I am often wrong (borischerny.com)

120 pointsby bcherny10 hours ago103 comments

alasano an hour ago

Haven't seen any Claude Code specific examples of Boris admitting he's wrong and then actually fixing things in the way the community wants.

There are mind blowing bugs in CC that go unaddressed for months.

Something like 15-20% of all Fable messages in CC are invisible to users. You've most likely noticed this when Claude references something it said but it never said it?

It happens frequently when Fable outputs a message above a certain number of tokens just before doing a tool call.

This has been going on for months. If "users can't see messages the agent sends" isn't a critical issue that gets addressed within 24 hours, I don't really care if you admit you're often wrong, we know.

dimitri-vs 33 minutes ago

He would, but he keeps hitting his weekly limit. /s Seriously though, you would think they would have the (agentic) resources to do better QA on their flagship product. Not a week goes by without some kind of regression.

bellowsgulch 33 minutes ago

I don’t even know why someone would write and post a blog article this banal.

Everyone lives this way. You may say, “No, many people very much do not,” and you’d only be right in the shallow, vapid, explicit sense.

But even in the unconscious, passive mind, do people live this way.

Why post?

Hey, look at me I’m a rational human being who strives for constant progress. I use expressions like “update your priors” to show you what ideological circles I identify with.

Just shut up dude. Show me your numbers or shut up.

nullbio 27 minutes ago

Anthropic never listens to their customers or community. It's basically their culture at this point.

bcherny 21 minutes ago

Author here. How can I repro what you’re seeing? Double check you don’t have /focus mode enabled.

pclowes 6 hours ago

Having listened to him give a couple of talks I am always struck by how much he talks and writes like Claude code.

I don’t think he farms out all of his writing and talking to LLMs. I don’t think Claude code was trained to emulate him or anything.

I think his “voice” has been filed LLM smooth by years of agent based interactions. He claims Anthropic engineers use an average of 500+ agents a day. They are human interfaces to token generators more than human to human communication. They are picking up the tendencies of their most frequent communication partner.

Unfortunately, I see Claude being wrong often enough that I view it as a faulty narrator. Often helpful, sometimes totally full of it.

And now I subconsciously apply this filter to anything that sounds like Claude.

Makes me nervous that my voice may be becoming that of a faulty narrators.

bmitc 6 hours ago

> He claims Anthropic engineers use an average of 500+ agents a day.

What are they doing all day with that, I wonder?

simonw 6 hours ago

Does that mean 500 separate agents or 500 agent sessions I wonder.

bdangubic 6 hours ago

the former

simonw 4 hours ago

What does that mean though? Does it mean there are more than 500 different "agent" systems within Anthropic and employees interact with most of those in a daily basis?

sitkack an hour ago

That isn't humanly possible, you will blow out your neurotransmitters and not be able to think. Only being semi serious, but we can't make that many decisions a day.

Kim_Bruning an hour ago

Right, but you can imagine eg a hierarchy, in which case you might only talk with -say- 10 reports directly.

sitkack an hour ago

That isn't typically how abstraction is tallied. The ceo doesn't say they use 15k employees, or the programmer uses 30B transistors. Or the director uses 120 workers. You enumerate what you actually interact with.

pixl97 6 hours ago

Well, trying to make RSI for one so humans don't have to do that work.

LLMs are still a very new technology in relation to human timeliness. There is a whole lot of exploration to be done.

saghm 3 hours ago

I mean, in relation to human timelines, so are computers in general. It's not close why you think that this is unique to LLMs.

pixl97 6 hours ago

To err is human.

Higher level thinking has fewer constraints on being wrong than lower level subconscious thinking. Low level stuff tends to have some repetitive and evolutionary basis. Higher level thought tends to be more one off, less evidence based, and more exploratory until we get to the point of being an expert around particular concepts.

A huge amount of human thinking is being a parrot and repeating statements without a deeper understanding. For example when I say 1+1=2 I'm not thinking about it. If I say 638483+949948= calculation is necessary.

So in this, your voice has always been one of a somewhat faulty narrator, LLMs just may be further degrading the quality of the narration.

mpalmer 5 hours ago

Left, right, higher, lower, male, female. People love to explain the brain by dividing it in half, or into poles.

Nothing more human than to label, simplify and categorize, even in the absence of higher quality information.

pclowes 4 hours ago

Lets say you have a colleague named Bob. Bob is a pretty good engineer, but he is as confident when he doesn’t know as when he knows.

You can never tell his degree of confidence in his answer. For low-level things he is pretty good but for critical high-level things it is more ambiguous.

You work around this by checking Bob’s work. Having formal verification steps to check what he says.

Now let’s say you meet Bob’s twin brother Bill. Who talks and sounds just like Bob. He makes fairly grand high-level statements that you can neither test nor verify.

How much do you intuitively distrust him?

ramesh31 6 hours ago

>"They are human interfaces to token generators more than human to human communication. They are picking up the tendencies of their most frequent communication partner."

I see this happening at work, too. All communication and collaboration between engineers has broken down. Juniors don't have questions anymore. Seniors don't discuss architecture anymore. Everyone is just off in their own world of feature work with the only interaction coming at merge time. Really depressing what has happened to our trade.

infamia 7 hours ago

> Something that people learn quickly when they work with me is that my approach to pretty much every problem is: > ... > 6. Act with urgency to achieve the goal

If everything is urgent, then nothing is. This guy sounds miserable to work for and with. Assuming this is accurate and not just hyperbole, he is essentially saying he has no prioritization skills because everything is urgent. I think most people who have been around the block have worked with people like this, and unbeknownst to them, their coworkers develop a default snooze button associated with most of their requests and projects.

goostavos 6 hours ago

Heavens. Is it possible you're reading into it a bit? He's miserable to work with? From this one blog post?

A more generous read, or, at least the reading I took: "once we (think we) know what we're doing, we violently execute."

So, "boo" on you. This guy sounds awesome.

kevinkoning 6 hours ago

I was literally writing almost this exact post but decided to reload the page first.

dyauspitr 6 hours ago

Developers get triggered about managers breathing down their neck when they read things like this that’s why you get such strong reactions.

thunderfork 6 hours ago

I disagree, on the principle of "slow is smooth, smooth is fast"

TeMPOraL 6 hours ago

This principle is basically a movie quote, though.

magicalist 5 hours ago

No it's not, though?

whateveracct 2 hours ago

and similarly, the need for slack in software teams

phoghed 6 hours ago

How often do people that make this kind of assertion end up themselves being the ones that are miserable to be around I wonder

infamia 5 hours ago

> Heavens. Is it possible you're reading into it a bit?

Perhaps, which is why I hedged with the possibility that it is mere hyperbole. However, I think what did it for me was his statement that he provides and expects feedback to anyone not following this recipe, which is at utterly without nuance. Incidentally, you can execute with focus and intention without urgency and arguably be more effective over the long haul.

saghm 3 hours ago

If someone literally publishes on the internet that they require their employees to act like every problem is urgent, it's not clear why you think we shouldn't take them at their word. It's a pretty common thing for bad managers to expect people to work full-tilt 100% of the time rather than understanding that tends to burn poorly out. I'm honestly not sure how someone could spend a decent amount of time in this industry and not be able to recognize that pattern and have thoughts about how to avoid it unless they just don't really care about it much, so while you're entitled to disagree, it's hard not to get the impression that being so affronted by the parent comment pointing out that the blog post doesn't seem to address the very real pattern of phrases like the article uses being euphemisms for pretty horrible work cultures that you just also don't particularly care about it.

Personally, I've seen far too many talented people in tech be worked too hard for too long by management that either is too clueless or too uncaring to the point where it can take years for their health and happiness to recover not to find it extremely alarming when someone says stuff like "everything is urgent". The likelihood that they mean pretty much exactly what they say rather than mean something more nuanced is high enough that the fact that don't seem concerned about the implication says more than enough.

tayo42 23 minutes ago

It's not saying treat every problem as urgent, it's saying go through 5 steps that are defing the problem correctly then treat it urgently.

bmitc 6 hours ago

This list also makes zero sense. It says to gather missing information after gathering all known information but before defining a problem. How could you even know what information is missing, much less information that is important, without knowing the problem? And if you're to gather missing information, that you somehow know about, doesn't that make it part of gathering known information? The rest of the list is just as dumb. This list is like a middle schooler was asked to come up with a problem solving framework.

This guy is usually all over threads in which he gets to show off his internal knowledge of Claude Code. I'm sure he'll be here after getting clowned.

The entire Bay Area seems like the most insufferable people known to man. These people have zero introspection.

bjustin 5 hours ago

> It says to gather missing information after gathering all known information but before defining a problem. How could you even know what information is missing, much less information that is important, without knowing the problem?

The post’s description of these steps is reasonable IMO. I’d write it as “put in order the relevant information you have” and “find the information which you know you need but don’t have at hand”.

By way of bad analogy, one could imagine writing up a document first off the top of your head, then filling in more of the document based on the documentation of the relevant systems, corresponding to these two steps the author describes.

ccapitalK 34 minutes ago

There are multiple ways to read what the author said. I personally read it as urgency relative to other stages in the lifecycle, not other tasks you are balancing it against. So if you have five things you are slowly shaping into an executable state, with four of those in the requirements gathering/solution shaping phase, as soon as the fifth ticks over into a state where the solution is ready to implement, you should focus on implementing the solution over shaping other tasks.

To me this seems like a viable approach, and one that isn't obviously the correct approach (but what if busy stakeholder X only has time to discuss unrelated task Y 30 minutes from now? Do you still sit down to work on the shaped task to completion?). Choosing this approach isn't without its downsides, so choosing it is a deliberate decision with its own tradeoffs.

cube00 8 hours ago

I can't say I agree with forcing your team to use your own personal "framework" of approaching a problem or else you'll get "feedback".

> Sometimes I will give feedback to people when they are missing steps in the framework, or are poorly executing some of the steps. I expect the same feedback in return.

I also don't like that urgency is built in as the standard process either, no wonder everyone is burnt out.

> 6. Act with urgency to achieve the goal

CSSer 8 hours ago

But if you don't only surround yourself with people who think exactly like you, how will you ever recruit an army of yes men and women?

nerevarthelame 6 hours ago

I'll rent an army of yes agents instead.

adamsb6 7 hours ago

It’s basically OODA loop, which is itself just as descriptive of how people act and adjust than it is prescriptive.

How else would you describe iteratively solving problems?

baxtr 7 hours ago

Interestingly enough the problem with most of problem solving is identifying the right problem to solve.

It may sound weird but OODA starts making sense once you’ve identified the right problem to focus on.

In its original definition it was based on dogfights. There, your problem is clearly defined.

datadrivenangel 7 hours ago

and the fun question of how do you find good problems is very hard to systematize!

knollimar 5 hours ago

These steps, but in many other arbitrary orders, some with feedback to previous steps

jsw97 7 hours ago

Acting with urgency is a bit at odds with discovering flaws in your plan. If you're sprinting you're less likely to notice smells and things that are inelegant, more likely to paper them over. That said, there is a time for urgency. Just not every single task.

glimshe 8 hours ago

Nothing more annoying than a manager with a personal know-it-all framework requiring people to follow it or else they get "feedback".

dofm 8 hours ago

He's often wrong, don't you know.

Just not about your performance review.

bcherny 14 minutes ago

Author here. This isn’t the one true framework, but it is the one I use. The goal of this post was to communicate to the team the way I think. There are many ways to think and there isn’t one that is more correct than others.

The word “feedback” might be overloaded here also — if you haven’t worked in a culture where feedback is an honest, no-blame part of the culture, then I can see how the idea of giving feedback can feel like a disingenuous corp-speak way to make a person fall in line or have their career impacted. There’s also an inherent power dynamic in giving feedback. However, if the work culture celebrates feedback as an honest way to have more direct conversations, and makes coworkers feel psychologically safe talking to one another directly in this way, it is something that makes culture better for everyone and gives better results in the end. I have given feedback to many people, and I have received it in turn many times.

Also, I am an IC, not a manager.

weakfish 6 hours ago

I still am mind blown at how bad CC is as software. It’s just not that hard of a problem. I get that harnesses aren’t trivial, but they’re not insane either. And the fact that it’s running on a JS runtime (that they bought!) is also crazy. Why not Go/BubbleTea? Why not literally anything native? It makes no sense

I don’t want to be a jackass, but it’s hard to take anything Boris says seriously when he’s headed up such weird software. And it’s not like resourcing or money is an issue for them. If Claude was so damn good, why does CC suck?

bmitc 6 hours ago

Turns out he just used what he knew, TypeScript, and not what best solves the problem. He must have not had his "framework" then.

watt 6 hours ago

Claude Code is also offered as an SDK, you can build custom (customized) harness on top of what essentially is Claude Code. https://code.claude.com/docs/en/agent-sdk/overview

simonw 6 hours ago

I'll be honest, I don't actually understand what people mean when they say Claude Code is bad software.

Seems pretty good to me. Presumably this is about the TUI version?

metaltyphoon 6 hours ago

Do you really think that having this many issues is justifiable/ok?

https://github.com/anthropics/claude-code/issues

tripledry 5 hours ago

I dont't really know stats about such things, but I assume the adoption of CC has been insane compared to almost anything, and is also like two years old? Yeah, not surprised.

But also, if they all use 500 agents daily and latest models can "one shot" everything, one would think 5k issues are fixed in no time...

Havent used CC in some time, worked fine last time I tried.

metaltyphoon 4 hours ago

> But also, if they all use 500 agents daily and latest models can "one shot" everything, one would think 5k issues are fixed in no time...

IMO, CC should be the poster child of what LLM coding should "feel" like. If things are so good why are there so many issues? Why can't they get a handle like other well-run projects? As you said, they have unlimited tokens so this project should be close to pristine as much as possible.

simonw 4 hours ago

Those numbers don't really mean anything. Claude Code has millions of users, and that issue forum is the most obvious place for them to ask questions or request features.

If there were 11,000 open and confirmed bugs then yeah, that would mean the software is bad.

metaltyphoon 4 hours ago

> Those numbers don't really mean anything

IMO this is very dismissive. One example of probably many more, where software is used by millions and yet doesn't have this much being reported.

https://github.com/curl/curl/issues

simonw 2 hours ago

curl isn't end-user software, and has a very small, well defined surface area.

infamia an hour ago

No one knows how many bugs claude has because Anthropic auto-closes Issues (or at least used to) if there isn't someone constantly pinging the issue every two weeks. I've contributed to several issues that were confirmed by several other people, which were they were auto-closed after people gave up confirming the problem without any response from Anthropic. They seemingly don't care if it isn't on fire or at least smoldering heavily, which seems really bad in my book if you're trying to make even reasonably good software.

simianwords 5 hours ago

I'm surprised you think Claude Code is good software. I find it so hard to use because it is fundamentally constrained as a TUI. It is buggy, clunky and slow. It is sooo slow.

One example of what is particularly bad with it: tool calls and progress. Codex UI does it so much better. The way in which CC waits for a task to complete etc is really poorly done compared to Codex.

Another thing that's missing: no way to continue a side chat in Claude Code - this is easy in Codex with /side and it is super usefu.

simonw 4 hours ago

Claude Code has /btw which I think is the equivalent of /side in Codex.

I don't think Claude Code is perfect software, but I don't think fact that Codex has a slightly nicer implementation of certain patterns makes Claude Code bad software.

fractorial 6 hours ago

I’ve rolled my own harness in Go. I have a rule to not let the production LoC exceed 50k lines. It is _very_ nice for my use cases. DeepSeek Flash V4.1 often performs at the level of GPT 5.6 Sol for non-orchestration tasks (programming and maths).

I add features and tweak it all the time: You just need to get comfortable with spending 3 hours in a chat session every 3 weeks to think hard about how to simplify whatever slop you didn’t simplify the last time you did this :)

weakfish 2 hours ago

Is it open? I'd love to take a look and perhaps steal some ideas :)

ares623 2 hours ago

They're a small bootstrapped startup, give them some grace.

otterley 8 hours ago

This seems strongly aligned with the Amazon doc-writing and decision making process. I found it to be unusually effective as a business process, and took it with me when I left to my current role.

Making thoroughly informed decisions and iterating on a decision doc before committing to a direction and plan is better than every alternative I’ve ever observed in my career.

The criticism I’ve read thus far on this thread seems unwarranted. I give the same kind of feedback to my mentees when their work product or process could use improvement.

margalabargala 7 hours ago

> Making thoroughly informed decisions and iterating on a decision doc before committing to a direction and plan is better than every alternative I’ve ever observed in my career.

My last company did this. It usually devolved into a design-by-committee full of compromises to make various stakeholders happy and often yielded a worse artifact.

It became more effective once people got burnt out on the process and most stakeholders stopped caring and started rubber stamping, allowing the one or two people willing to put in the energy to come up with something coherent.

saghm 2 hours ago

I worked for AWS for several years, eventually leaving during the big "return" to office push because my geographically distributed team working on a product that didn't exist back before the remote period was told we had a month to either move to one of three cities where our team was allowed to work out of our transfer to a team in our area. My wife had an autoimmune condition that would put her at risk if I commuted, so I asked my manager what processes there were for exemptions, but he literally hadn't been told anything by the higher-ups and that as far as he was aware, there were no processes defined at all and we'd have to just try to talk with HR and upper management to try to figure something out. I didn't think that the company expecting me to rush to figure it out when they were the ones who put an artificially constrained timeline on us to either abandon what we had been working on it uproot our lives, so I ended to just giving my notice a couple of days later instead.

My point here is that companies that love to have extremely formal processes around for to handle technical things are not necessarily less likely to have extremely arbitrary decisions without any process for recourse defined when it comes to how employees get treated. If someone describes a technical process that they say they use for everything that a literal reading seems pretty dubious in regards to things like burnout or micromanagement, I don't think it's that crazy to recognize that the reality is probably at least as bad as the obvious implication. Sure, they're not directly saying "I overwork my employees by imposing short deadlines on everything and I nitpick their processes if they different from my own", but there are enough managers who do act this way that it's kind of hard to think someone who cared about being perceived as saying that wouldn't go out of their way to clarify where the nuance is if it truly exists.

AdieuToLogic an hour ago

Right and wrong are forms of judgement, subject to debate, and sources of resentment.

Correct and incorrect are at least possibly quantifiable and do not intrinsically involve subjectivity.

In other words, my being incorrect is something others can help me to understand and rectify. My being "wrong" is a position which can yield second order harm.

Imanari 8 hours ago

Steps 1–5 of his framework are increasingly formal ways of saying “figure out what’s going on before doing something,” followed by step 6: “then do it fast”

verdverm 7 hours ago

“let Claude figure out what’s going on before doing something”

“then ask Claude to do it fast with no mistakes”

(edited for accuracy)

dcj4 35 minutes ago

Well maybe stop posting then and leave it to people who are not often wrong.

joduplessis 6 hours ago

It is strange how people who say they are "often wrong", never quite sound like they take that into consideration when delivering opinions or thought pieces - I see it fairly often in tech. Anyways; nothing against Boris, but Anthropic/Claude has certainly been the first company (& product) too annoying for me to use.

nullbio 24 minutes ago

It's because it's some weird form of virtue signalling/humble brag. Nothing genuine about it.

jascha_eng 7 hours ago

That's what it took to finally support Agents.md I guess. Boris had to blog about having made a mistake.

How about you stop taking things so personal instead and let others steer more.

bcherny 6 hours ago

Author here. These are unrelated, just happened to both be the same week.

6LLvveMx2koXfwn 8 hours ago

Unlike me, 56 and yet to be wrong once.

dofm 6 hours ago

It is a burden all of its own.

trunnell 3 hours ago

> 3. Define the problem

If you do this step well, in my experience, the next steps fall into place quickly.

My version: accurately naming the problem is the essence of problem solving. There are things you usually need to do before you can accurately name the problem, because most problems aren’t presented to you in textbook form.

Once properly defined and framed, it’s obvious how to solve most problems, most of the time.

If you’ve ever worked with someone amazingly good at accurately naming the problem, it’s hard to unsee it. This is one of the hidden talents of the most effective people I’ve met.

fjni 6 hours ago

> I hope it is interesting or helpful

I think you're wrong. I think it's embarrassing. Though I might be wrong.

glitchc 6 hours ago

This guy doesn't think deeply about any problem, possibly because he has never had to and probably because he has never wanted to. He would probably make a good residential plumber.

rando103747202 6 hours ago

You must not be a home owner because good residential plumbers are definitely out there solving the “hard problems” that techies love to bloviate about every day.

someguy101010 7 hours ago

a foolish consistency is the hobgoblin of little minds

serjester 5 hours ago

It seems strange to write a blog post about being proven wrong, without a single example of being wrong. Especially with all the current Claude.md drama.

Everyone loves being wrong in the abstract - this reads more like a self-congratulation than a genuine reflection.

dijit 5 hours ago

Heh, I have the opposite... uh "problem".

I am often right.

This has two negative effects;

1) I start to believe my own hype because I am so consistently correct- which blinds me to other ideas if I don't actively take steps to humble myself.

(after all, I won't be right very often if I stop listening, as that's part of why I am right, because I listen to people and have a huge amount of context)

and

2) I am able to quickly come to a conclusion which makes people uneasy, as they think I haven't considered all the points even though I have- and it's also true that people have a bias to inaction unless it's an urgent issue.. this is how things get stuck in committees and meetings and continually get kicked down the road because it's difficult to get everyone together and there's a million reasons to keep deferring meetings.

What I'm trying to say is, don't sit there thinking that "if only I could make correct decisions"- because even if you are quick, correct and decisive: you will ruffle feathers.

(at the risk of sounding arrogant: i'm not saying I'm right about everything, like the red baron, I pick my battles very carefully).

0gs 8 hours ago

i am pretty sure it would just be "wrong," not "meta-wrong," and given the title, i am giving myself the point.

rzzzt 7 hours ago

I am not even wrong.

badgersnake 7 hours ago

“I am often wrong” is directly from how to make friends and influence people.

hippycruncher22 5 hours ago

We all have a short time on this planet. This desire to always have urgency, speed, more money is insane.

Humans are in trouble

Marciplan an hour ago

why does boris have this urge to become an influencer

nullbio 20 minutes ago

It makes him feel important and smart and powerful.

animalfarm 5 hours ago

Boris is a scientist, that's all that has to be said here. Keep up the great work.

preommr 6 hours ago

And yet there's none of this uncertainty or caution with his posts that then go on to have massive ripple effects because of his position at Anthropic and the marketting related to claude.

I personally have a lot of anger and frustration with many people in the ai hypesphere that are just mindlessly frolicking around without a care in the world, happy to speak into the megaphone offered by masses that are in a rat-race to avoid some AI dystopian hellscape that keep getting painted by these thought leaders... and then going "oopsies... I am just human guys... y so mad?!"