If y’all can’t cope without Claude, y’all need Jesus. There’s the “can boost my productivity “ and then there’s the “Claude takes the wheel and my brain is off”.
AGENTS.md on a standard protocol. Sorry but no. You either understand the thing or you don’t.
It’s a chat protocol. Something that is supposed to be very private and secure. Seeing an AGENT.md file is a huge turn-off there, sorry to say. Feel free to burn my karma down to oblivion.
I'd actually feel pretty safe with a LLM project if spec'd against the protocol documentation as opposed to a rookie's handcoded implementation. If security is the concern, I don't think using random reimplements is very safe to begin with.
Same. I had a couple LLM's rewrite, harden an anonymous image board. It's not popular but exposed to the internet and the Tor network. Not worried at all.
Unless the model changes and messes half the code base on next iteration. Or Anthropic decides to A/B test your agent.
Or when shit goes sideways and someone actually needs to take a human look at the BF s. I’d rather have the guy who manually with human eyes read the specs.
> Something that is supposed to be very private and secure
Not sure how using an LLM for development of the tool has any affect on this. From a security perspective, I think that would've had more validity a year or two ago, but these days, I'd argue LLMs practice better security in generated code on average than a normal developer.
From the privacy angle, I have no idea how having an AGENTS.md (for development purposes) has any impact on privacy.
I don't want to "burn [your] karma to the ground", I just want to understand this angle, because I'm not sure I see how it applies.
Indeed, Linus Torvalds is infamous for not caring what he ships (https://news.ycombinator.com/item?id=50111350). That's why he's never been known to go on, let's say impassioned tirades against people who submit bad patches to the linux kernel. After all, it's not like he's ever apologized for inflammatory behavior before (https://news.ycombinator.com/item?id=18000698).
On a more serious note, it's not a dichotomy that one either uses AI to code or they care about what they ship. Some people use AI to code and care what they ship.
Point 1 is dependent on the individual and often not the case. Especially in cases where the part that takes effort is figuring out the poorly documented syntax/api you’re stuck with for the task (extra fun with new components iterating rapidly and pinning the next version requires new scaffolding), you can read the invocation and the accompanying couple of lines of test code way faster than you’d mould them yourself. Which also translates neatly to point 2 (how efficiently can you in many cases ascertain the outcome of smearing the chosen bits on the cpu with easily digestible tests).
Also the emotionally laden appeal to "responsibility" is weak, as it glosses over the many cases where overspending resources on creating the thing would be the irresponsible choice.
> Point 1 is dependent on the individual and often not the case.
Not really. To properly understand code you must have a mental model of what it is doing. You need that model whether you are reading or writing the code. It is easier to build that model while writing the code than while simply reading it. To build the model while reading the code requires having the same understanding of the problem and the same approach already in mind, which is almost never the case for any moderately complex problem.
> Especially in cases where the part that takes effort is figuring out the poorly documented syntax/api you’re stuck with for the task
Reading LLM generated code does not avoid this, and in fact it is often worse since LLM comments are terrible at getting to the point.
> Some people use AI to code and care what they ship.
The vast, vast majority of people using LLMs to build software don't care at all about quality. I'll grant you Torvalds, but he's very much not the norm (and he's wrong: by the time you review the code the model wrote, you spent as much time reviewing it as you would've writing it, so no time was saved).
Believe it or not, some people actually know how to write code, and <shock horror> understand what it fucking does too!
I will never understand software dev's obsession with LLM generated slop. Compare it with the response from the likes of professional authors, artists.
I've said it before I'll say it again: a computer generating shit en masse for you is great if you don't know how to do it yourself, and don't care what the result is.
That only works because the clockmaker had the manual experience to begin with and only needs to remember to get back into the groove. If however he had always only worked with CNC machines the story would be very different.
I'm not convinced that's true. If you have experience driving an automatic car with lane assist, you'll have an easier time driving a 1980s manual car than somebody with no driving experience at all.
Likewise, the machinist still knows the principles of construction even if he's only used CNC machines. The endoscopist still knows the principles of colonoscopy even if he's only done it with AI assistance.
Just anecdotally, back when I took courses in assembler and logic circuits, there seemed to be no great difference in success between people like myself that had previous experience with that, and people who'd at most done some high-level scripting.
If you have enough curiosity I doubt using AI will be a roadblock to true understanding, just like high-level programming languages weren't.
Same. That is why I am over in a corner happily coding away with Common Lisp and McCLIM to write myself an editor that mixes ACME UI with Lisp. Is it ultra-polished? Hell no. But it definitely keeps me sane and I know what I wrote.
Only on the UI part though. I wanted a Genera/CLIM approach, so having that filesystem thing sitting there felt wrong. But I did like the “all UI is text” approach. And with CLIM presentations it can go very far.
If Ubuntu offers LTS and is catering to business it is very much open to criticism. They can take it or leave it, but anyone is entitled to an opinion about it.
To pre-empt any replies: yes, I absolutely prefer BSDs over Linux any day. But even those are flawed and I really think we missed the Symbolics golden era. THAT would be the age of "own and live in the system". OpenBSD gets closest there. At least the codebase is hackable enough.
Linux went off the fucking rails. What the fuck is that over engineered yes command?!
The OpenBSD implementation is much slower than both the GNU versions from 2015 and 2026. However, their goals are different from ours, and that statement should not be interpreted as criticism of theirs.
It makes the code way less auditable and more prone to bugs and errors. Or let the kernel change its paging mechanism and now your fucking “yes” tool needs an update to be “efficient”. The tool has one job…print yes or another word you give it. It by definition does not have to optimized to oblivion. Same goes for echo.
It’s arsinine to optimize it to that level instead of just keeping it readable and maintainable. And portable.
The gnu version is 100% not easily portable because it has assumptions about the underlying kernel.
> It by definition does not have to optimized to oblivion. Same goes for echo.
I don't know about oblivion, and non-portable optimizations are not good. But perhaps yes(1) and echo(1) are among the tightest inner loops of scripting. You would not want them to bottleneck the pipeline. You'd want them pumping output faster than it could be accepted or written out.
Perhaps there is an opportunity for a /dev/yes, which acts like /dev/zero, only it continually outputs whatever filename it was opened as (good luck!)
The current implementation works on any system with read and write system calls.
The Linux optimization just uses splice and vmsplice. If those APIs are changed to avoid zero-copy, as was considered for some time after the AF_ALG security issues, it is unlikely that another API would take their place. So, no, I do not think it needs any changes if Linux changes.
Sure, CPU wise an old phone can do the same job, but not the GPIO.
But hey, thanks AI delusion , even a fucking raspberry pi is now a purchase I gotta think 3 times about before pulling the trigger.
reply