Yes, I always use `du . -h 2>/dev/null | sort -k1hr | head -nN` where that last N is however many directories I want to show. I run this regularly and have for a very long time precisely because of the issue that the post talks about.
$ ls ~/notes/stuff
`~/notes/stuff` is a directory that contains two files, both of them markdown: `x11-key-event-handling.md` and `x11-resources.md`. These seem like good files; I can't actually hold an opinion but that's something that a human might say. I hope you like them.
No, I prefer when my tools just give me information, same with LLMs.
Well, yeah, it's just good marketing and Bun ultimately doesn't matter anyway, not to the wider ecosystem and especially not to Anthropic. The only purpose Bun had for Anthropic was as a way of getting attention, so that's what they used it for.
You, by your own admission, haven't even written a single line of Zig despite having ~31 Zig projects on GitHub. I don't think your knowledge of the language is to be trusted in almost any capacity. This might seem harsh but I don't trust someone who's experience with a language amounts to slopping out 30+ repositories and not even engaging with the language normally.
By my own admission I wrote ~100K loc in zig-head. Having a background in linux kernel development of all things I can tell you that Zig is so much better than C or Rust, that I think linux kernel rush to rust is misguided.
I haven't even stated whether I agree with the opinion that Zig is worth it, in fact I do think Zig is worth it for a large set of problems and I wrote Zig for years, I am stating simply that I would never trust anyone who's self-admitting that they don't even write the language they're arguing for when it comes to opinions on whether it's good or not. It's not really about whether Zig is good, it's about someone who doesn't even write the language and doesn't even know it, not having a valuable opinion on it.
I guess that since you haven't built the car you're driving, your opinions on it are null and void as well.
Anyone who actually believes that I can't have ANY sound opinion on Zig after 31 projects building with it should get their head examined for brain tumors. I mean, it's not like I have to deal with all the positive and negative effects of things written in it. It's not like I've had to solve problems in it that emerged when the LLM didn't do things correctly (and yes, I can tell when this is so, and not just when things are buggy). And it's not like I don't know (by heart, not by LLM) at least 15 other languages that I can draw on (C, for example, for which I not only got an A in a class at Cornell once, but was in fact the person with the highest score in a class of ~150 people... A perfect score, in fact) to form valid opinions in combination with how I see Zig working.
So please take your baseless skepticism and baseless assumptions and shove them up your ass, dude. I have work to do, and I'm far more capable of it now than I was, thanks to the LLM boost.
Honestly, I wasn't harsh enough... Though I don't think I could write a better post showing how useless your opinion on things actually is than the one you wrote yourself.
And no, I don't think you can have any valuable opinions on Zig since you don't write it. In your analogy you're not even driving the car, but it doesn't surprise me that you can't figure that out.
I am absolutely plotting the route and intervening when the car tries to do something stupid. That ends up working out a lot better than actually driving the car because you can focus on the goals, the car often knows better routes that you failed to consider, you can measure the tradeoffs and you can determine the minimum-viable-path to get there, so just fuck right the hell off with this stupid-ass baseless skepticism
the ones learning how to run the looms safely and productively are going to continue to succeed and scale upwards and outwards while you get paid pennies to use knitting needles on bespoke hand-coded solutions. And at this point, I don't give a damn anymore because you lot deserve your upcoming rot 1000%, especially with a stubborn pissant plebe fucking answer like that. Holy shit. You're literally going to stubborn yourself into poverty just to make a point. Enjoy.
Jane Street has unlimited engineers and money to do this.
At least from the sidelines, it looks like they've built/forked most parts of the OCaml ecosystem to make it work (OxCaml, Dune was built by then, custom profilers, custom networking hardware, etc).
Of course a lot of their work is open source and can be used, but I wouldn't assume that it would be worth the effort to do something similar with OCaml yourself. Maybe it is! LLMs go brrr and all that.
You could produce a completely fcked up model using AI, and also a completely awesome one using AI. So, the "overstating capabilities" part really have nothing to do with this discussion.
As for the claim part around AI being used to assist further AI development, I have already told to read Anthropic's blog post. You can take help from chatgpt, if needed.
> Any country that developed sufficiently advanced models will pursue the same path.
Looking at most of the available evidence, Mythos is an incremental upgrade over other models and nowhere near the implied advancement that this seems to point to. I guess you could be right in that a sufficient advancement would cause this type of withholding of it, but I think it's kind of silly to think that the US has reached that level.
1. My own harness + Local (which usually means Qwen3.6-35B-A3B), I use this fairly often for research gathering on topics, info gathering on code bases, etc.
2. My own harness + DeepSeek v4 Flash served by DeepSeek, I added $20 quite some time ago and somehow still have $18.77 in there after I don't know how many prompts. I use this pretty often, slightly less than my local setup, it's great and what I'm planning on running locally (eventually).
3. My own harness + OpenRouter with whichever model I want to try out. I use this very rarely.
4. Pi + OpenAI Codex $20 subscription. I don't use this almost at all anymore, but I keep the Codex subscription for testing things out to see how GPT-5.5 will handle a problem the other setups have issues with.
> Why do you trust it with serving full quality?
The only thing I've noticed seems unbearably useless sometimes versus what I noticed before was GPT-5.5 which has had some of the weirdest degradations I've seen. It's not to Anthropic levels but it definitely had some service issues a few times where I was wondering if they had accidentally (or purposefully) lobotomized it.
Everything else has mostly just been the same, except DeepSeek I noticed had some speed issues a few days ago.
> What harness do you use? Why do you trust it not to have malware (most harnessed are TS apps)?
I pretty much only use my own, agents are trivial to make and it's definitely not hard to make one that's better than Claude Code or Codex for whatever you're doing.
I want to say that I agree with you on the value of writing your own coding harness. I wrote something simple in Emacs Lisp and it makes me happy occasionally using it. I am trying to learn Rust and I am working on my own Rust core orchestration layer and I plan on both a Rust command line client and I already have a Python library wrapper for the Rust code that I have written so far. I write a lot of ‘little books’ and I am almost sure to write yet another one on my current hacking project.
Are my little hacks as effective as OpenCode or Claude Code? No way, but I am learning a lot and having fun.
Do you write /maintain evals? This is something I want to get into more. Otherwise I feel really blind and feel compelled to just drop money on frontier.
Not really. I have one I made for fun where I let LLMs control a text editor called Kakoune, and then give them no other way to do things, to see how they deal with it, but that's not really a scenario I expect them to do well at.
So far most of them have done very poorly on that one, because they are all overtrained on just executing shell commands.
A former colleague of mine and I made a simple test for some baseline "Everything worth using should be able to do this pretty easily and swiftly" but that's some very minor code generation with a very straight forward, boilerplate-type pattern.
I saw someone on lobste.rs proudly say that they haven't written a line of Zig code in their life. They have 31 Zig repositories on GitHub. GitHub is useless at this point. (As you might imagine, they also post on HN regularly and is quite "AI positive".)
Corporate open-source (Open Source) is done for free labor and PR, it shouldn't be bonus points for any company that does it, unless they commit to it and pay their contributors, have no CLAs that allow them to relicense the work, or adopt practices and licenses that are clearly more in line with the actual spirit of free software. Real free software that should be considered a public good is produced by people, for people.
There are sometimes well meaning people in corporations that do their best to at least get something out there and kudos to them, but corporations running Open Source projects should receive no goodwill for it, it's basically a scam.
Well yeah, you shouldn't give much credit to the corporation, but neither should you backlist all applicants who ever worked for them (as OP says some frontier labs do)
I'm not really commenting on that, I just want to remind people that Open Source is highly overrated and should not be looked at as a point in favor of a company.
While I agree with your point I don't agree that open source is overrated. This movement is one of the greatest developments in modern history, and the fact that corporations have exploited it for their own gain should in no way diminish its significance.
Open Source is the company takeover of the good that Free Software represents, I don't really see it as a "movement" by people. It's set up precisely to exploit the people for free labor and look good doing it.
Eric S. Raymond: "The people who knew Russ as a Quaker, a pacifist and a gentleman, and no racist, but nevertheless pressured OSI to do the responsible thing and fire him in order to avoid political damage should be equally ashamed. Abetting somebody elses witch hunt is no less disgusting than starting your own. Personally, I wanted to fight this on principle. Russ resigned the presidency rather than get OSI into that fight, and the board quite properly respected his wishes in the matter. That sacrifice makes me angrier at the fools and thugs who pulled him down."
>Guido is not racist like ESR is, and it would have been a disaster to have somebody as racist and obsessed with dragging the organizations he leads into the pro-racism side of political culture war battles that have absolutely nothing to do with their mission, as ESR has a track record of trying to do: He threw down the gauntlet and attempted to drag OSI into supporting Russ Nelson after his infamous "Blacks are Lazy" blog posting that caused him to resign for the good of OSI, who ESR wanted to spend their resources and reputation fighting his culture war against (dog whistle alert:) "thugs" who don't want to follow a racist leader. That kind of blatant racism and totally non-python-related racist culture warfare bullshit political battles would have been extremely detrimental to the python community, just as his other antics and his and Russel's racist rants were detrimental to the open source community. OSI has enough problems attracting women and minorities that they don't need white male leaders telling black people they're lazy and accusing people who disagree of being "fools and thugs".
Russ pulled his own "Blacks are Lazy" post down and resigned of his own free will and was not fired, so ESR was unwittingly calling Russ a fool and thug for pulling himself down, even though he was actually attacking anti-racist people, who didn't believe blacks are lazy, and thought racist white people who publically called all blacks lazy (then patronizingly lectured them on why they are justified to be lazy) didn't deserve to lead OSI.
Actually, Russ is a Quaker (or rather used to be until he renounced it for being too "socialist"). He created the first Quaker website in the world, quaker.org, in early 1995.
But his actual lifelong ideological religious cult is Libertarianism, obviously. And they epitomize what's wrong with the open source movement, ESR having based his career on tearing down and shitting all over everything RMS has done with Free Software.
ESR and Russ and their ilk just love playing a tired little game I call "Libertarian Chicken":
For many more examples, just look at the decades long consistent pattern of ESR's obnoxious inflamatory posts to the linux mailing lists, before he got kicked off for playing said games.
reply