Boris Cherny
Everything, newest first — across every channel. Their profile → · Subscribe
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 20 beliefs, in the piece's order there
-
Their words
And my hypothesis is there's probably dozens, hundreds of opportunities like this with the models of today that no one has yet realized.
-
Their words
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.
-
Their words
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.
+ 17 more
-
Their words
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.
-
Their words
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.
-
Their words
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.
-
Their words
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.
-
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.
-
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!
4 March
From one piece Building Claude Code with Boris Cherny — The Pragmatic Engineer 4 beliefs · newsletter.pragmaticengineer.com
-
korrents.com
The scarce skill is now context switching across parallel agents, not sustained deep work.Their words
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.
-
Their words
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.
-
Their words
always make sure that when you start a migration, you finish the migration.
+ 1 more
-
Their words
once there is a good plan, it will one-shot the implementation almost every time.
25 February
12 June 2025
4 June 2025
8 May 2025
12 December 2024
19 June 2024
From one piece NPM and NodeJS should do more to make ES Modules easy to use 3 beliefs, in the piece's order there
-
Their words
CommonJS can be challenging to statically analyze, and uses an inefficient, synchronous module loading algorithm at runtime.
-
korrents.com
New JavaScript projects should default to ES Modules (type=module) rather than CommonJS.Their words
We should make type=module the default for new package.json files for the npm init, yarn init, and pnpm init commands.
-
Their words
NPM and NodeJS should do more to make ES Modules easy to use
2 June 2024
10 December 2023
From one piece Learning to work (very) remotely 2 beliefs, in the piece's order there
-
Their words
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.
-
korrents.com
In-person interaction with coworkers cannot be replaced by remote or asynchronous work.Their words
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.
-
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
From one piece Time and Timing 3 beliefs, in the piece's order there
-
korrents.com
A great idea and good execution are not enough for a business to succeed; timing also has to be right.Their words
Successful businesses don't just have a great idea and execute it well, but they need to do it at just the right time.
-
korrents.com
Knowledge compounds over time, improving the quality of decisions and outcomes throughout a person's life.Their words
Like an investment, your knowledge will compound to improve all the choices you make and things you do throughout life.
-
korrents.com
Most investment returns come from long-term compounding rather than the price paid at purchase.Their words
most of your gains come from the long-term effects of compounding, not from the price you bought at
17 January 2022
13 March 2021
24 December 2019
8 September 2019
26 May 2019
10 August 2018
Nothing matches.
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.
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.