Sorry folks, this is a rollout artifact, we needed a way to turn this off remotely via feature flags if it broke something, and with telemetry off you don't get those. It's already been fixed as part of v2.1.281 releasing today.
Apologies again folks, this was a fully human error on my part - I should've found a better way to launch with a kill-switch.
mpoteat 3 hours ago [-]
The AGENTS.md support was implemented via our new extensibility system for CC, called Mods, which is launching soon-ish. A mod is a plugin with a new type of hook, which we call a function hook.
Might I gently suggest that you have a model at least as capable as Opus 5.5 translate that from Claudish to English? Or, even better, have an actual human work on the docs a bit? As it stands, they are fairly egregious, and they seem to devote at least as much space to little AI-generated quips that convey no meaning than to actually explaining what’s going on.
Also, maybe a human should decide whether these are “function” hooks or “module” hooks. All of this marketing calls them “function” hooks, but the json config seems entirely unaware of this.
(Has anyone else noticed that half the sentences in Claudish aren’t merely weird: they are noun phrases and not sentences at all? I’m pretty sure that any decent pre-LLM NLP-based grammar checker would correctly flag half the sentences in Claudish. Also, whatever variant of Claude wrote this thing can’t even capitalize around semicolons consistently with itself, let alone consistently with how English has been written for at least a century.)
edit: Fixed the link. Thanks, kaszanka.
mpoteat 58 minutes ago [-]
Ouch! Much of this verbiage was dictated by me personally; I just have a fairly distinct register some might consider inscrutable. My English teachers in grade school always said the same :)
Rest assured I'll inject a bit less soul into the official docs once Mods are launched; re your feedback on the JSON key, what would you recommend?
amluto 49 minutes ago [-]
Your comment here is written in perfectly fine English :)
Maybe "function_hook_modules" for the JSON key?
Does this finally fix the limitation that there is no supportable way to replace the implementation of a native tool in Claude Code? codex-rs has an (undocumented but likely supportable if kind of awkward) mechanism, and I’m part way through a project that needs this. I was going to release it with a recommendation not to use Claude Code, but it’s at least plausible that this will change my mind. (I’m not sure yet — the $ mechanism might be too restrictive. It’s a start at least.)
xena 45 minutes ago [-]
Contact me at the email address in my HN account and we can arrange for a human with a soul and feelings to write the docs from scratch assuming you have a price in mind that values the nature of my talent and experience.
> they are noun phrases and not sentences at all? I’m pretty sure that any decent pre-LLM NLP-based grammar checker would correctly flag half the sentences in Claudish. Also, whatever variant of Claude wrote this thing can’t even capitalize around semicolons consistently with itself, let alone consistently with how English has been written for at least a century.
Probably just a case of a company hoping their scale can change the societal standard faster than they can be bothered to match the standard.
You'll talk like 2023 unsupervised TikTok generators and you'll be happy.
rickette 3 hours ago [-]
The only difference between CLAUDE.md and AGENTS.md is the filename. Do you really need a whole plugin system to support that use case? Feels like this could have been a one line change.
xandrius 3 hours ago [-]
Don't you run bizantine ralph loops on remote environments with codex security checks, coupled with jev, grok, open router and a fully independent openclaw (on a maxed out mac mini inside a caveau in an undisclosed location, with open telegram) to change constants? You're going to be left behind.
newsoftheday 1 hours ago [-]
Not related but I think I finally know how it must have felt to the generation prior to mine, when we tried to explain computers to them; because even as a retired 30 year plus software engineer, I have no idea what the comment says.
ffsm8 51 minutes ago [-]
Unc you're so cooked it's not even funny younger than me but you're out here aura farming in the negatives fr fr. NPC-ahh behavior, 0 aura, -1000 rizz. Couldn't be me
Sorry couldn't resist
Not sure what you didn't understood in their comment though, maybe the raph loop (and jev which was just released)? Isn't the rest completely self explanatory?
NicoJuicy 34 minutes ago [-]
It's almost all related to LLM's, which is fairly new.
Basically he's describing an LLM assistant setup that does coding on a vps or Mac mini ( some contradiction with Openrouter though) where you can communicate with the assistant through telegram
doublerabbit 3 hours ago [-]
You sound like my type. hey, wanna come over to myspace so I could twitter your yahoo till you google all over my facebook?
The plugin system itself was probably already in the making, and they just chose to implement this tiny feature as a plugin to try it out.
As for the only difference being the file name, that's an untested assumption. Up until now, Claude hadn't supported AGENTS.md, and it's a simple application of Hyrum's Law that somebody, somewhere, was taking advantage of that to give one set of instructions to Claude, and a different set of instructions to some other provider. The correct behaviour in the presence of both files is not obvious, either.
Having a kill switch for the change is a perfectly reasonable safety measure in case something goes horribly wrong.
Wowfunhappy 2 hours ago [-]
> somebody, somewhere, was taking advantage of that to give one set of instructions to Claude, and a different set of instructions to some other provider.
I'm this person, I am actively doing this! I have some instructions which the Claude models need and OpenAI models will do by themselves. If the OpenAI models see the Claude instructions, they will go way overboard in a way I don't want.
Mind, the change does not affect me at all, because when both instructions are present Claude continues to read CLAUDE.md and Codex continues to read AGENTS.md. But if Claude started preferring AGENTS.md, that would be mildly annoying.
californical 1 hours ago [-]
Within agents.md, an idea. Feel free to steal if you work on this:
Model.Claude*:
Do this one thing
Model.Claude.Opus.4.8:
Extra specific instructions
Model.*:
This is relevant to everyone
Harness.ClaudeCode*:
Why not, let’s allow harness specific instructions so you can do things differently depending how you’re working
everforward 34 minutes ago [-]
I did this at one point with Jinja templates.
I wrote an agent launcher sort of bash script. Pass in the command to start the agent, the script checks if there’s a Jinja file in a special directory matching that name, and builds it to AGENTS.md. Then it launches the agent.
I was trying to use it as a sort of janky RAG. I had a bunch of snippets (one for DB architecture, one for how load balancing works, etc), and my Jinja files were mostly a list of snippets to pull in. Voila, a bunch of agents that share little pieces of info but have a single source of truth.
I never got a ton of value tbh, it was very good at just grepping the snippets.
dotancohen 56 minutes ago [-]
I would like to subscribe to your newsletter.
Seriously, though, this is a great idea. Good communicators know to tailor their discourse to their audience. LLMs are just as sensitive to small variations in prompts, and just as inconsistent between them, as are humans.
Wowfunhappy 45 minutes ago [-]
It's not a bad idea, although at that point it probably shouldn't be a .md file anymore. You'd want to use YAML or something.
markhahn 20 minutes ago [-]
careful, that might lead to programming. using, you know, a programming language.
redox99 2 hours ago [-]
That line of thought is the reason why everything gets so overengineered.
Read CLAUDE.md if it doesn't exist read AGENTS.md you don't need to overthink it so much.
arcfour 2 hours ago [-]
This line of thinking is something you will quickly be disabused of once you try supporting software that hundreds of millions of people use.
And I say this as someone that loves the Unix philosophy dearly.
lunar_mycroft 2 hours ago [-]
How, exactly, would the proposed solution (combined with a setting to disable it) break, and how would implementing it the way Anthropic did address that? Be specific.
arcfour 2 hours ago [-]
Some people might have a different CLAUDE.md and AGENTS.md because they use Claude to do one thing and $other_agent to do another thing. Or because Claude does XYZ by default, and other agents do ABC, and they want to give the correct guidance to both.
This is, to me, a completely reasonable and believable use case that could break if you implement this fix without "overengineering" it.
A setting to disable what? Be specific. See? Not so simple...
lunar_mycroft 2 hours ago [-]
First, GP's proposal already addresses that. If both are present, CLAUDE.md would be used. Second, that is solved with a settings toggle. Read a boolean from .claude/settings.json and disable the new behavior if it's true (or false, depending on what you want to name the setting). third, you skipped the second part of my question: "how would implementing it the way Anthropic did address that?" Implementing the same behavior through multiple layers of abstraction and an order of magnitude more code doesn't solve the issue you mentioned.
Bonus forth point: why is this critical to solve for claude code, but not for all the other harnesses which have all converged on AGENTS.md for this purpose?
arcfour 1 hours ago [-]
Okay, so we agree that this fix isn't quite as simple as it sounds then, yes? We've just had 3+ paragraphs of discussion around potential edge cases and additional considerations beyond "read one of two files."
lunar_mycroft 45 minutes ago [-]
We've had a long discussion only because you refuse to admit that a very simple solution would work (despite completely failing to show how it wouldn't). The problem is that your opinion is not in fact proof that you're right.
dylan604 2 hours ago [-]
if [ !-f CLAUDE.md ]; then
AGENTS.md
fi
you're really over thinking this, and i'm wondering if you're risking pulling something stretching like that to pick this up shilling for Anthropic.
arcfour 1 hours ago [-]
Is accusing someone of "shilling for Anthropic" for suggesting that a bug fix might not be so simple really the level of discourse HN has devolved to now? Is it the kind of HN you want?
dylan604 20 minutes ago [-]
Is the level of HN discourse suggesting that having a large number of users worth of never making simple changes something you want? This isn't a move fast break things suggestion, this is a rational common sense suggestion. Instead, you're pushing an overly complex way of implementing something that would allow for all sorts of unknowns. Earlier comments suggesting this new mods concept was being worked on giving the dev a new 20lb sledge hammer so the CLAUDE/AGENTS situation suddenly got beat on like it was a railroad spike when it just needed a smaller hammer since it was only a finishing nail.
bakugo 2 hours ago [-]
> Read CLAUDE.md if it doesn't exist read AGENTS.md
> Some people might have a different CLAUDE.md and AGENTS.md
How exactly do these two conflict? If you have both, nothing changes.
arcfour 1 hours ago [-]
Which order do you prefer them in? Since CLAUDE.md is no longer necessary, but was for so long, what happens when users only update AGENTS.md going forward while keeping a stale, unchanged CLAUDE.md around?
We're talking about changing default behaviors here in ways that can be surprising to users. It's reasonable to try and accommodate existing setups, future setups, and - yes - careless users.
dotancohen 54 minutes ago [-]
Bash does this well, reading only the first of half a dozen config file locations it searches. And if the user needs it to read from an additional location, just add a source line to that location.
dylan604 2 hours ago [-]
I've never heard of the 'move fast, break things' mentality ever giving a damn about number of users. If so, no changes would ever be made. The great thing about having millions of users is QA can be eliminated entirely as you'll start hearing about issues from the users directly.
amluto 2 hours ago [-]
Frontier lab AI agent tools break their users’ workflows worse than this on a regular basis.
arcfour 1 hours ago [-]
What's your point? Nobody can hold themselves to a higher standard because they didn't in the past?
dotancohen 59 minutes ago [-]
> Having a kill switch for the change is a perfectly reasonable safety measure in case something goes horribly wrong.
Having a way for the user to revert the update is a perfectly reasonable safety measure in case something goes horribly wrong.
Even though Anthropic or any other software provider could technically run anything on our system, there exists a modicum of trust between supplier and user. Anthropic performing arbitrary changes that are tangential but not specific to the premise of delivering a harness to package code files and prompts in context to their LLM breaks that trust for many users.
epihelix 2 hours ago [-]
> Having a kill switch for the change is a perfectly reasonable safety measure in case something goes horribly wrong.
What, exactly, is going to go horribly wrong here ...? The worst case you're proposing is that an Anthropic model acts on AGENTS.md rather than CLAUDE.md. It's not going to be the end of the world; at worst it'll be `git reset --hard HEAD` time. But this wouldn't happen, because:
> The correct behaviour in the presence of both files is not obvious, either.
It seems extremely obvious to me: the non-breaking change is the right change here. If both exist, Anthropic models continue to use CLAUDE.md and ignore AGENTS.md. This is not rocket science. Why are we overthinking this?
hamburglar 1 hours ago [-]
> What, exactly, is going to go horribly wrong here ...?
Operating anything at scale teaches you that the universe of “things that can go horribly wrong” has a much better imagination than you. That goes quadruple with complex and squishy reasoning models.
I’ve seen a couple of really good examples of what can go wrong in this subthread, the most straightforward of which is that abruptly changing a fundamental behavior can break existing use cases.
vikramkr 2 hours ago [-]
Because when you have tons of users ainor fuckuo is a big fuckup and also it's really common to have both claude.md and agents.md and use @ syntax (which lets you reference markdown files when using Claude code, but not other harnesses) so you Claude md looks like
```md
@AGENTS.md
[Claude specific stuff]
```
And then what happens if someone now puts @syntax in their agents.md triggering a loop etc. It's all vibe coded - including code from days with dumber models - there's gonna be all sorts of dragons under the hood
speleding 2 hours ago [-]
The Claude sandbox has a slightly different ENV compared to ChatGPT (LC_CTYPE set to C instead of UTF8 I believe) which upsets some scripts we have.
So in the CLAUDE.MD we tell it about that and then tell it continue reading AGENTS.MD. Not very hard to work around if CLAUDE.MD goes away, but just to support your point that the split did have its uses for some.
bakugo 2 hours ago [-]
This "tiny feature" consists of hundreds of lines of code spread across 57 source files, many of which are less than 30 lines long, often contain more comments than code, and have no real reason to exist. It's the very definition of overengineering and overcomplexity.
That said, I do find it somewhat funny that Anthropic themselves are falling victim to their own model's tokenmaxxing.
stingraycharles 3 hours ago [-]
Yes, but at the same time, it’s also a good, simple use case to test a new plugin system. I can totally understand that.
flippingheck 2 hours ago [-]
At $FAANG, ~all changes go through feature flags.
There are processes to make changes outside of feature flags, but they have enough friction that it's easier to just use a feature flag.
This level of paranoia is consistent with the blast radius of changes breaking Claude users.
dotancohen 49 minutes ago [-]
I'd love to hear more about this. Though I usually write bespoke software for specific clients, I'm about to release my first general-availability application. It's a rust application with Python GUI on the desktop (Linux, Mac, Windows) and a skinny Android application that wraps the rust on mobile. I'm going to be gating features starting probably next week. I'd love to hear tips and experience for implementing feature flags, for both the desktop and mobile space.
Thanks!
1 hours ago [-]
chrisweekly 2 hours ago [-]
With apologies for not just testing this myself (currently AFK), doesn't it still work to have a CLAUDE.md file containing just `@AGENTS.md`?
chrisjj 2 hours ago [-]
> Do you really need a whole plugin system
Vibe-coding gotta vibe-code.
verdverm 1 hours ago [-]
need to, no, but if you put the Ai to task, expect over engineering
bakugo 2 hours ago [-]
Go download the leaked source code from earlier this year, search for all occurrences of the string `CLAUDE.md`, and be horrified.
rmnclmnt 1 hours ago [-]
Welcome to SWE in 2026
oblio 3 hours ago [-]
One line change? Pffft. That means you're still looking at the code, you're behind the times.
locknitpicker 3 hours ago [-]
> The only difference between CLAUDE.md and AGENTS.md is the filename. Do you really need a whole plugin system to support that use case? Feels like this could have been a one line change.
I don't think this is a reasonable assumption. The document format in CLAUDE.md is whatever Anthropic specifies, where AGENTS.md is a common ground format that is expected to be supported by any agent, be it from Anthropic or not.
You might argue that differences are small or negligible, but that is just an expectation.
ljm 3 hours ago [-]
It's not a format though is it? it's literally just an extension to the system prompt in plain markdown.
There is no rhyme or reason to the structure of this file, just like with most things in AI. It's best effort human language.
BowBun 3 hours ago [-]
I think you're giving these files too much credit. There are no specs, they are freeform text. In this sense they are the same. The expectation of what could be in it by each vendor means nothing unless it's enforced.
sunaookami 2 hours ago [-]
There is no "specification", it's literally just a text file that gets loaded into context. You don't even need to write markdown. It's not that hard man.
logifail 3 hours ago [-]
> The document format in CLAUDE.md is whatever Anthropic specifies
Q: Do Anthropic actually specify a document format?
Diti 1 hours ago [-]
Nope! Claude is even able to understand AsciiDoc just fine (which is a blessing). But it will always insist on the Markdown extension.
taormina 3 hours ago [-]
No, they do not.
glub 27 minutes ago [-]
I've developed several plugins for different harnesses, and I needed some upstream change for most of them.
The deciding factor for me whether or not I will work on the feature of the plugin is whether I (or rather, my agent) can look in upstream source and evaluate if it can be done with minimal upstream change, which I then contribute. And generally, even if no upstream change is needed, agents work so much better when they can read the code.
So why not just make Claude code open source? Considering also that source code was leaked once anyway.
63stack 2 hours ago [-]
>via our new extensibility system for CC, called Mods, which is launching soon-ish. A mod is a plugin with a new type of hook, which we call a function hook.
An extensibility system called mods, which is a plugin with a new type of hook that we call function hook?
I can't tell if this is real, or you are making fun of overengineered AI solutions.
Is this real?
d5lt5 3 hours ago [-]
Sounds like you've read the deepseek harness paper.
dybber 2 hours ago [-]
Will you extend your plugin to read skills and rules from `.agents`? Or should we write our own plugin/mod for that?
c0rruptbytes 53 minutes ago [-]
mods seem like a grasp at all the pi and dsh users
dotancohen 1 hours ago [-]
So what Anthropic calls "telemetry" is really "telechangeability"? That's sits with me even less comfortably than did the idea that some features are only available with telemetry enabled.
stravant 39 minutes ago [-]
That's just how big companies roll out software changes for software that auto-updates.
It's much preferable to be able to instantly fix it if the rollout of a new feature goes wrong than have everyone who installed the broken version bring stuck with problems until the company realizes the issue and rolls forwards with a fixed version.
I've used feature flags extensively throughout my career as a SaaS developer, but I've never considered their usage in desktop software. Not sure how I feel about it.
post-it 49 minutes ago [-]
Not necessarily. They probably have an integrated service that handles some telemetry and also feature flags, like Braze. They toggled the whole thing off based on telemetry settings. It's a bug I've made before too.
OtherShrezzing 3 hours ago [-]
>Apologies again folks, this was a fully human error on my part
Blink twice if you need help
3 hours ago [-]
anon48293 2 hours ago [-]
Or add one additional telemetry metric and an extra prompt
piltdownman 3 hours ago [-]
Much respect for the prompt response, humility, and frank disclosure.
aviperl 3 hours ago [-]
Ouch.
I've had to send such messages, but internally at work, not on HN!
Have a great day, human.
michaellee8 3 hours ago [-]
Really loved this Tibo-level responsiveness, if Anthropic can keep it up with this level of service, I am pretty sure a lot of people will just ditch their ChatGPT subscription and just move to Claude.
jimmaswell 2 hours ago [-]
Why would I ever do that to myself? My experience with Codex/GPT is fantastic, while my impression of Claude/Opus is that it's longwinded, patronizing, token-inefficient, stops to ask stupid questions every other minute, overcomplicates simple tasks, often poor engineering overall. I don't use it but this is what I see my partner run into who has access to both and compares them often. She has the same assessment.
michaellee8 1 hours ago [-]
Cuz OpenAI has been secretly downgrading models on many accounts, including mine lately. I paid $200 a month since like gpt-5.4, and since Astra released I found the model is somehow acting strange, it is until I checked X I have discovered that OAI is giving Luna level models when I am requesting Sol/Astra, or some piece of s** that is even worse than Luna. I basically had to ran every session with a Pelican test to determine if that session is safe. So I just spun up my Claude $20 and figured that now I can get all the work done just with Opus 5. Let me show you a pelican, by "gpt-6-sol". Cutting usages is one thing, but secretly downgrading models to a level that is not reliable anymore is the last straw. I am not saying other frontier labs (I am talking about you Anthropic) isn't doing this, but their version of downgraded/quantized/reduced effort model is at least usable, probably just slightly dumber, OAI's differences is day and night. https://imgur.com/a/PDbYdOQ
jimmaswell 48 minutes ago [-]
Somehow this just hasn't happened to me. I use Astra on high all day for fairly intensive game dev tasks, sometimes cranked up depending on the task.
I have heard ultra thinking might delegate to worse agents for some of its sub-tasks, but I don't use that much anymore since Astra came out. Just high seems good enough to throw most laundry lists at.
nullbio 36 minutes ago [-]
It's night and day difference, for 3 days, until Anthropic nerf the model.
enraged_camel 1 hours ago [-]
Wow, thanks for sharing your experience. Very insightful.
d5lt5 3 hours ago [-]
On the other hand, if Anthropic is to follow the industry standards, this would never have happened in the first place. It's not like the feature gates are the frontier of software development.
vikramkr 2 hours ago [-]
There are two or three relevant companies in this space in America and this is the one of them that kicked off the whole terminal agent harness thing in getting market adoption. It's perfectly fine for neither of these companies to follow industry standards while they're figuring shit out
bpodgursky 2 hours ago [-]
This is the most symbolic and unimportant change in history (you can literally just symlink), I think people will be fine.
d5lt5 2 hours ago [-]
Symlink requires admin, and most people do not run CC as admin with bypass permissions though.
arcfour 2 hours ago [-]
? You need root to run ln? Since when?
farlight 2 hours ago [-]
On Windows you do. If you have to suffer it for some reason.
arcfour 2 hours ago [-]
Ah, right. Windows...
Does that apply to WSL? I would assume everyone develops on WSL these days if they have to use Windows, at least...
d5lt5 2 hours ago [-]
There is a very valid reason on Windows not to allow people to do 'ln -s' without an admin.
WSL also has a huge perf hit when you cross FS boundary, but perhaps you have never experienced it, because you said, "Ah, right. Windows..."
But at least you've heard about WSL!
arcfour 1 hours ago [-]
Yes, I prefer to use functional operating systems, or at least ones I can fix myself, without incurring a "huge performance hit" by wrapping them in spyware disguised as an OS ;-)
bpodgursky 2 hours ago [-]
Right... you can just do it yourself.
cowboylowrez 2 hours ago [-]
What we need is a low level but constant drumbeat against openai in general. In general the AI situation is overleveraged and underpoliced, with the occasional hints of AI gone wild. If openai were to just be left to die, we could let that financial mess unroll and bail out the leftovers, I don't like bailouts anymore than the next guy but with this administration its almost a guarantee if things go south because this adminstration can charge administrative fees of maybe $20-30 billion (which goes to trump), get Sam Altman to serve one or two years in a cushy resort type fed place for the hugging face hacking and put openai's processes on github as a premium feature, say $10000 a month to access (which again goes to trump).
I know I know, why are we giving money to trump? Its because he's going to take it anyways so can't we at least apply some window dressing?
serf 1 hours ago [-]
> ...if Anthropic can keep it up with this level of service...
fuckin laughable, literally invoked a laugh from me in real life.
I hope customers aren't so stupid that they think a chatty developer on twitter/hn/mastodon/screaming-in-the-wind/wherever (or any other public-facing-place) means shit about customer service, and that goes towards ANY company where the primary customer service is an LLM.
Anthropic is the only company where it took (!) 9 weeks (!) to convince to hand over a 4 dollar refund for book-keeping errors on their side that caused an inappropriately early account deactivation due to time zone issues on their end, while all the while telling me that they don't offer refunds. It took stacks of evidence and argument, and that was after spending two weeks in their system trying to convince every level that I was worth a human.
For me personally it'd require Dario to resort to armed mugging to see another buck out of my wallet. I'm not alone.
tl;dr : being able to convince the powers that be on highly active industry forums (hacker news, twitter, mastodon..?) to act right using the power of peer shaming doesn't good customer service make. That said -- I do appreciate the direct response/statement from mpoteat;
..I just don't appreciate the good actions of a decent individual being too broadly interpreted as the do-good customer-centric nature of Anthropic .. an element I do not believe exists there.
BowBun 3 hours ago [-]
Because they respond to HN threads about their products? Which are likely Claude hooks monitoring for activity in the first place? Come on...
At least make an argument for switching vendors based on the quality or price of their service.
user43928 2 hours ago [-]
After I was mildly disappointed with GPT-6 Sol and Luna not improving intelligence and only cutting the price, I'm running Opus 5.5 today.
After the last month or so in the Codex app, I was pleased with the Claude app.
It might be a case of the grass always being greener on the other side, but this is what stands out:
After 3-4 hours of usage, the weekly usage limit moved by only 1%.
Compared to Astra where I can watch the limit draining live, this is a great improvement.
I'd estimate it 3x cheaper, and that's with a 450k context limit instead of the 258k in Codex.
So far Opus 5.5 appears less prone to stopping for no apparent reason at checkpoints in the middle of a longer task.
It doesn't open an internal browser with a useless comparison page, where it then proceeds to add notes despite no one having asked for it.
It is a breath of fresh air: I get the response in the chat, while the Codex app recently loves randomly opening artifacts instead.
Opus 5.5 xhigh made great progress on the task, more so than Astra High, but that could be random chance.
Oh, and the 'Auto' mode actually works and does not force me to instead run 'Full access' like in the Codex app, lest it blocks even 'git push'.
m3kw9 2 hours ago [-]
Sure a fast response on HN would make people switch. Try better rates, infra, limits etc.
irregularbowels 3 hours ago [-]
[dead]
baq 24 minutes ago [-]
It was obvious this was the reason, it’s a very easy thing to forget about
saadn92 1 hours ago [-]
Thanks for admitting to the mistake, but my understanding was that coding was fully solved now?
yangcheng 34 minutes ago [-]
is there reason I can't update claude to 2.1.281? I just run claude update
> claude update
Current version: 2.1.280
Checking for updates to latest version...
Claude Code is up to date (2.1.280)
grim_io 3 hours ago [-]
The same guy writing readme's for my vibeslopped toy projects is also the readme writer at Anthropic, what a coincidence ;)
fg137 3 hours ago [-]
> a fully human error
Would be interesting to know how much time you/your team spent on that design decision
rachr 3 hours ago [-]
The correct design was in the AGENTS.md but they didn't have telemetry on
davidmurdoch 2 hours ago [-]
How are you planning to turn this off remotely when telemetry off?
lukewarm707 1 hours ago [-]
is it common to deploy software with a remote kill switch installed?
harry19023 52 minutes ago [-]
yes? feature flags have been a thing for a long time.
lukewarm707 38 minutes ago [-]
how strange.
as i said in another comment. i don't want someone to toy with my software remotely. that seems wrong to me!
i do not like others to decide that they know what is best for me. and then force it on me without my consent.
i will decide if i like your changes. if i do like your fix, i will install it.
in my car, do not remotely turn off my air conditioning. don't turn off my AGENTS.md.
senko 3 hours ago [-]
I hope disabling /r if telemetry is disabled is also unintentional...
owebmaster 40 minutes ago [-]
telling people Anthropic remote-control their users computers isn't the smartest thing to do
Maxion 3 hours ago [-]
Well now, this is how you do community outreach
h1fra 2 hours ago [-]
people are overeacting
2 hours ago [-]
mococa 1 hours ago [-]
"Claude, deploy yourself to a bunch of idiots, f** the bugs"
samyar 1 hours ago [-]
valid
ndbe 3 hours ago [-]
I don't understand, isn't coding solved already?
mort96 3 hours ago [-]
"Rollout artifact"? This is Claude-speak isn't it? I have never ever heard anyone call a bug like this a "rollout artifact" before.
ako 3 hours ago [-]
I was probably an agent that made the change, and the same agent that commented here on HN.
criley2 2 hours ago [-]
I don't think "bug" is the correct term. They put a feature behind a feature flag, and feature flags don't work if you turn them off (via telemetry). That's "Working As Designed™".
mort96 2 hours ago [-]
It's clearly an unintended interaction. Nobody intended for the telemetry switch to control whether it reads AGENTS.md (hence mpoteat's apologetic response). Whether you consider that to be a "bug" or not really wasn't the point of my message.
_vertigo 1 hours ago [-]
Clearly not Claude-speak, see the rest of the message. "Rollout artifact" just means "an artifact of how we rolled this change out" which maybe isn't proper English but the message was obviously not written by Claude. Upgrade your Claudish detection
chrisjj 19 minutes ago [-]
> That's "Working As Designed™".
You must be baffled by the fact they're fixing it.
bbor 1 hours ago [-]
Feels pretty normal to me, IDK. "Rollout" is definitely what was happening here, and this leftover problem can be described as an "artifact" most generally - I guess otherwise it'd be a... just "problem" or "mistake"? Cause "bug" doesn't really fit. Plus, the Claudism here would definitely involve "soak", and possibly even "wall-time" lol
IMHO it's worth keeping in mind that Anthropic employees are some of the least likely to casually pass off artificial prose as authentic, given the company's ethos/brand/cover story (depending on how cynical you are). To them this is all getting pretty high stakes pretty damn quickly; based on my usage of full strength Opus 5.5 today, I can't even imagine what working with their full internal stack must feel like. If they were willing to let the machines speak for them, they'd all be melancholically lounging around home by now instead of coming in to work!
...I am refusing to consider the fact that they probably are still WFH because of Salesforce forcing their shared security contractor to strike. Call that a mental health ignorance on my part :)
sandrello 3 hours ago [-]
Based on my experience with these tools so far, this seems exactly the kind of subtle but extremely severe bug that sneaks in when you start piling up layers of AI generated patches to a codebase without caring too much about the code.
HotHotLava 3 hours ago [-]
"extremely severe" - aren't we laying it on a bit thick here? The whole impact seems to be that users who have telemetry turned off got this feature ~2 days later, when the bug was noticed.
code_runner 2 hours ago [-]
a "feature" that every user has asked for - which is the equivalent of changing claude.md to agents.md - and the release isn't even smooth because the telemetry isn't wired up quite right.
for an organization that is being used as a model for new agentic software development practices.... and every software exec on earth is trying to reshape their organizations after - its a pretty stupid bug for a feature that should've been straightforward in the first place + took forever for them to get around to.
its just kind of emblamatic of the rough edges that exist EVEN FOR SIMPLE THINGS whenever human judgement is totally removed the equation.
t-writescode 50 minutes ago [-]
Or it’s as simple as “hey, they don’t want telemetry? Cool, we’ll turn off all the extra phoning home” and their feature flag code uses the same paths as telemetry because it’s the same endpoint, etc.
Oops, easy mistake!
code_runner 2 hours ago [-]
ps: apparently thats not how you spell emblematic - but I'm actually glad to leave a little humanity around given the topic :D
archonis 44 minutes ago [-]
Good thing they don't apply the same standards to security sandboxes.
hgoel 3 hours ago [-]
Yep, especially with long contexts (and moreso if the last thing you were working on in the same context involved telemetry too). AI sneaks in weird conditions like this and then does the entire "You're absolutely right" thing if you're paying enough attention to catch it.
crazygringo 3 hours ago [-]
It seems to be exactly the opposite, a "fully human error":
Nothing to do with AI patches at all, nor was it a bug. It was intentional human behavior, a temporary rollout setting, that seems to have made sense.
But I guess that doesn't fit the "narrative".
fg137 2 hours ago [-]
One thing I do know is that an Anthropic employee is definitely NOT going to blame this on the model they are using.
q3k 3 hours ago [-]
> It seems to be exactly the opposite, a "fully human error"
"LLMize the succeses, humanize the failures." is the PR strategy at play here. Anything goes well it's because AI did it, anything goes bad it's because a human didn't catch it.
crazygringo 2 hours ago [-]
Wow people are cynical here.
No matter what happens to be the truth, HNers have a cynical narrative to fit it.
abathologist 2 hours ago [-]
People are just paying attention to what is happening the world.
crazygringo 1 hours ago [-]
No, people seem to be adopting simplistic narratives and then slotting the facts wherever they most conveniently fit into their narrative.
ndbe 3 hours ago [-]
[dead]
Agentlien 3 hours ago [-]
I used to actively use Msty for local models because it just worked and had a lot of nice advanced features. A few months ago they released their beta version of a Claw-like UI and mentioned using a version of it to develop Msty itself. Well, that was around the time I stopped using Msty because every update started breaking things and two updates in a row included bugs which wiped all my configs, chats, and history.
tpurves 3 hours ago [-]
Except that, and this I find slightly amusing, is a situation where they definitely don't want to publicly blame the ai model when there are mistakes.
lucfranken 3 hours ago [-]
Isn't that how they just release all features? So they can do progressive roll outs and telemetry on issues with it?
Not sure if they later move the code from inside the flag check to the main code or that they keep the flag check.
But if they would keep all features behind a flag that would not make most sense as you then would have not many features without telemetry.
fg137 3 hours ago [-]
This is what's written in their release notes for 2.1.277:
> Added AGENTS.md support: in a project with no CLAUDE.md, Claude Code reads AGENTS.md instead
My dumb brain tells me none of this is rolled out progressively (as of that version). You either have it or not.
nijave 3 hours ago [-]
It's been like this at least months. I turned telemetry off a few months ago and it basically prevented all stages rollouts of new features from working.
Anthropic commonly gates behind feature flags that require telemetry until they're "promoted" and defaulted on.
A little bit annoying you can't manually control the flags without telemetry but I think the title is a bit click bait.
arrowsmith 3 hours ago [-]
Claude Code also doesn't read AGENTS.md by default if there's a CLAUDE.md it can read instead. This isn't limited to your repo, e.g. if you have a ~/CLAUDE.md then no AGENTS.md will be read.
To always read both, you have to switch the 'Project instructions' setting to the non-default `claude-md-and-agents-md`.
Just in case anyone is wondering why their AGENTS.md still isn't being read.
fg137 2 hours ago [-]
This in some way sounds like VSCode's bug of always adding Copilot as a co-author of git commit regardless of user settings.
If people only glance over the code agents generate for them and don't bother to spend even half a minute thinking through what's actually happening, this is inevitable.
Certainly this kind of things happened before LLMs existed. But I'm not optimistic about the direction of how things are going.
MPSimmons 1 hours ago [-]
Couldn't you just make a CLAUDE.md that says, "Read AGENTS.md in this same directory"?
shermantanktop 1 hours ago [-]
I don’t understand why people are confused about the use of a launch flag, for this and for anything.
It’s a simple distributed systems problem. Separate the deployment of a new software feature (to umpteen hosts) from the triggering of that software with a lightweight switch.
If someone think that reading AGENTS.md is always benign, because they can’t imagine how it could be a problem…users are very creative.
petters 59 minutes ago [-]
Exactly! I can not believe this is in the top spot.
throwuxiytayq 1 hours ago [-]
Meanwhile, Codex devs just merge their changes and hit the release button. If a thingy breaks, they fix the thingy and release a hotfix. How irresponsible! It’s a miracle the software works at all!
59 minutes ago [-]
nfRfqX5n 4 hours ago [-]
Crazy part is: can’t tell if this intended or a bug
serial_dev 3 hours ago [-]
Someone on the Claude Code team is probably wondering the same...
kennethops 3 hours ago [-]
I like to give my graces to people and the companies who are typically not trillions of dollars. Have an incredible amount of resources that many countries would like to have, with fewer of the obligations. I'm going to chalk this up to its intended
vaylian 3 hours ago [-]
Can you think of a bug that makes sense in this case?
hgoel 3 hours ago [-]
Vibe coding
thejazzman 3 hours ago [-]
It is most certainly the kind of subtle bug the LLMs love to slip in and burn you in production
Not sure what y’all are thinking with these unwritten conspiracy theories that begin and end with “it’s intentional”
jpitz 3 hours ago [-]
Assuming that it's intentional, what's the motivation?
And I’m sure there’s no conceivable way an organization as well resourced as Anthropic can separate out feature flags from telemetry. It’s just too complicated! Maybe when we get AGI?
vorticalbox 3 hours ago [-]
I use cursor and claude, its kinda annoying having to have the same skills in both so I made a ~/.agents/skills folder then ln both cursor and claude skills to point to that folder.
which works except that claude uses .skills/synced which is uses to sync changes to skills from claude servers into the skills folder.
every other agent I have used just directly syncs into .skills so it ends up duplicating skills
jdlyga 2 hours ago [-]
You're absolutely right! AGENTS.md shouldn't be gated behind telemetry on
tjoff 3 hours ago [-]
Nice find, though I'd rather read the prompt that was used to write this article. It is about ten times longer than it needs to and is quite painful to read.
sschueller 1 hours ago [-]
If they can't even get this simple thing right, I am worried about the future of anthropic's products.
msp26 3 hours ago [-]
Claude Code Remote control only works with telemetry enabled too.
pszypowicz 2 hours ago [-]
Yeah, no thank you. This was why I polished my setup for VPN -> SSH -> [MOSH] -> TMUX -> claude/codex
cowpig 3 hours ago [-]
The number of people raw-dogging software that executes arbitrary instructions on their machine coming from a 3rd party server just absolutely baffles me.
The same people who've spent years of their career making sure that never happens.
0m13 3 hours ago [-]
can i ask claude to change these settings for me, and will it enable telemetry as implied checkpoint when i ask it to enable AGENTS.md?
rvz 3 hours ago [-]
I am once again (for the third time) [0] asking you to stop using a closed-source harness.
Edit: The linked repository does not contain source code for Claude Code, the harness, itself. It only contains the source code for (some) scripts, mods and plugins.
SyneRyder 2 hours ago [-]
Forgive me if I'm missing something really obvious, we'll blame it on lack of sleep... but is that actually the full source to Claude Code? I'm looking at the repository and I only see source for plugins, mods and scripts. When I get to the readme, it says:
"This repository includes several Claude Code plugins that extend functionality with custom commands and agents. See the plugins directory for detailed documentation on available plugins."
But I'm not a TypeScript guy, so I concede I might be missing something incredibly obvious. I remember there was a leak of the Claude Code source code at one point, and people vibe coding conversions to other languages from the leak, but I don't think the Claude Code harness itself is open source or even source available.
pbasista 1 hours ago [-]
I think you are not missing anything. I have not checked the code itself originally, I am sorry for that. But you are right that there seem to be no actual code for the harness itself. Just the code for (some) mods, plugins and scripts.
I just read the first line in the README file which says:
> Claude Code is an agentic coding tool ...
and I immediately assumed that this is what this repository hosts.
It claims that it includes plugins but that does not mean it does not include anything else. It also never explicitly claims, as far as I can tell, that it does not hold the source code of Claude Code, the harness, itself.
It is all extremely misleading, in my opinion. Which might be on purpose, unfortunately.
wccrawford 3 hours ago [-]
It's not open source. It's more "source available", since it's published, but you legally can't do anything with it. Other than maybe build it yourself, for yourself, I guess.
1 hours ago [-]
sunaookami 2 hours ago [-]
That's not the source code. Claude Code is proprietary.
Traubenfuchs 3 hours ago [-]
Issue 95690, opened 3 days ago, 500k+ engineers, a simple CLI...
AGI was reached like 2 weeks ago, latest claude 5.x models rule supreme and software engineering is solved?
geophph 2 hours ago [-]
Turns out AGI boils down to two markdown files:
claude-md-or-agents-md
claude-md-and-agents-md
ChrisArchitect 2 hours ago [-]
Related:
Claude Code now reads AGENTS.md if there is no Claude.md
Uhm I turned off everything there is to turn off in my Pro plan, and Claude just read my agents.md with no issue? So... What telemetry am I missing? Or did they JUST update? (I updated my docker image 40 minutes ago to get Opus 5.5, am on version 2.1.280, so not the mentioned 2.1.277, so it's fixed?)
BiteCode_dev 2 hours ago [-]
Anyway, my claude.md contains only this:
@agents.md
3 hours ago [-]
mrguyorama 1 hours ago [-]
Wait wait wait WAIT
So, these tools have a file they want to read in with some configuration.
That filename is hardcoded?
Fucking DOOM had a command line parameter to provide an arbitrary configuration file name!
That's completely irrespective of the fact that you need a feature flag set by remote infrastructure to change a setting of which completely local file to read.
It's weird, I feel like Claude would have tried to make this a configurable setting by default! Is that just not an option in JS land? Not a common pattern to have configuration in the first place? I don't know about that, all the JS based code editors have comprehensive configuration files.
What the hell is going on....
pmlnr 3 hours ago [-]
Urm... no tests caught this? How?
chrisjj 4 hours ago [-]
Vibe-coding at its best.
lightchaser08 3 hours ago [-]
[dead]
Ajjayaade 3 hours ago [-]
[flagged]
Ajjayaade 3 hours ago [-]
[flagged]
gmponyo 3 hours ago [-]
This is not the only case where Anthropic has done stuff silently without giving users any information about changes that would hurt them.
mgaldys4 3 hours ago [-]
Even if this was an honest rollout mistake, the design is indefensible. Reading a local file should never depend on a remote feature flag, and silently skipping it with no warning is worse. I've tried to give Claude Code the benefit of the doubt, but this crosses a line.
tehlike 3 hours ago [-]
Not everything is malicious. The author of the feature already responded on why this happened
lukewarm707 55 minutes ago [-]
it is indefensible.
chrisweekly 2 hours ago [-]
I'm not the person you replied to, but your response misses their point: rollout issue aside, the approach is flawed by design. The feature author didn't address that at all.
tehlike 2 hours ago [-]
The person had something else before they edited. They were overly negative, saying (from my memory) that it was inexcusable, and they had enough, pointing to malice.
The response as it is now sounds fair. Before that it was not.
46 minutes ago [-]
Rendered at 16:12:12 GMT+0000 (Coordinated Universal Time) with Vercel.
The mod is source available here: https://github.com/anthropics/claude-code/tree/main/mods/age...
Apologies again folks, this was a fully human error on my part - I should've found a better way to launch with a kill-switch.
If folks play around with it, I would love feedback on the relevant issue: https://github.com/anthropics/claude-code/issues/91870
Mods allow quite a bit more customizability and control. I really believe in the idea.
https://github.com/user-attachments/files/31802150/EXTERNAL....
Might I gently suggest that you have a model at least as capable as Opus 5.5 translate that from Claudish to English? Or, even better, have an actual human work on the docs a bit? As it stands, they are fairly egregious, and they seem to devote at least as much space to little AI-generated quips that convey no meaning than to actually explaining what’s going on.
Also, maybe a human should decide whether these are “function” hooks or “module” hooks. All of this marketing calls them “function” hooks, but the json config seems entirely unaware of this.
(Has anyone else noticed that half the sentences in Claudish aren’t merely weird: they are noun phrases and not sentences at all? I’m pretty sure that any decent pre-LLM NLP-based grammar checker would correctly flag half the sentences in Claudish. Also, whatever variant of Claude wrote this thing can’t even capitalize around semicolons consistently with itself, let alone consistently with how English has been written for at least a century.)
edit: Fixed the link. Thanks, kaszanka.
Rest assured I'll inject a bit less soul into the official docs once Mods are launched; re your feedback on the JSON key, what would you recommend?
Maybe "function_hook_modules" for the JSON key?
Does this finally fix the limitation that there is no supportable way to replace the implementation of a native tool in Claude Code? codex-rs has an (undocumented but likely supportable if kind of awkward) mechanism, and I’m part way through a project that needs this. I was going to release it with a recommendation not to use Claude Code, but it’s at least plausible that this will change my mind. (I’m not sure yet — the $ mechanism might be too restrictive. It’s a start at least.)
Probably just a case of a company hoping their scale can change the societal standard faster than they can be bothered to match the standard.
You'll talk like 2023 unsupervised TikTok generators and you'll be happy.
Sorry couldn't resist
Not sure what you didn't understood in their comment though, maybe the raph loop (and jev which was just released)? Isn't the rest completely self explanatory?
Basically he's describing an LLM assistant setup that does coding on a vps or Mac mini ( some contradiction with Openrouter though) where you can communicate with the assistant through telegram
As for the only difference being the file name, that's an untested assumption. Up until now, Claude hadn't supported AGENTS.md, and it's a simple application of Hyrum's Law that somebody, somewhere, was taking advantage of that to give one set of instructions to Claude, and a different set of instructions to some other provider. The correct behaviour in the presence of both files is not obvious, either.
Having a kill switch for the change is a perfectly reasonable safety measure in case something goes horribly wrong.
I'm this person, I am actively doing this! I have some instructions which the Claude models need and OpenAI models will do by themselves. If the OpenAI models see the Claude instructions, they will go way overboard in a way I don't want.
Mind, the change does not affect me at all, because when both instructions are present Claude continues to read CLAUDE.md and Codex continues to read AGENTS.md. But if Claude started preferring AGENTS.md, that would be mildly annoying.
I wrote an agent launcher sort of bash script. Pass in the command to start the agent, the script checks if there’s a Jinja file in a special directory matching that name, and builds it to AGENTS.md. Then it launches the agent.
I was trying to use it as a sort of janky RAG. I had a bunch of snippets (one for DB architecture, one for how load balancing works, etc), and my Jinja files were mostly a list of snippets to pull in. Voila, a bunch of agents that share little pieces of info but have a single source of truth.
I never got a ton of value tbh, it was very good at just grepping the snippets.
Seriously, though, this is a great idea. Good communicators know to tailor their discourse to their audience. LLMs are just as sensitive to small variations in prompts, and just as inconsistent between them, as are humans.
Read CLAUDE.md if it doesn't exist read AGENTS.md you don't need to overthink it so much.
And I say this as someone that loves the Unix philosophy dearly.
This is, to me, a completely reasonable and believable use case that could break if you implement this fix without "overengineering" it.
A setting to disable what? Be specific. See? Not so simple...
Bonus forth point: why is this critical to solve for claude code, but not for all the other harnesses which have all converged on AGENTS.md for this purpose?
you're really over thinking this, and i'm wondering if you're risking pulling something stretching like that to pick this up shilling for Anthropic.
> Some people might have a different CLAUDE.md and AGENTS.md
How exactly do these two conflict? If you have both, nothing changes.
We're talking about changing default behaviors here in ways that can be surprising to users. It's reasonable to try and accommodate existing setups, future setups, and - yes - careless users.
Even though Anthropic or any other software provider could technically run anything on our system, there exists a modicum of trust between supplier and user. Anthropic performing arbitrary changes that are tangential but not specific to the premise of delivering a harness to package code files and prompts in context to their LLM breaks that trust for many users.
What, exactly, is going to go horribly wrong here ...? The worst case you're proposing is that an Anthropic model acts on AGENTS.md rather than CLAUDE.md. It's not going to be the end of the world; at worst it'll be `git reset --hard HEAD` time. But this wouldn't happen, because:
> The correct behaviour in the presence of both files is not obvious, either.
It seems extremely obvious to me: the non-breaking change is the right change here. If both exist, Anthropic models continue to use CLAUDE.md and ignore AGENTS.md. This is not rocket science. Why are we overthinking this?
Operating anything at scale teaches you that the universe of “things that can go horribly wrong” has a much better imagination than you. That goes quadruple with complex and squishy reasoning models.
I’ve seen a couple of really good examples of what can go wrong in this subthread, the most straightforward of which is that abruptly changing a fundamental behavior can break existing use cases.
```md @AGENTS.md
[Claude specific stuff]
```
And then what happens if someone now puts @syntax in their agents.md triggering a loop etc. It's all vibe coded - including code from days with dumber models - there's gonna be all sorts of dragons under the hood
So in the CLAUDE.MD we tell it about that and then tell it continue reading AGENTS.MD. Not very hard to work around if CLAUDE.MD goes away, but just to support your point that the split did have its uses for some.
That said, I do find it somewhat funny that Anthropic themselves are falling victim to their own model's tokenmaxxing.
There are processes to make changes outside of feature flags, but they have enough friction that it's easier to just use a feature flag.
This level of paranoia is consistent with the blast radius of changes breaking Claude users.
Thanks!
Vibe-coding gotta vibe-code.
I don't think this is a reasonable assumption. The document format in CLAUDE.md is whatever Anthropic specifies, where AGENTS.md is a common ground format that is expected to be supported by any agent, be it from Anthropic or not.
https://agents.md/
You might argue that differences are small or negligible, but that is just an expectation.
There is no rhyme or reason to the structure of this file, just like with most things in AI. It's best effort human language.
Q: Do Anthropic actually specify a document format?
The deciding factor for me whether or not I will work on the feature of the plugin is whether I (or rather, my agent) can look in upstream source and evaluate if it can be done with minimal upstream change, which I then contribute. And generally, even if no upstream change is needed, agents work so much better when they can read the code.
So why not just make Claude code open source? Considering also that source code was leaked once anyway.
An extensibility system called mods, which is a plugin with a new type of hook that we call function hook?
I can't tell if this is real, or you are making fun of overengineered AI solutions.
Is this real?
It's much preferable to be able to instantly fix it if the rollout of a new feature goes wrong than have everyone who installed the broken version bring stuck with problems until the company realizes the issue and rolls forwards with a fixed version.
https://martinfowler.com/articles/feature-toggles.html
Blink twice if you need help
I've had to send such messages, but internally at work, not on HN!
Have a great day, human.
I have heard ultra thinking might delegate to worse agents for some of its sub-tasks, but I don't use that much anymore since Astra came out. Just high seems good enough to throw most laundry lists at.
Does that apply to WSL? I would assume everyone develops on WSL these days if they have to use Windows, at least...
WSL also has a huge perf hit when you cross FS boundary, but perhaps you have never experienced it, because you said, "Ah, right. Windows..."
But at least you've heard about WSL!
I know I know, why are we giving money to trump? Its because he's going to take it anyways so can't we at least apply some window dressing?
fuckin laughable, literally invoked a laugh from me in real life.
I hope customers aren't so stupid that they think a chatty developer on twitter/hn/mastodon/screaming-in-the-wind/wherever (or any other public-facing-place) means shit about customer service, and that goes towards ANY company where the primary customer service is an LLM.
Anthropic is the only company where it took (!) 9 weeks (!) to convince to hand over a 4 dollar refund for book-keeping errors on their side that caused an inappropriately early account deactivation due to time zone issues on their end, while all the while telling me that they don't offer refunds. It took stacks of evidence and argument, and that was after spending two weeks in their system trying to convince every level that I was worth a human.
For me personally it'd require Dario to resort to armed mugging to see another buck out of my wallet. I'm not alone.
tl;dr : being able to convince the powers that be on highly active industry forums (hacker news, twitter, mastodon..?) to act right using the power of peer shaming doesn't good customer service make. That said -- I do appreciate the direct response/statement from mpoteat;
..I just don't appreciate the good actions of a decent individual being too broadly interpreted as the do-good customer-centric nature of Anthropic .. an element I do not believe exists there.
At least make an argument for switching vendors based on the quality or price of their service.
After the last month or so in the Codex app, I was pleased with the Claude app.
It might be a case of the grass always being greener on the other side, but this is what stands out:
After 3-4 hours of usage, the weekly usage limit moved by only 1%.
Compared to Astra where I can watch the limit draining live, this is a great improvement.
I'd estimate it 3x cheaper, and that's with a 450k context limit instead of the 258k in Codex.
So far Opus 5.5 appears less prone to stopping for no apparent reason at checkpoints in the middle of a longer task.
It doesn't open an internal browser with a useless comparison page, where it then proceeds to add notes despite no one having asked for it.
It is a breath of fresh air: I get the response in the chat, while the Codex app recently loves randomly opening artifacts instead.
Opus 5.5 xhigh made great progress on the task, more so than Astra High, but that could be random chance.
Oh, and the 'Auto' mode actually works and does not force me to instead run 'Full access' like in the Codex app, lest it blocks even 'git push'.
> claude update Current version: 2.1.280 Checking for updates to latest version... Claude Code is up to date (2.1.280)
Would be interesting to know how much time you/your team spent on that design decision
as i said in another comment. i don't want someone to toy with my software remotely. that seems wrong to me!
i do not like others to decide that they know what is best for me. and then force it on me without my consent.
i will decide if i like your changes. if i do like your fix, i will install it.
in my car, do not remotely turn off my air conditioning. don't turn off my AGENTS.md.
You must be baffled by the fact they're fixing it.
IMHO it's worth keeping in mind that Anthropic employees are some of the least likely to casually pass off artificial prose as authentic, given the company's ethos/brand/cover story (depending on how cynical you are). To them this is all getting pretty high stakes pretty damn quickly; based on my usage of full strength Opus 5.5 today, I can't even imagine what working with their full internal stack must feel like. If they were willing to let the machines speak for them, they'd all be melancholically lounging around home by now instead of coming in to work!
...I am refusing to consider the fact that they probably are still WFH because of Salesforce forcing their shared security contractor to strike. Call that a mental health ignorance on my part :)
for an organization that is being used as a model for new agentic software development practices.... and every software exec on earth is trying to reshape their organizations after - its a pretty stupid bug for a feature that should've been straightforward in the first place + took forever for them to get around to.
its just kind of emblamatic of the rough edges that exist EVEN FOR SIMPLE THINGS whenever human judgement is totally removed the equation.
Oops, easy mistake!
https://news.ycombinator.com/item?id=49815363
Nothing to do with AI patches at all, nor was it a bug. It was intentional human behavior, a temporary rollout setting, that seems to have made sense.
But I guess that doesn't fit the "narrative".
"LLMize the succeses, humanize the failures." is the PR strategy at play here. Anything goes well it's because AI did it, anything goes bad it's because a human didn't catch it.
No matter what happens to be the truth, HNers have a cynical narrative to fit it.
Not sure if they later move the code from inside the flag check to the main code or that they keep the flag check.
But if they would keep all features behind a flag that would not make most sense as you then would have not many features without telemetry.
> Added AGENTS.md support: in a project with no CLAUDE.md, Claude Code reads AGENTS.md instead
My dumb brain tells me none of this is rolled out progressively (as of that version). You either have it or not.
Anthropic commonly gates behind feature flags that require telemetry until they're "promoted" and defaulted on.
A little bit annoying you can't manually control the flags without telemetry but I think the title is a bit click bait.
To always read both, you have to switch the 'Project instructions' setting to the non-default `claude-md-and-agents-md`.
Just in case anyone is wondering why their AGENTS.md still isn't being read.
If people only glance over the code agents generate for them and don't bother to spend even half a minute thinking through what's actually happening, this is inevitable.
Certainly this kind of things happened before LLMs existed. But I'm not optimistic about the direction of how things are going.
It’s a simple distributed systems problem. Separate the deployment of a new software feature (to umpteen hosts) from the triggering of that software with a lightweight switch.
If someone think that reading AGENTS.md is always benign, because they can’t imagine how it could be a problem…users are very creative.
Not sure what y’all are thinking with these unwritten conspiracy theories that begin and end with “it’s intentional”
https://www.thatprivacyguy.com/blog/anthropic-spyware/
+ not letting users change their email, or remove their payment methods, etc.
https://martinfowler.com/articles/feature-toggles.html
which works except that claude uses .skills/synced which is uses to sync changes to skills from claude servers into the skills folder.
every other agent I have used just directly syncs into .skills so it ends up duplicating skills
The same people who've spent years of their career making sure that never happens.
[0] https://news.ycombinator.com/item?id=49760449
So I am unsure if it is fitting to call it a "closed source" harness.
[0] https://github.com/anthropics/claude-code
Edit: The linked repository does not contain source code for Claude Code, the harness, itself. It only contains the source code for (some) scripts, mods and plugins.
"This repository includes several Claude Code plugins that extend functionality with custom commands and agents. See the plugins directory for detailed documentation on available plugins."
But I'm not a TypeScript guy, so I concede I might be missing something incredibly obvious. I remember there was a leak of the Claude Code source code at one point, and people vibe coding conversions to other languages from the leak, but I don't think the Claude Code harness itself is open source or even source available.
I just read the first line in the README file which says:
> Claude Code is an agentic coding tool ...
and I immediately assumed that this is what this repository hosts.
It claims that it includes plugins but that does not mean it does not include anything else. It also never explicitly claims, as far as I can tell, that it does not hold the source code of Claude Code, the harness, itself.
It is all extremely misleading, in my opinion. Which might be on purpose, unfortunately.
AGI was reached like 2 weeks ago, latest claude 5.x models rule supreme and software engineering is solved?
claude-md-or-agents-md
claude-md-and-agents-md
Claude Code now reads AGENTS.md if there is no Claude.md
https://news.ycombinator.com/item?id=49760187
@agents.md
So, these tools have a file they want to read in with some configuration.
That filename is hardcoded?
Fucking DOOM had a command line parameter to provide an arbitrary configuration file name!
That's completely irrespective of the fact that you need a feature flag set by remote infrastructure to change a setting of which completely local file to read.
It's weird, I feel like Claude would have tried to make this a configurable setting by default! Is that just not an option in JS land? Not a common pattern to have configuration in the first place? I don't know about that, all the JS based code editors have comprehensive configuration files.
What the hell is going on....
The response as it is now sounds fair. Before that it was not.