I am a HUGE herdr fan - discovered it a few months ago and it's exactly what I need for my workflow. Thousands of others have discovered it as well, which is awesome.
I have such mixed feelings about this - YC means VC means commercialization means enshitification. I really wish that weren't the case, but it so very often is.
Here's hoping this one's different...
(PS I am a big YC fan in general! I don't mean to sound anti-YC or anti-VC or anti-capitalism. But when it comes to low-level essential development tools, I'll never forget what happened to Warp, which started out as such a nice clean terminal project and turned into an absolute money-chasing mess.)
I can't tell if this is sarcasm but in case its not, being capable of doing something and having the desire and resources to do it are not the same thing
Not sarcasm at all. I think you might overestimate the time and effort needed for this. When you maintain a _personal_ fork with no users except yourself, you only ever need to change something when you encounter a bug or need a new feature.
E.g. I have personal forks of mosh and cmux, each took maybe 1 hour of my time total?
I found this article https://news.ycombinator.com/item?id=49156111 resonating with me, except I obviously don't do stuff like "nightly cron to sync with main", I just never touch the code unless it breaks or I want a new feature.
I think I only added two features, pasting images over mosh (ssh already worked but not mosh) and a compact version of sidebar.
The story behind the fork is: I had a bug with raycast, filed a PR that fixed it for me https://github.com/manaflow-ai/cmux/pull/2435, a different fix made it into next release that for me didn't work. Maybe the problem was on my side, but at this point it was easier to fork the working version than debug further.
It’s literally the VC playbook, the whole point of the funding is to undermine competitors with subsidized/free products and then raise prices/enshittify. Anyone who thinks it’ll be different this time is fooling themselves.
> YC means VC means commercialization means enshitification
It doesn't have to be that way. YC partners are supportive if you just want to take the YC funding and nothing more, keeping the team small and just focusing on making the product better for customers. Indeed YC advises against taking VC if you don't need it.
I hate that you're right, but you're right. Twitter and HN can scream and yell as loud as they want but the fact is, enterprises are going to use Fable via API and pay the bills. In fact, restricting individuals probably makes it MORE likely that enterprises will pony up.
It's usable for coding and code auditing. The classifier will have some false-positives and some tasks will be downgraded to 4.8 if it's security-adjacent (I presume), but otherwise there's no restrictions on using this for coding.
Tom Brown
Chief Compute Officer
Anthropic
548 Market Street
San Francisco, CA 94104
Dear Mr. Brown:
Since the issuance of my previous letters, dated June 12, 2026 and June 26, 2026, Anthropic has taken steps in close coordination with the U.S. government to address
the risks associated with Claude Mythos 5 and Claude Fable 5. Among other things, Anthropic has agreed to proactively detect and address security risks associated with the models; to work diligently with the U.S. government on protocols and standards and releases for Mythos, Fable, and future models; and to inform the U.S. government of any malicious activity.
In light of these actions and commitments, as well as the Bureau of Industry and Security's evaluation of the diversion risks now presented by Claude Mythos 5 and Claude Fable 5, the controls in the June 12 letter are withdrawn. A license is no longer required for the export, reexport, or in-country transfer, including deemed export or deemed reexport, of the Mythos or Fable models.
Commerce reserves the right to reevaluate the decisions made in this letter and the necessity of reimposing a license requirement, should circumstances change or should Anthropic fail to adhere to its commitments.
If you have any questions about this letter, please contact me or the Under Secretary of Commerce for Industry and Security, Jeffrey Kessler, at (202) 255-1864.
> Among other things, Anthropic has agreed to proactively detect and address security risks associated with the models; to work diligently with the U.S. government on protocols and standards and releases for Mythos, Fable, and future models; and to inform the U.S. government of any malicious activity.
How likely is it the resolution was just a direct flow of data on what each Claude user is specifically using Claude for, probably sent off to some other (gov-owned) AI datacenter for analysis?
He's the one who led the choice to refuse working with the gov for surveillance or defense, and it led to that block right after.
I have no proof but I assume he believes at least some of what he's preaching (which doesn't mean he won't fold, at the end of the day it's an american company anyway).
Brown is probably more of a diplomat, "Sure, but not now" goes a lot further than "No, never", though it has the issue of kicking the can down the road.
> He's the one who led the choice to refuse working with the gov for surveillance or defense
This is false and just Anthropic being good at PR. He's happy to let it be used for airstrikes on Iran for example, just wants to keep a human in the loop. So the AI will say 'I am extremely sure this building (a girl school) is a military base' and the human will say 'I am being asked to carry out more airstrikes and who am I to question AI' and will bomb a school with Amodei then washing his hands.
You can find a source for it being used here [1] though parent is misrepresenting it either on purpose or by lacking understanding, I stand to my point above, the timeline is
1. the US used it, in venezuela then to prepare Iran
2. it became public through journals reporting it, but they didn't really hide from it afterwards and told explicitely what and who they used, naming anthropic
3. Diego (the CEO) answered by saying this violate terms and the US is not allowed and should stop that immediately, publicly
4. They have a talk, and while concessions are made it blocks not about war with ennemies but about surveillance at home, which Diego refuses to let go
5. Trump reacted by calling Anthropic a "Radical Left AI company run by people who have no idea what the real World is all about"
6. Peter Hegseth annonce they will stop using it but asked for a stop gap deal "Anthropic will continue to provide the Department of War its services for a period of no more than six months to allow for a seamless transition."
7. Open AI annonce a deal with the governement four and a half HOURS later, with totally cool safeguards "We think our agreement has more guardrails than any previous agreement for classified AI deployments, including Anthropic's", journals note that "OpenAI's new Pentagon deal doesn't explicitly prohibit collecting Americans' publicly available information - a sticking point that rival Anthropic says is crucial for ensuring domestic mass surveillance doesn't take place"
8. In totally unrelated news, Anthropic new models get banned for exports in a move the US has never done before, no other company has their models banned
And now
9. Anthropic change the person talking with the gov to Brown
10. After a bit anthropic models start being unbanned
Maybe he just lacks social skills, but I remember watching videos of him talking about mass job loss with what looked like glee on his face. All his actions and communications do not give me a sense that his "principles" are good or even what he claims them to be
Could you please stop posting unsubstantive comments and flamebait? You've unfortunately been doing it repeatedly, and we already asked you a couple days ago.
Your comment, genius. Makes me miss n-gate dotcom, which hasn't been updated since 2021. This comment would make a great entry. If you aren't familiar with it, you really want to be.
One of the contributing factors that led to this control in the first place was that the commerce department couldn't get Dario on a call immediately:
"Then White House started reaching out to Anthropic to speak with Dario Amodei, who was at a wellness retreat.... When Amodei was finally available past 1pm, he had three tense phone calls with a combo of ppl including Cairncross, Bessent, Lutnick, Kessler, Will Scharf, Richard Walters, and Walker Barrett."
Anthropic has disputed that Dario was at a wellness retreat but both sides seem agree that it seemed to be a problem (and it is very apparent that Dario's response made things worse).
It's shocking to me that Anthropic seems to be run with the same managerial chaos as depicted in early seasons of Entourage.
Dario may be a genius, but when it comes to running a big business — which involves dealing with governments and regulators — it's like he just fell off a turnip truck.
I'll take it one step further - we have a 2-year-old toddler and recently I realized that I was spending a full, solid, real 1-1.5 hours per day doing the same kitchen & play area clean-up. Every day. No matter how hard I tried, the daily chaos of my wife & I working from home, preparing meals, and our family spending time in this part of the house meant it just needed this work.
I hired a lovely person recently who comes to the house for exactly that hour a day every day and now does this task for us. It's the most "luxury" labor service I've ever hired, and it, easily and without question, the best use of $$ I have ever spent on a service. I have an extra hour to hang with the family now and our kitchen & play area are now fully reset and spotless every night when we go to bed and every morning when we wake up.
It's not streaming service cheap, and I'm thankful that my business can generate enough $ to allow me to pay for this service, but man is it freeing and wonderful.
The real cause is that you and your wife never learned how to keep house. I'm in the same boat. My house is cluttered. Not like hoarder bad but stuff just piles up. I've been a guest where the house is always neat and everything is put away. The hosts just never let anything get out of place. Everything they own has a place and it always goes back there immediately after its used. They maintain this organized well kept home almost effortlessly, because they were taught how to do it at a young age by parents who were the same way. Whereas for me, it would take me several dedicated hours a day to get everything picked up and put away.
Yes and no. They somehow tidy the house as they are moving through it anwyay. So it doesn't amount to substituting that time for something else they would be doing. Or at least that's how it appears to me.
I can see the charm in hiring a cleaning person you trust, but I personally wouldn't extend that to paying a faceless corporation to send a robot to do it.
I'd much rather pay a nice human significantly more money than have it done by a stinking robot.
I’ve read so many stories like this that I’ve actually gotten scared of making PRs open source projects.
There’s one in particular where a feature I really wanted didn’t exist, so I forked and had Codex 5.5 assist with building the feature on my local version. It works perfectly. My life has been improved in being able to have this feature now.
Normally I’d want to share it back with the community so others can benefit as well (presumably if I wanted this feature, others probably want it too.) But…I am not pretending this is perfect, great, or even good code. I spent about an hour total on it - it works, I haven’t had any issues with it, but it’s probably slop by any hard-core engineering account. And I neither want to get attacked for submitting slop nor do I have the time to properly engineer it to be hand-coded, so the net result is that it lives on my machine alone.
Is this the right outcome? I feel guilty that I’m getting a better version of this software and others aren’t. I want to help makes others lives easier too, but I don’t want to burden the project maintainers or get yelled at for submitting slop.
First, you don't have to feel guilty of anything, since forking open source projects to make changes tailored to your use case is as old as open source itself. It is, in fact, the primary benefit of open source.
Second, it is not a given that your change would be accepted regardless of who wrote it. Maybe the feature is too niche for its complexity, maybe it is better implemented with more generality or extensibility that does not make sense for your own use. In those cases, your change might have been rejected upstream, so having it only locally is a perfect fine solution.
Third, if you believe it is actually useful for broader users, open an issue requesting that feature, and say LLM implemented it in an hour. Then the maintainers can prompt their own LLM to implement it with ease, or do whatever they want with their project.
I did this recently too, didn't really care about the code quality of a small tool, just asked Claude to add in the features I wanted and it produced something that worked.
I just pushed the changes to my fork of the project and left it at that. Leaves the feature around for me and anyone that stumbles across my fork, without wasting the original dev's time looking at code I didn't care to look at.
Even before AI coding I think it was relatively common to fork some code and edit it to have something you want, then to either leave it as a personal version, or to never actually get a response on the PR.
As a maintainer, discovering that a PR is AI-generated just absolutely saps any motivation I have to actually review it. I've never been a great reviewer, and AI means I have to watch out for really different kinds of errors. There's also the potential for extra friction with interactions with the "author": some people try to pull a "I'm just a smol bean, not a programmer, how dare you ask me to do anything" in response to changes, while others just play a middleman role in between you and the AI they're using.
If you're actually motivated to get a working fix upstream, and you're willing to do more than be a passive player, then it's not necessarily a problem to submit it (subject to responsible disclosure, of course)... but you also say that you don't have the time to properly engineer it, which makes me think you don't have the time to be sufficiently engaged in the upstreaming process anyways.
AI has inverted the effort - in the past a PR meant someone had to come in, read your ticket, documentation, code and tests to successfully author a PR. Subsequently reviewing that PR would typically take less time than authoring it and you would receive fewer PRs.
Now it is it the opposite, maintainers are flooded with low effort PRs that take more effort to review than author, but the author is unable to see why this is problematic to the maintainer and the project.
Exvuse me, I've been doing drive by manual slop PRs for at least a decade.
I certainly didn't read a ticket; I ran into the problem myself. I probably didn't read documentation or write tests either. I just fixed my problem and tried to help others a bit.
I'm glad it works for you, but please do not submit low-effort stuff like this, if you're not willing to do the rest of the work to make it maintainable.
I get the desire to help -- that's fine -- but AI code is abundant and of low value. Don't sandbag them with more work and increase their maintenance burden, with stuff they could easily vibe code themselves.
Just go for it. Do it enough, and over time you'll either find yourself resilient enough, or conclude that people do not actually deserve it (or rather that you do not deserve the struggle), and you'll be cured of this compulsion. The only way to go is forward.
It isn't clear that AI generated code is copyrightable, so that portion of the code wouldn't able to have the license enforced against violators, and so the authors wouldn't accept such code. Of course if its permissively licensed, the authors probably don't care to enforce the license, so might be fine including the code.
To submit the code, at minimum, you should review and fix the code diff, run the appropriate static analysis tools against it, write the pull request description and commit messages yourself, read the contribution guidelines, make sure everything matches that, disclose that you used AI and for what, and the prompts used.
It’s a reasonable when you frame it like this: the consequences of one AI-assisted addition are small… but maintainers are responsible for the codebase’s long-term quality after years of additions. The bar's higher. (Similarly, my friends like it when I host an occasional dinner party, but things would really suck at a restaurant run by nothing but my clones.)
Yes, if you can't vouch for the quality of the code that is the correct outcome. The long term health and maintainability of an open source project takes precedence over adding another feature. This was the case before repos were flooded with AI slop as well. Virtually no project would have accepted a random code dump if the person submitting it does not understand it because that just means the burden falls on someone else which would very quickly get any software project into big trouble.
If you don't have time to properly engineer it, then you can't submit. Why would you feel guilty? Others can throw a coin in the laundromat, too, if they are so inclined.
There is nothing wrong with forking, and one man's "better" version is another's bloat. Also, making a fork rather than a PR avoids burdening maintainers.
We're in this weird in-between phase of the tech world where projects like this can now be put together in a few hours/days, but the audience of us HN folk are still trained on the idea that this is the result of months or years of work.
We're going to have to re-train ourselves on what hard work looks like (and thus what should be upvoted here).
I don't know whether the project's creator (@willchen96?) is a lawyer, or if they work at a law firm that helped them shape this, or how much time and effort they put into this, or whether law firms even want or need a vibe-coded open source project for their legal AI stack, but we should be considering the totality of those things when looking at new projects these days.
I'm guessing a lot of similar debates were had in the 1970s when we first started compiling C to Assembly, and I wonder if the outcome will be the same.
(BTW: I was not around then, so if I'm guessing wrong here please correct me!)
Over time compilers have gotten better and we're now at the point where we trust them enough that we don't need to review the Assembly or machine code for cleanliness, optimization, etc. And in fact we've even moved at least one abstraction layer up.
Are there mission-critical inner loops in systems these days that DO need hand-written C or Assembly? Sure. Does that matter for 99% of software projects? Negative.
I'm extrapolating that AI-generated code will follow the same path.
The high level language -> assembly seems like an apt analogy for using LLMs but I would like to argue that it is only a weak one. The reason in that, previously, both the high level language and the assembly language had well defined semantics and the transform was deterministic whereas now you are using English or other human language, with ambiguities and lacking well-defined semantics. The reason math symbolisms were invented in the first place is because human language did not have the required unambiguous precision, and if we encounter hurdles with LLMs, we may need to reinvent this once more.
This debate didn't start with C. Compilers existed pretty much since Algol, and the debate was there too.
There were also similar arguments made about certain other mechanisms that programmers expected to become obsolete over time, but which never did. For example, all the "visual programming" that later transformed into "no code" programming never really delivered on the promise. (We still have a bunch of tools and languages that carry the "visual" adjective in them, but very few people remember why that adjective was there in the first place). Eg. Visual Basic was supposed to be visual because you'd build interfaces by dragging components into the designer view of your IDE and then using graphical editor style interface to position them, label them etc. Not only MSVS came with the "designer" view, Eclipse had one too, probably more than one. Swing had its own "designer" as did a bunch of other UI frameworks.
Programmers also believed that flat files will be gone and be replaced by some sort of a structured database with an advanced query mechanism. Again, never happened, and the idea is mostly abandoned today as the storage moved on in a completely different direction.
Object databases: (not to be confused with object store like S3) the direction that seemed all but assured at the down of objects -- never really happened either. Instead we still struggle with ORM, and it's not sure that ORM will not die off eventually.
I wouldn't be so quick as to profess AI prompt libraries to replace source code. There are many problems with this idea, beside the quality of the output. The control of the AI agents and their longevity (in source code this is ensured by standards). Collaborative programming: how people w/o access to the agent are supposed to work with the prompt library instead of the source code?
I don't think we are anywhere close to the point where we can realistically expect prompt libraries to be a generally accepted replacement for the source code. In some niche cases? -- perhaps, but not more than that.
Their best model to date and they won’t let the general public use it.
This is the first moment where the whole “permanent underclass” meme starts to come into view. I had through previously that we the consumers would be reaping the benefits of these frontier models and now they’ve finally come out and just said it - the haves can access our best, and have-nots will just have use the not-quite-best.
Perhaps I was being willfully ignorant, but the whole tone of the AI race just changed for me (not for the better).
Man... It's hard after seeing this to not be worried about the future of SWE
If AI really is bench marking this well -> just sell it as a complete replacement which you can charge for some insane premium, just has to cost less than the employees...
I was worried before, but this is truly the darkest timeline if this is really what these companies are going for.
Of course it's what they're going for. If they could do it they'd replace all human labor - unfortunately it's looking like SWE might be the easiest of the bunch.
The weirdest thing to me is how many working SWEs are actively supporting them in the mission.
The day I start freaking out about my job is the day when my non-engineer friend turned vibe coder understands how, or why the thing that AI wrote works. Or why something doesn't work exactly the way he envisioned and what does it take to get it there.
If it can replace SWEs, then there's no reason why it can't replace say, a lawyer, or any other job for that matter. If it can't, then SWE is fine. If it can - well, we're all fucked either way.
> If it can replace SWEs, then there's no reason why it can't replace say, a lawyer
SWE is unique in that for part of the job it's possible to set up automated verification for correct output - so you can train a model to be better at it. I don't think that exists in law or even most other work.
What is the automated verification of correct output and who defines that?
But before verification, what IS correct output?
I understand SWE process is unique in that there are some automations that verify some inputs and outputs, but this reasoning falls into the same fallacies that we've had before AI era. First one that comes to mind is that 100% code coverage in tests means that software is perfect.
Right, and that's why it's only part of the job. The benchmarks they're currently doing compose of the AI being handed a detailed spec + tests to make pass which isn't really what developing a feature looks like.
Going from fuzzy under-defined spec to something well defined isn't solved.
Going from well defined spec to verification criteria also isn't.
Once those are in place though, we get https://vinext.io - which from what I understand they largely vibe-coded by using NextJS's test suite.
> First one that comes to mind is that 100% code coverage in tests means that software is perfect
I agree.. but I'm also not sure if software needs to be perfect
Agree. Anthrophic in particular have been quite clear in what they are trying to do. Every blog post about every new model almost dismisses every other use case other than coding - every other use case seems almost a footnote in their communication.
Don't worry – if you're lucky they might decide to redistribute some of their profits to you when you're unemployed =)
Of course this assumes you're in the US, and that further AI advancements either lack the capabilities required to be a threat to humanity, or if they do, the AI stays in the hands of "the good guys" and remains aligned.
I have such mixed feelings about this - YC means VC means commercialization means enshitification. I really wish that weren't the case, but it so very often is.
Here's hoping this one's different...
(PS I am a big YC fan in general! I don't mean to sound anti-YC or anti-VC or anti-capitalism. But when it comes to low-level essential development tools, I'll never forget what happened to Warp, which started out as such a nice clean terminal project and turned into an absolute money-chasing mess.)