsoft and Atlassian, now writing and building solo on agentic engineering. Writes Kun's Field Notes and posts a lot about AI coding agents on X.

• more and more people are discovering the great combo of herdr + firstmate. it's such a good feeling that i wish more folks could discover sooner letting a single agent babysit all your sessions is so clearly the next level experience we're all heading towards
  Quoting@arthurcdbtw, thank you @kunchenguid. FirstMate is very impressive!

  Related

Co-founder of Superlogical, started in 2026 to build server-side terminal infrastructure; creator of Ghostty. Co-founded HashiCorp and created Vagrant and Terraform before that.

• A quick look into remote persistent sessions with Superlogical! Not just remote sessions, but some functionality like remote directory lists, too. Superlogical can actually be a full SSH replacement (I don't run SSH on my servers anymore), and I talk about that briefly, too.

  Related

Co-founder and CEO of Shopify; long-time Linux user and Omarchy contributor.

• Stats: 1572 sessions, longest 9603 turns, 0 amulets kinda disappointed in the X crowd right now 😁
  Quoting@tobiI always liked nethack. This 42 year old marvel is one of the deepest adventure games ever made. It also looks like crap, at least out of the box. GPT6 Astra made a headless version for me. You can now use its brain as a library or as mcp or via javascript library. Meet

  Related

Co-founder and CEO of Linear; previously principal designer at Airbnb, where he led the Design Language System, and founding designer at Coinbase.

• Thanks @jasonlk! Lot to do still but: 1) @linear is used by pretty much by all major labs/ai companies out there 2) our MCP traffic grows 50% MoM 3) we have the most agent integrations and active usage than any platform like this (3rd party, in-house agents) 4) our AI revenue (loops, coding sessions) has grown about 500% per quarter 5) we are closing several public companies/enterprises each quarter to help them coordinate their agent work
  Quoting@HarryStebbingsThe Bull Case for Linear Being a $100BN Company: "Linear is the clear winner. They have built an agentic product first that allows us to build 100x more software, and that means 100x more features than ever before. Humans cannot keep up with it, and humans still have to work with agents. If every h…

  MCPRelated

Co-founder of Superlogical, started in 2026 to build server-side terminal infrastructure; creator of Ghostty. Co-founded HashiCorp and created Vagrant and Terraform before that.

• The Superlogical server is built to run anywhere and everywhere and serve a level of scale (terminals+clients) unmatched w/ prior solutions. So let's start talking about that, starting with memory usage and comparisons to other popular multiplexers. I want to start by talking high level: why does terminal/client scale matter? This matters because we're seeing unprecedented terminal usage and client attachment mainly due to AI. They like to spawn more sessions than we've ever seen, and they are all their own clients. So we have to optimize it. Even if you don't use AI/agents, this just makes t…

  Related

Co-founder and CEO of Shopify; long-time Linux user and Omarchy contributor.

• motorsport-telemetry-rs — fast Rust libraries for motorsport telemetry, sessions, video, GPS, and track metadata

  Related

American software engineer; worked on code-server at Coder and teaches TypeScript and open-source contribution. Publishes at joeprevite.com.

• today is the day you stop doomscrolling stay with me - this will take 5mins 1. open the AppStore 2. download "ScreenZen" (free) 3. configure limits (e.g. 4 15-min sessions) 4. start with 1 social media app 5. a few days later, add another 6. repeat until you've added all apps too busy right now? add a calendar event with this tweet and do it this weekend trust me, you'll thank me next month

  Related

Writer and developer. He runs the Latent Space newsletter and podcast about AI engineering, and writes essays on software and careers at swyx.io.

• by total views, matt’s now the top @aidotengineer speaker in our brief history, and arguably one of the best skills experts in the world — his /grill-me has reached all echelons up to @satyanadella (with some variations…) /wayfinder is @mattpocockuk’s /grill-me for /grill-me, when you are just navigating the fog of war and don’t yet know what you dont yet know, and need to orchestrate research and other grill sessions to get there. super glad to have @ricmac help launch our new Skills coverage with his course launch this week! 👇exclusive interview, quick read
  Quoting@latentspacepodWe chat to @mattpocockuk about his /wayfinder skill, which he designed for the "fog of war" — when you need to figure out a project but the end state isn’t entirely clear. This is the first in a series of skills we'll be exploring in the coming weeks.

  Related

Founding member of OpenAI and former director of AI at Tesla; creator of nanoGPT and the term "vibe coding".

• This is a super exciting release - Claude Fable 5 is the same underlying model as Mythos but with added safeguards. The benchmarks are great and it's SOTA on everything by a margin but I'll add that *qualitatively* also, this is a major-version-bump-deserving step change forward (imo of the same order as Claude 4.5 was in November), peaking especially for long problem-solving sessions on very difficult problems. You can give it a lot more ambitious tasks than what you're used to, the model "gets it" and it will just go, and it's never felt this tempting to stop looking at the code at all (but…
  Quoting@claudeaiFable 5 is state-of-the-art on nearly all tested benchmarks, with exceptional performance in software engineering, knowledge work, scientific research, and vision. The longer and more complex the task, the larger Fable 5’s lead over our other models.

  AnthropicbenchmarksRelated

Programmer known for LiveJournal, memcached, OpenID and gearman; worked on the Go programming language at Google and later joined Tailscale.

• sessweb — Share Claude Code sessions to peers on your Tailscale tailnet

  Commitsfix owner check race on startup

  AnthropicstartupsRelated

Programmer; wrote Extreme Programming Explained and Test-Driven Development, signed the Agile Manifesto, and writes Tidy First?.

• Genie Lessons from Genie Sessions: Prose as a Programming Language

  Kent sits down with one of the founders of OpenProse to talk through their method of prose as a programming language.

  startupsRelated

Software engineer and engineering leader at Canonical, working on Ubuntu; writes about his homelab, Nix and tooling at jnsgr.uk.

• shellspectre — A Rust/eBPF utility for recording SSH/TTY/PTY sessions. Useful for tracing agent sessions and remote sessions on a Linux machine. Submission for a 1 day hackathon event at Canonical.

  LinuxRelated

Co-founder of Modem and a founding engineer at Sentry, where he went on to be VP of Engineering. Co-author of Third-party JavaScript, and co-host of the State of Agentic Coding podcast with Armin Ronacher.

• In 3 weeks at the next Devtools Toronto: traces.com - share agent coding sessions polarity.so - sandboxes for agent testing superuser.app - agents in your team chat tidra.ai - AI code maintenance at scale docsalot.dev - docs agents can read codepathfinder.dev - trace vulns across your codebase

  Related

Managing partner at Ritholtz Wealth Management. Writes the blog The Irrelevant Investor and co-hosts the Animal Spirits podcast with Ben Carlson.

• Wild market. We haven't seen anything like this since the dotcom bubble burst. Over the last 8 sessions, 115 stocks in the S&P 500 have decline 7% or more in a single day. The average drawdown when that happens is 34%. Right now we're 1.5% below the all-time high.

  Related

Research psychologist, instrumental in founding the field of naturalistic decision making; developed the recognition-primed decision model, the PreMortem method and the ShadowBox training method, and wrote Sources of Power and Seeing What Others Don't.

• Can AI Do Pre-Mortems for Us?

  AI systems can churn out effective pre-mortem critiques of plans. But they miss the team dynamics and culture-building benefits of in-person pre-mortem sessions.

  Related

Executive coach for product leaders. Previously a partner at GV (Google Ventures) and a product manager at Google. Writes at Bring the Donuts, including a standing essential-reading list for product managers.

• CEOs and Product Leaders: A Better Relationship

  A relationship built on communication, candor, and trust - In my coaching sessions with CPOs and other senior product leaders, the relationship with a CEO is a frequent topic. Sometimes there’s been a colossal dust-up;…

  Related