Boris Cherny
Creator of Claude Code at Anthropic.
Boris Cherny did not write this page. ppll compiled it from their own words, each linked to the source. Is this you? · Report a mistake
Latest x.com
What they believe
-
Being wrong is something to love, because it is what lets you define the problem more clearly, find the right solution, and solve it faster.
I love being wrong. It is my favorite, because it helps me more clearly define the problem, find the right solution, learn more quickly, and solve the problem.
borischerny.comSaid 19 Sept 2026This on korrents
-
With a good enough plan, a coding agent implements the whole change in one attempt.
once there is a good plan, it will one-shot the implementation almost every time.
newsletter.pragmaticengineer.comSaid 4 Mar 2026This on korrents
The bold line is korrents’ wording; the quote is theirs. These 2: what they wrote before what they said aloud, one per source, newest first.
Feed
As its own page →Hiding
15 October
8 October
7 October
6 October
1 October
28 September
26 September
25 September
24 September
23 September
22 September
-
Usestheir ownrcmnd.app
OpusTheir words
I used Opus 5.5 to formally verify the Claude Agent SDK using Lean. A couple short prompts = 16 PRs fixing various bugs and race conditions.
-
Usesrcmnd.app
LeanTheir words
I used Opus 5.5 to formally verify the Claude Agent SDK using Lean. A couple short prompts = 16 PRs fixing various bugs and race conditions.
-
Usesrcmnd.app
TLA+Their words
TLA+ also works well. I sometimes combine Lean and TLA+ to look for issues around data flow, concurrency, and state mgmt.
20 September
19 September
From one piece I am often wrong — Boris Cherny's Blog 2 beliefs · borischerny.com
-
korrents.com
When there is new data, you have to update your priors, even when the resulting churn feels thrashy.Their words
When there’s new data, you have to update your priors.
-
Their words
I love being wrong. It is my favorite, because it helps me more clearly define the problem, find the right solution, learn more quickly, and solve the problem.
17 September
16 September
14 September
11 September
-
Recommendsrcmnd.app
Threat Intelligence reportTheir words
The latest Threat Intelligence report is an absolutely terrifying and important read.
7 September
1 September
7 August
27 July
From one piece Boris Cherny: We Cut 80% of Claude Code's Prompt 13 beliefs · youtube.com
-
Their words
I think the skill nowadays is less about prompt engineering and more about figuring out how do you give Claude a hard task that seems a little bit too hard. And then how do you make it possible for Claude to verify its work along the way? And the verification I think is probably the single most important thing that people do not get right
-
Their words
one example is the model can now rewrite essentially any code base from one language to a different language.
-
korrents.com
The way to find what a model can do is to hand it tasks slightly harder than you believe it can handle.Their words
One is you should give the model slightly harder tasks than what you think it can do.
+ 10 more
-
Their words
Because the model can do this at every given model generation, but there is often not a product that lets the model do this and lets it express this kind of ability to do this.
-
Their words
I think evals, they outlive the harness a little bit, but not by that much. Like an eval might live for maybe one, two, three model generations, but nowadays the you know, we're on the exponential. The model is improving so quickly, very often we just saturate the eval, and then we have to throw it away, and we have to come up with a new eval.
-
Their words
And the model is not like that. It's um the way to think about it is almost like a like a living creature, like it's something more organic.
-
Their words
I I think this is sort of the crazy thing about building on models. It's just so different than all the engineering that I've ever done. Like in the past when you built on systems, you built these like big beautiful systems and you really think about the system design up front. You have like a big suite of unit tests. You think about everything and you know, like a re-architecture is a big project.
-
Their words
And you don't want to guess what's the instruction that the model needs because you might not predict it correctly. The thing that you want to do is you want to run it.
-
Their words
for people that aren't building agentic products, but you're using Claude code, every 6 months delete your Claude MD. Delete your skills. Delete your hooks.
-
Their words
And what's interesting is that the model is actually a little bit more intelligent without these prompts.
-
Their words
And the reason is every model is very different. So, something that you did for one model maybe 3 months ago, it just might not translate at all to the next model.
-
Their words
it's it's literally we're looking at neurons in the model's brain that light up when prompt injection happens. So the model won't even tell you but we can actually see those neurons and we can figure out and diagnose that it's happening. And then you combine that with the auto mode classifier and with these three layers we just cannot demonstrate prompt injection anymore.
-
Their words
the model does not seem to be prompt injectable anymore.
24 July
-
Likedtheir ownrcmnd.app
Claude Opus 5Their words
Opus 5 is a great model for coding, data analysis, design, biology, knowledge work.
8 July
-
Recommendstheir ownrcmnd.app
Claude Code /checkupTheir words
New in Claude Code: /checkup
2 July
-
Lovedtheir ownrcmnd.app
Claude Code ArtifactsTheir words
Artifacts in Claude Code have been life changing. Excited to expand to Pro and Max!
12 June 2025
4 June 2025
8 May 2025
12 December 2024
19 June 2024
2 June 2024
10 December 2023
-
Usestheir ownrcmnd.app
WorkplaceTheir words
Instead of meetings, I used Workplace posts (Meta’s internal version of Facebook Group posts) to share thoughts, start discussions, and make announcements.
7 September 2022
17 January 2022
13 March 2021
24 December 2019
8 September 2019
26 May 2019
10 August 2018
Nothing matches.
Beliefs
Korrents What they believe 35 beliefs — each backed by an exact quote.
Each is a — compiled by korrents.com, not by them: the one-line wordings are korrents', the quotes are theirs.
Recent
Being wrong is something to love, because it is what lets you define the problem more clearly, find the right solution, and solve it faster.
I love being wrong. It is my favorite, because it helps me more clearly define the problem, find the right solution, learn more quickly, and solve the problem.
I am often wrong — Boris Cherny's Blog Said 19 Sept 2026
When there is new data, you have to update your priors, even when the resulting churn feels thrashy.
When there’s new data, you have to update your priors.
I am often wrong — Boris Cherny's Blog Said 19 Sept 2026
Prompt injection is no longer a live attack on the frontier model: it simply does not follow instructions it reads on the internet any more.
the model does not seem to be prompt injectable anymore.
Boris Cherny: We Cut 80% of Claude Code's Prompt Said 27 Jul 2026
Show 32 more
Prompt injection can be caught by watching the neurons that fire when it happens, so a defence no longer depends on the model reporting the attack.
it's it's literally we're looking at neurons in the model's brain that light up when prompt injection happens. So the model won't even tell you but we can actually see those neurons and we can figure out and diagnose that it's happening. And then you combine that with the auto mode classifier and with these three layers we just cannot demonstrate prompt injection anymore.
Boris Cherny: We Cut 80% of Claude Code's Prompt Said 27 Jul 2026
Prompt work does not transfer across model generations: what you wrote three months ago for one model may be worth nothing to the next.
And the reason is every model is very different. So, something that you did for one model maybe 3 months ago, it just might not translate at all to the next model.
Boris Cherny: We Cut 80% of Claude Code's Prompt Said 27 Jul 2026
A frontier model is measurably more intelligent with no system prompt at all; the prompts that remain are there for the product, not the model.
And what's interesting is that the model is actually a little bit more intelligent without these prompts.
Boris Cherny: We Cut 80% of Claude Code's Prompt Said 27 Jul 2026
Every six months you should delete your whole AI configuration — instructions, skills and hooks — and find out how much of it the model never needed.
for people that aren't building agentic products, but you're using Claude code, every 6 months delete your Claude MD. Delete your skills. Delete your hooks.
Boris Cherny: We Cut 80% of Claude Code's Prompt Said 27 Jul 2026
You cannot predict which instructions a model needs, so a system prompt has to be discovered by running the thing rather than designed in advance.
And you don't want to guess what's the instruction that the model needs because you might not predict it correctly. The thing that you want to do is you want to run it.
Boris Cherny: We Cut 80% of Claude Code's Prompt Said 27 Jul 2026
Building on a model is unlike any previous software engineering, because the thing you are building on cannot be designed up front.
I I think this is sort of the crazy thing about building on models. It's just so different than all the engineering that I've ever done. Like in the past when you built on systems, you built these like big beautiful systems and you really think about the system design up front. You have like a big suite of unit tests. You think about everything and you know, like a re-architecture is a big project.
Boris Cherny: We Cut 80% of Claude Code's Prompt Said 27 Jul 2026
A model is better thought of as a living creature with a personality you must get to know than as a component you specify.
And the model is not like that. It's um the way to think about it is almost like a like a living creature, like it's something more organic.
Boris Cherny: We Cut 80% of Claude Code's Prompt Said 27 Jul 2026
Evals are not the durable asset people think they are: one survives about one to three model generations before it saturates and has to be thrown away.
I think evals, they outlive the harness a little bit, but not by that much. Like an eval might live for maybe one, two, three model generations, but nowadays the you know, we're on the exponential. The model is improving so quickly, very often we just saturate the eval, and then we have to throw it away, and we have to come up with a new eval.
Boris Cherny: We Cut 80% of Claude Code's Prompt Said 27 Jul 2026
Product overhang: at every model generation the model can already do things no product yet lets it do, and the product is usually what is in the way.
Because the model can do this at every given model generation, but there is often not a product that lets the model do this and lets it express this kind of ability to do this.
Boris Cherny: We Cut 80% of Claude Code's Prompt Said 27 Jul 2026
The way to find what a model can do is to hand it tasks slightly harder than you believe it can handle.
One is you should give the model slightly harder tasks than what you think it can do.
Boris Cherny: We Cut 80% of Claude Code's Prompt Said 27 Jul 2026
A model can now port essentially any codebase from one programming language to another, work that used to take a team over a year.
one example is the model can now rewrite essentially any code base from one language to a different language.
Boris Cherny: We Cut 80% of Claude Code's Prompt Said 27 Jul 2026
The skill that matters now is not prompt engineering but giving a model a way to verify its own work, and it is the thing people most often get wrong.
I think the skill nowadays is less about prompt engineering and more about figuring out how do you give Claude a hard task that seems a little bit too hard. And then how do you make it possible for Claude to verify its work along the way? And the verification I think is probably the single most important thing that people do not get right
Boris Cherny: We Cut 80% of Claude Code's Prompt Said 27 Jul 2026
Elaborate agent scaffolding is unnecessary: a task plus a way to check the output is enough to keep a model working for weeks.
You don't need slash goal, you don't need slash loop. These help, but really all you need is give the model the task, give it a way to verify the output of its work so it doesn't get stuck, and it will just go.
Boris Cherny: We Cut 80% of Claude Code's Prompt Said 27 Jul 2026
The failure mode of experienced engineers with AI is over-specifying: telling the model to do the task exactly the way they would have done it.
So when I look at engineers that have been, you know, coding for a long for a long time, you know, like for for years or for decades, this is a really really common failure mode is trying to over specify and it's trying to be overly specific and then, you know, get the model to do the to do the task exactly the way that you would have done it. And that that's just not the way the model works.
Boris Cherny: We Cut 80% of Claude Code's Prompt Said 27 Jul 2026
Orchestrating thousands of agents is a new form of test-time compute, a fourth lever alongside network size, training data and training flops.
Like this is actually like a new form of test time compute. Like when we talk about the scaling laws and kind of we talk about the model getting more intelligent over time, historically, it's been a function of the size of the neural net, the amount of training data, and the number of flops that you put in to the training. And then recently, we also added test time compute. So this is essentially a fancy way a researcher way of saying how many tokens does it generate. And now dynamic workflows are essentially a new way to orchestrate test time compute.
Boris Cherny: We Cut 80% of Claude Code's Prompt Said 27 Jul 2026
Software maintenance is on the path to being fully automated, with scheduled agents already doing what used to take dozens or hundreds of engineers.
we're on the path to fully automating the maintenance of our apps by doing this. And this is again hundreds of agents running every day, sometimes thousands of agents every day. It's doing the work of you know, dozens or hundreds of engineers.
Boris Cherny: We Cut 80% of Claude Code's Prompt Said 27 Jul 2026
Coding is solved for the kind of coding he does, and not for everyone: deep systems work, distributed systems and pixel-level UI checking still defeat the model.
So coding is solved for the kind of coding that I do. It's not solved for everyone. You know, there's still code bases that are like super deep systems code bases where quad still struggles.
Boris Cherny: We Cut 80% of Claude Code's Prompt Said 27 Jul 2026
Working with models has stopped being a theoretical science and become an empirical one, so your priors from computer science class are a hindrance.
And it's really about being empirical. So forget all of the things that you learned about past models. Forget everything that you've learned about computer science theory in class. Look at the model, try to do a task, see where it struggles, and then based on that adjust. So it's just like very much become it's not a theoretical science, it's become an empirical science.
Boris Cherny: We Cut 80% of Claude Code's Prompt Said 27 Jul 2026
There are dozens or hundreds of things today's models can already do that nobody has discovered yet, and they are found by playing rather than by planning.
And my hypothesis is there's probably dozens, hundreds of opportunities like this with the models of today that no one has yet realized.
Boris Cherny: We Cut 80% of Claude Code's Prompt Said 27 Jul 2026
With a good enough plan, a coding agent implements the whole change in one attempt.
once there is a good plan, it will one-shot the implementation almost every time.
Building Claude Code with Boris Cherny — The Pragmatic Engineer Said 4 Mar 2026
A migration must be finished once it is started, because a half-migrated codebase confuses models as much as it confuses people.
always make sure that when you start a migration, you finish the migration.
Building Claude Code with Boris Cherny — The Pragmatic Engineer Said 4 Mar 2026
Working prototypes have replaced product requirement documents.
There’s just no way we could have shipped this if we started with static mocks and Figma or if we started with a PRD.
Building Claude Code with Boris Cherny — The Pragmatic Engineer Said 4 Mar 2026
The scarce skill is now context switching across parallel agents, not sustained deep work.
It’s not so much about deep work, it’s about how good I am at context switching and jumping across multiple different contexts very quickly.
Building Claude Code with Boris Cherny — The Pragmatic Engineer Said 4 Mar 2026
Build for the model six months from now, not the model of today.
At Anthropic, we don't build for the model of today, we build for the model of six months from now. And that's still my advice to founders that are building on LLMs.
Y Combinator, quoting Boris Cherny on the Lightcone Podcast Said 25 Feb 2026
NPM and NodeJS should do more to make it easy to use ES Modules.
NPM and NodeJS should do more to make ES Modules easy to use
NPM and NodeJS should do more to make ES Modules easy to use Said 19 Jun 2024
New JavaScript projects should default to ES Modules (type=module) rather than CommonJS.
We should make type=module the default for new package.json files for the npm init, yarn init, and pnpm init commands.
NPM and NodeJS should do more to make ES Modules easy to use Said 19 Jun 2024
CommonJS is harder to statically analyze than ES Modules and its synchronous module loading is less efficient at runtime.
CommonJS can be challenging to statically analyze, and uses an inefficient, synchronous module loading algorithm at runtime.
NPM and NodeJS should do more to make ES Modules easy to use Said 19 Jun 2024
In-person interaction with coworkers cannot be replaced by remote or asynchronous work.
there is simply no alternative to seeing your coworkers in person, catching up about their families and lives without the ticking clock of a virtual meeting, and grabbing beer after-hours to kvetch and ideate and get to know each other as friends.
Learning to work (very) remotely Said 10 Dec 2023
As people become more senior in an organization, it demands more of their time and attention, leaving less room for individual contributor work.
I realize I was doing the work that other engineers should have been doing, but often couldn't due to the realities of being in an organization that demands more of your time and attention as you grow more senior.
Learning to work (very) remotely Said 10 Dec 2023
Most investment returns come from long-term compounding rather than the price paid at purchase.
most of your gains come from the long-term effects of compounding, not from the price you bought at
Time and Timing Said 7 Sept 2022
Knowledge compounds over time, improving the quality of decisions and outcomes throughout a person's life.
Like an investment, your knowledge will compound to improve all the choices you make and things you do throughout life.
Time and Timing Said 7 Sept 2022
A great idea and good execution are not enough for a business to succeed; timing also has to be right.
Successful businesses don't just have a great idea and execute it well, but they need to do it at just the right time.
Time and Timing Said 7 Sept 2022
What is a korrent?
A korrent is a belief a person has stated in their own words: one sentence stating the claim, backed by a quote and a source, kept at korrents.com.
Under a name here, the quoted block is what they actually said. The korrent beneath it is the claim those words support, in korrents' wording — tap it to see the record, its source, and who else holds it.
Nobody here wrote their own korrents. They are compiled from public statements, and a person can change their mind, which is recorded too.
Recommends rcmnd
rcmnd What they recommend 13 things — each backed by an exact quote.
Compiled by rcmnd.app, not by them: the quotes are theirs, and each links to the post it was copied from.
Recent
Uses TLA+
TLA+ also works well. I sometimes combine Lean and TLA+ to look for issues around data flow, concurrency, and state mgmt.
x.com 22 Sept 2026
Uses Lean
I used Opus 5.5 to formally verify the Claude Agent SDK using Lean. A couple short prompts = 16 PRs fixing various bugs and race conditions.
x.com 22 Sept 2026
Uses Opus
I used Opus 5.5 to formally verify the Claude Agent SDK using Lean. A couple short prompts = 16 PRs fixing various bugs and race conditions.
x.com 22 Sept 2026
their own
Show 10 more
Recommends Projects
Projects are how I write a lot of my code these days. Really excited for everyone to try the new experience! Rolling out now
x.com 17 Sept 2026
their own
Loved Claude
Simple enough for everyone to access Claude's full capabilities. I've been using this experience every day for the last few weeks, and it feels awesome. Simpler, faster, and more powerful.
x.com 16 Sept 2026
their own
Liked Claude
Super cool way to use Claude https://www.vals.ai/blogs/fable-solves-cyphral-distich
x.com 14 Sept 2026
Recommends Threat Intelligence report
The latest Threat Intelligence report is an absolutely terrifying and important read.
x.com 11 Sept 2026
Loved Fable 5.1
This model is a pleasure to work with, and I've been using it for everything.
x.com 1 Sept 2026
their own
Uses Auto mode
The team and I use Auto mode exclusively, and have been for many months. I couldn't imagine going back to permission prompts! Really excited to get this out to everyone.
x.com 7 Aug 2026
their own
Liked Claude Opus 5
Opus 5 is a great model for coding, data analysis, design, biology, knowledge work.
x.com 24 Jul 2026
their own
Recommends Claude Code /checkup
Loved Claude Code Artifacts
Artifacts in Claude Code have been life changing. Excited to expand to Pro and Max!
x.com 2 Jul 2026
their own
Uses Workplace
Instead of meetings, I used Workplace posts (Meta’s internal version of Facebook Group posts) to share thoughts, start discussions, and make announcements.
borischerny.com 10 Dec 2023
their own
Where they publish
Site borischerny.com Their own site and blog.
A small personal site: posts on TypeScript, tooling and building developer products, plus pointers to the books and talks.
Recent
- I am often wrong 19 Sept 2026 [I shared this note with my team earlier this week, and am posting it here as well. I hope it is interesting or helpful for others working on building product in the age of AI.]
- NPM and NodeJS should do more to make ES Modules easy to use 19 Jun 2024 Coming back to JavaScript and TypeScript after a few years neck deep in Python and Hack, I kept hitting a number of new, cryptic errors when running NodeJS code in my dev environment:
- Learning to work (very) remotely 10 Dec 2023 For the last year and a half, I have been working at Instagram in Japan. It’s a bit of an unusual setup: I live and work remotely from Nara, Japan, in a timezone that few other Meta engineers work in (most of Instagram…
Show 7 more
- Time and Timing 7 Sept 2022 You often hear that “timing matters”. It helps to think about this as two related concepts: time and timing.
- Dinosaur Food: 100 million year old foods we still eat today 17 Jan 2022 I just finished Oliver Sacks’ excellent Everything in Its Place. In it, he mentioned as an aside that the Ginkgo biloba tree is hundreds of millions of years old, and its phenotype has been practically frozen since then…
- Data Management on the Web Still Sucks 13 Mar 2021 It’s 2021, and data management on the web still sucks. This is crazy!
- React+TypeScript: Use unions of objects for props 24 Dec 2019 When typing React component props using TypeScript, I often see code that makes use of optional and nullable fields:
- On Contagion 8 Sept 2019 If you have a tree with a node that has a property P, and all of its parents also need to have property P, then P is contagious.
- 13 Tips for Writing a Technical Book 26 May 2019 I spent the last year and a half writing my first technical book for O’Reilly (Programming TypeScript). I’d never written a technical book before. In fact, prior to the 300-page book, the longest thing I’d written was a…
- On Derived State 10 Aug 2018 Derived state for frontend applications comes up a lot. State B depends on State A, so after you update A, by the time you read B you want it to be updated based on the latest value of A. There’s a bunch of ways to mode…
Link verified 21 Sept 2026. Recent items update automatically from the channel.
x.com @bcherny Where the Claude Code work is narrated.
The active channel: notes on building Claude Code, agent tooling and developer workflow, and where most of the positions on this site were said.
Recent
- Over the last few years, we have made significant progress on prompt injection for Claude models. As agents do more, it is increasingly urgent that we solve it across the industry. Really excited to partner with Gray Swan to host this competition. Can’t wait to see what you find! 15 Oct 2026
- Sometimes I read on flights, and sometimes… 8 Oct 2026
- Haiku 5.5 is a good Haiku. With 100k token context, it's also 10x cheaper than Haiku 4.5 7 Oct 2026
Show 17 more
- I am surprised that people are surprised this is how I prompt Claude. Talk to Claude the way you would a coworker. There's no secret to prompting. There's no need to be overly scaffolded or prescriptive for most tasks -- give Claude a goal, and it will figure it out. Back in the Sonnet 3.5 days, your prompt mattered a lot. Nowadays, it's much more important to communicate to the model: 1. What you want it to do 2. How much effort you want it to spend 3. How it should verify that it did the right thing 6 Oct 2026
- I asked Opus 5.5 to make an interactive website companion for the latest @AcquiredFM Home Depot episode. It came out pretty nice! Water color illustrations all drawn by Claude, too: https://t.co/Camrfu3bwT Episode here: 6 Oct 2026 acquired.fm
- Mods are absolutely insane. You can now customize Claude to work and look the way you want by just prompting it. Each person works differently, so there's no reason why everyone should have an identical Claude experience. Make Claude your own, and share mods as plugins so others can try your mods too. 1 Oct 2026
- Sonnet 5.5 fixing a bug with Claude Code. 30% faster and 30% less usage. 28 Sept 2026
- Can’t wait to see what you build. 26 Sept 2026
- Tag writes >50% of my PRs every day. It also does ~100% of my data analysis, and fixes most of our product feedback + bugs. It's not like a regular Slack bot. It is proactive, programmable, it has memory, it has access to your connectors. With Opus 5.5 and Fable 5.1, it has strong judgement. Example prompts I use: - "@Claude react to threads in this channel with ✅ when resolved" - "@Claude from now on, attempt to repro every bug in this channel end to end, running the full app. once you reproduce the bug, put up a pr to fix it and tag the right team for code review" - "@Claude brainstorm ~100… 25 Sept 2026 claude.com
- It was an honor to meet Donald Knuth at the Computer History Museum today 24 Sept 2026
- If you've noticed how fast https://t.co/9A6X5iqpbs and the Desktop app have become in the last few weeks, here's how we did it. Lots of juicy learnings & techniques in the blog post for engineers working on speeding up your own apps. 23 Sept 2026
- I used Opus 5.5 to formally verify the Claude Agent SDK using Lean. A couple short prompts = 16 PRs fixing various bugs and race conditions. Video attached. TLA+ also works well. I sometimes combine Lean and TLA+ to look for issues around data flow, concurrency, and state mgmt. I don't know either language well, but Claude is excellent at both. This approach is super useful for formally modeling your code and finding bugs that a human probably wouldn't have spotted. Is formal verification the future of coding (or at least, bug finding)? 22 Sept 2026
- Opus 5.5 is a really good model. It's been my daily driver the last few weeks. We had Opus 5.5 and Fable 5.1 each port HAProxy from C to Rust. Both passed nearly all of HAProxy's tests, but Opus 5.5 finished in 9.5 hours compared to Fable 5.1's 12 hours, and for 51% less cost. 22 Sept 2026
- 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] 17 Sept 2026
- Projects are how I write a lot of my code these days. Really excited for everyone to try the new experience! Rolling out now 17 Sept 2026
- Also today: Claude Docs, Claude Slides, and Claude Design are in every conversation. Ask Claude for a presentation and you get one you can open, edit, and export as PowerPoint or PDF. Same for a document or a design. There's no separate tool to navigate to. They're just in the chat. 16 Sept 2026
- Claude Code showed that AI could do real work, not just answer questions. Developers hand Claude a feature, come back to shipped code. That's where much of the industry's serious engineering runs now. Cowork proved knowledge workers could do the same: hand Claude the brief, come back to finished files. Today, chat and Cowork start merging into one Claude. The direction: one Claude that carries context across everything you're working on, wherever you are. Simple enough for everyone to access Claude's full capabilities. I've been using this experience every day for the last few weeks, and it f… 16 Sept 2026
- Claude Mods are landing now. Someone already built a Tetris-in-Claude mod 🤯 See issue for the latest community update, technical details, and more cool demos 14 Sept 2026
- Fable solved the Cyphral Distich (a 370 year old cypher). Super cool way to use Claude 14 Sept 2026 vals.ai
- The latest Threat Intelligence report is an absolutely terrifying and important read. As models become more intelligent, without the right safeguards and monitoring they also become more dangerous. Many capabilities are dual use: a model that codes well can be used to hack critical infrastructure; a model that assists with biology research can also be used to engineer the next pandemic. These issues are complex, thorny, and increasingly important for everyone to understand so that the world can weigh in and respond to rapidly escalating risks. 11 Sept 2026 anthropic.com
Link verified 1 Sept 2026. Recent items update automatically from the channel.
GitHub bcherny TypeScript tooling and a long tail of projects.
Several hundred repos, mostly TypeScript tooling — json-schema-to-typescript among the widely used ones.
Recent
- bcherny.github.io — My blog 20 Sept 2026
- json-schema-to-typescript — Compile JSON Schema to TypeScript type declarations 7 Sept 2026
- redirect-claude 12 Jun 2025
Show 5 more
- anthropic-stream-repro 4 Jun 2025
- undux — ⚡️ Dead simple state for React. Now with Hooks support. 8 May 2025
- mcp-ping 12 Dec 2024
- es-module-stats — Collecting statistics on how the internet uses ES modules 19 Jun 2024
- json-schema-to-typescript-browser — Browser demo for json-schema-to-typescript 2 Jun 2024
Link verified 1 Sept 2026. Recent items update automatically from the channel.
About the English under a post
Some people here publish in a language other than English. Where they do, this site shows a machine translation beneath the post, in this typeface — the site's own, not theirs.
The post itself is never changed, moved or hidden: what is set in the serif above is exactly what the person published, and it is what to quote them on. A translation can be wrong in ways that matter, especially about tone.
Only the post's own words are translated. A quoted post, a linked article and a belief on korrents.com are left in their original language.