Boris Cherny

🏃 🏃 🏃

Super excited about this launch -- every Claude Code user just got way more context, better instruction following, and the ability to plug in even more tools

Lovely piece from @TheAtlantic https://www.theatlantic.com/technology/2026/01/claude-code-ai-hype/685617/

A small quality of life detail: you can now press tab to add more instructions when accepting/rejecting a permission prompt. We tried probably a dozen iterations of this UX over the last few weeks before deciding to ship this one. Let us know what you think!

RT Guillermo Rauch If you're an engineer, 2026 is the year when you return to the fundamentals. Unix, CLIs, tests & types, markdown. Great and accessible documentation. Did I say markdown. There'll be lots of markdown. You can now 𝚌𝚞𝚛𝚕 -𝙷 '𝚊𝚌𝚌𝚎𝚙𝚝:𝚝𝚎𝚡𝚝/𝚖𝚊𝚛𝚔𝚍𝚘𝚠𝚗' the @vercel docs: Which agents like Claude Code do by default, saving lots of data transfer and tokens in the process: Original tweet: https://x.com/rauchg/status/2011152152623005736

RT Alex Albert I'm happy to share that we (@AnthropicAI) are investing $1.5 million in support of the Python Software Foundation and open source security. Python powers so much of the AI industry. Supporting the folks that make our work possible is an honor. Original tweet: https://x.com/alexalbert__/status/2011143093266104800

RT Felix Rieseberg Claude Code doesn't just resonate with developers anymore. Non-technical people are using it to build things. Technical people are using it for non-technical work. The line is blurring. I'm by far not the first to think about this. Multiple teams at Anthropic have been working on "agentic experiences" for months - Claude not just as a chat partner, but as something that helps you do real work. @bcherny nudged me: can we take what we've built internally and ship an early, scoped-down version in a few days? So we took a small team, set an aggressive deadline ("Monday sound good?"), and got to work. @claudeai wrote Cowork. Us humans meet in-person to discuss foundational architectural and product decisions, but all of us devs manage anywhere between 3 to 8 Claude instances implementing features, fixing bugs, or researching potential solutions. For native code, we use local Git worktrees on our local machines. For smaller or web-code only changes, we just tell Claude to go implement it. When someone reports a bug in Slack, we often just @-mention Claude and tell it to fix it. A human (and another Claude) reviews all code before it's merged, but we're now spending most of our time orchestrating a fleet of Claudes and making decisions than artisanally writing individual lines of code. We're releasing Cowork early. It has rough edges. But figuring out what to build is increasingly the hardest part of software engineering - and we think getting feedback early and hearing what users actually need is how we build something truly good. Original tweet: https://x.com/felixrieseberg/status/2010882577113268372

RT Lenny Rachitsky Testing out the new Claude Cowork. I asked it to go through every Lenny's Podcast episode and pull out the 10 most important themes and lessons for product builders. Then, the 10 most counterintuitive truths. I gave it access to a folder with 320 transcripts. First, it said "This is a substantial task - 320 podcast transcripts to analyze!" 15 minutes later... The 10 most Important themes from Lenny's Podcast 1. Activation Is Everything — Slack's "2,000 messages" moment, Gamma's 30-second magic. Get users to value fast. 2. Storytelling as a Superpower — Compelling narratives align organizations better than documents. 3. Positioning Is Strategy, Not Marketing — April Dunford's 5-step framework that starts with competitive alternatives, not messaging. 4. Product Discovery Before Delivery — Teresa Torres' Opportunity Solution Trees and Marty Cagan's Four Risks framework. Talk to customers weekly, not quarterly. 5. Ruthless Prioritization — Shreyas Doshi's LNO Framework (Leverage/Neutral/Overhead) and focusing on opportunity cost over ROI. 6. AI is Transforming Product Development — Model maximalism, evals as core PM skill, CEOs becoming ICs again. 7. Empowered Teams vs. Feature Factories — Marty Cagan's distinction: give teams problems to solve, not features to build. 8. Build Your Operating System — Claire Hughes Johnson's framework for founding documents, operating cadence, and decision frameworks. 9. Pre-Mortems and Risk Anticipation — Shreyas Doshi's technique to surface failure modes before they happen. 10. Small Teams, Outsized Impact — Jason Fried's 2-person/6-week constraints, Shopify's pair programming culture. The 10 most counterintuitive truths: 1. Fear Gives Bad Advice—Do the Opposite — Whatever you're afraid to do (hard conversation, telling the board bad news) is exactly what you should do. 2. Adding Friction Can INCREASE Conversion — Adding personalization questions to signup improved Amplitude's conversion by 5%. 3. ...

Since we launched Claude Code, we saw people using it for all sorts of non-coding work: doing vacation research, building slide decks, cleaning up your email, cancelling subscriptions, recovering wedding photos from a hard drive, monitoring plant growth, controlling your oven. These use cases are diverse and surprising -- the reason is that the underlying Claude Agent is the best agent, and Opus 4.5 is the best model. Today, we're so excited to introduce Cowork, our first step towards making Claude Code work for all your non-coding work. The product is early and raw, similar to what Claude Code felt like when it first launched. Cowork includes a number of novel UX and safety features that we think make the product really special: a built-in VM for isolation, out of the box support for browser automation, support for all your http://claude.ai data connectors, asking you for clarification when it's unsure, We are excited to see how you all use it. Cowork is available now as a research preview for Claude Max subscribers in the macOS app. Click on “Cowork” in the sidebar: https://claude.com/download

RT tobi lutke My annual MRI scan gives me a USB stick with the data, but you need this commercial windows software to open it. Ran Claude on the stick and asked it to make me a html based viewer tool. This looks... way better. Original tweet: https://x.com/tobi/status/2010438500609663110

RT Melvin Vivas Claude Code desktop now has Plan mode Original tweet: https://x.com/donvito/status/2010356898147733652

RT Numman Ali Claude Code v2.1.3 has solved the compaction issue Auto compaction works very well if you start with Plan Mode and explicitly ask the model to make a Comprehensive To Do list Plans and To Dos persist across compaction Runtime was 52m 54s with beautifully written code ⛩️ Original tweet: https://x.com/nummanali/status/2010042788566720955

Great tip for bigger codebases

RT Ado Claude Code is sandboxed to your current directory. Building an web app that imports from a shared SDK that's outside the current directory? /add-dir ../sdk Now Claude sees both and can read and edit both. No symlinks. No switching sessions. Original tweet: https://x.com/adocomplete/status/2009741551753449849

RT Anthropic New on the Anthropic Engineering Blog: Demystifying evals for AI agents. The capabilities that make agents useful also make them more difficult to evaluate. Here are evaluation strategies that have worked across real-world deployments. https://www.anthropic.com/engineering/demystifying-evals-for-ai-agents Original tweet: https://x.com/AnthropicAI/status/2009696515061911674

We just open sourced the code-simplifier agent we use on the Claude Code team. Try it: claude plugin install code-simplifier Or from within a session: /plugin marketplace update claude-plugins-official /plugin install code-simplifier Ask Claude to use the code simplifier agent at the end of a long coding session, or to clean up complex PRs. Let us know what you think!

Claude Code 2.1.0 is officially out! claude update to get it We shipped: - Shift+enter for newlines, w/ zero setup - Add hooks directly to agents & skills frontmatter - Skills: forked context, hot reload, custom agent support, invoke with / - Agents no longer stop when you deny a tool use - Configure the model to respond in your language (eg. Japanese, Spanish) - Wildcard support for tool permissions: eg. Bash(*-h*) - /teleport your session to http://claude.ai/code - Overall: 1096 commits https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md If you haven't tried Claude Code yet: https://code.claude.com/docs/en/setup Lmk what you think!

Try it and tell us what you think! Comes with automatic git worktrees out of the box

RT Josh Pigford claude's 𝙰𝚜𝚔𝚄𝚜𝚎𝚛𝚀𝚞𝚎𝚜𝚝𝚒𝚘𝚗𝚃𝚘𝚘𝚕 is the single greatest AI innovation in the last 6 months. the *quality* of output because of that singular tool is majorly slept on. Original tweet: https://x.com/Shpigford/status/2008722847649415637

💍

RT Derya Unutmaz, MD This is a good analogy. I've been working with Claude Code with Opus 4.5 for the past weeks, & I confidently say that it has achieved AGI level in coding! It is indeed a watershed moment we've been waiting for! It will continue to get exponentially better in a self-improving way! Original tweet: https://x.com/DeryaTR_/status/2008310069104890102

RT Wes Winder opus 4.5 with ralph wiggum and playwright is agi Original tweet: https://x.com/weswinder/status/2008051871743918410

A few of you asked how to disable auto-generated terminal titles in Claude Code CLAUDE_CODE_DISABLE_TERMINAL_TITLE=1 claude You can also add that env var to the “env” section of your settings.json https://code.claude.com/docs/en/settings

RT Anthony Morris ツ Becoming a user of Claude Code changed the way I do my job. Then I was lucky enough to join the Claude Code team. It had an even bigger impact on my work. Being surrounded by smart, AGI pilled folks changes the way you see the world. It's hard to imagine what the next year will bring but there's no question it's going to be a one to remember. Original tweet: https://x.com/amorriscode/status/2007925844434694272

RT Thariq If you started using Claude Code over the holidays, you might be curious about how AI actually works, the benefits and risks, and where it's headed. Here are some of my favorite papers on alignment, interpretability, and societal impacts 🧵 Original tweet: https://x.com/trq212/status/2007903193158881323

run this: /mobile

RT Dmitrii Kovanikov I'm not joking and this isn't funny. We have been trying to compile a C++ program at Bloomberg since last year. There are various options, not every struct is aligned... I gave Claude Code the source code and input, it generated the expected output in an hour. Original tweet: https://x.com/ChShersh/status/2007848920786083922

RT Ryan Peterman Fiona Fung currently supports the Claude Code team at Anthropic and was previously a Senior Director at Meta. She grew quickly through the ranks at Microsoft and Meta before joining Anthropic. I interviewed her about what she learned along the way. We discussed: • When to trade off team health for impact • Why dogfooding is important for engineering leaders • Microsoft vs Facebook culture • Feedback that changed her career • Advice on how to mentor and use 1 on 1s Where you can find the interview: • Spotify: https://open.spotify.com/episode/3ejuFRQIdiAnSclPzmcDtI?si=N7LQyjqYTY68vKnbLE7VMA • YouTube: https://youtu.be/b5-d8u-c99s • Transcript: https://www.developing.dev/p/anthropic-eng-leader-and-ex-senior • Apple: https://podcasts.apple.com/au/podcast/the-peterman-pod/id1777363835 Original tweet: https://x.com/ryanlpeterman/status/2007846665882071067

RT David Shapiro (L/0) The entire internet rn Original tweet: https://x.com/DaveShapi/status/2007770411556348248

RT Jake Re Today I handed Claude a document that I've been growing for...years on building an orchestrator/distributed runtime that I had only purely theorized possible. One we've been working towards. It would have taken me probably months to code by hand. Building on 5 years of work and 10 years of experience. Claude wrote all the code in Golang in 4 hours. I'd always actually wanted it in Rust cause I thought it would be easier to express, so I threw it in a loop with a "Rewrite it in Rust and make it as succinct as possible" I went and ate a burrito. I came back and it was done. That's the world we live in now. Original tweet: https://x.com/JustJake/status/2007730898192744751

RT Beff (e/acc) Every moment not spent locked in on Claude Code feels very high opportunity cost all of a sudden Original tweet: https://x.com/beffjezos/status/2007729643345125698

RT Wes Winder ralph wiggum kinda goes crazy this was one shot lol Original tweet: https://x.com/weswinder/status/2007694764452557307

Great way to use Claude Code

Perfect way to use claude code

RT internetVin The more I fuck around with Claude Code, the more I feel like 2026 is the tipping point for how we interact with computers. Will never be the same again. All of this shit is becoming StarCraft for the next little bit. Original tweet: https://x.com/internetvin/status/2007452653551284289

RT Gergely Orosz For the last ~20 years, I did most of my coding inside an IDE - the last ~15 with increasingly good autocomplete. Which is why it’s so weird that I barely opened an IDE the last two weeks, even as I pushed lots of code. I use the CLI, the web and my phone (!!) to prompt code Original tweet: https://x.com/GergelyOrosz/status/2007451804380926453

RT Maze holy fuck. you guys weren't lying. opus 4.5 is insane. Original tweet: https://x.com/mazeincoding/status/2007418206198346189

RT Martin_DeVido In a remarkable act of synchronicity i noticed yesterday Sols first flowering- on the first day of the new year. And today through the Webcam Claude saw them too What a remarkable start to a new year. Happy new year to you all, I'm ecstactic for the interest in this project. I haven't had a chance to follow back a lot of you- I certainly will. X rate limits these so it will take some time. Original tweet: https://x.com/d33v33d0/status/2007280874354864585

RT Ado Happy New Year! In December, I shared 31 days of Claude Code features. Thanks for following along and the replies, the questions, the "wait it can do that?" If you missed any (or want them all in one place), here it is. Your 2026 terminal is about to be very different. 🧵 Original tweet: https://x.com/adocomplete/status/2006802341228655083

RT Andrej Karpathy I was inspired by this so I wanted to see if Claude Code can get into my Lutron home automation system. - it found my Lutron controllers on the local wifi network - checked for open ports, connected, got some metadata and identified the devices and their firmware - searched the internet, found the pdf for my system - instructed me on what button to press to pair and get the certificates - it connected to the system and found all the home devices (lights, shades, HVAC temperature control, motion sensors etc.) - it turned on and off my kitchen lights to check that things are working (lol!) I am now vibe coding the home automation master command center, the potential is 🔥.And I'm throwing away the crappy, janky, slow Lutron iOS app I've been using so far. Insanely fun :D :D Original tweet: https://x.com/karpathy/status/2005067301511630926

RT Jarred Sumner People frequently ask: > How is Bun sustainable? If I bet my company’s tech stack on Bun, will Bun still be around in a few years? We didn’t have a great answer to this question, until today Original tweet: https://x.com/jarredsumner/status/1995917255583170721