This is an aside, but I'm really struck by how many people on HN use Windows (based on repeated mentions I've seen in comments). I've worked for a pretty wide range of companies over the last decade and only one, maybe two companies even had any people that worked on Windows machines. I haven't worked at a company where devs used Windows in 15 years (and even that company eventually switched to linux).
As I've gotten deeper into LLMs/AI roles even Macs have seemed to start having equal share compared to devs running full Linux setups.
Is this just a sign of that a larger and larger portion of HN users are working for large corporations? I honestly can't even remember that last time I saw a serious developer pull out a Windows laptop.
While we're doing anecdotes: I essentially never meet people who own an iPhone, and I've lived (3 months+) in a huge number of countries and cities. The handful people who do are American; bubbles exist :)
For a long time, high end graphics and games was mainly done on Windows and Visual Studio. I'm from that world, and only made the Linux transition last year November after Microsoft forced everyone's hand.
I've been a developer for more than two decades. I've worked at four employers during that time, and all of them had significant fractions of devs using Windows. Not vouching for the idea that any of them are "serious" though. I've never worked at a prestige employer or FAANG or anything. Just boring businesses of different sizes. Some are software, and some just do software. But Windows has always been everywhere.
If you work at a company with well over a hundred employees, you're likely to see at least half of them on windows and devs may get an option of Windows or Mac... and IMO, Windows + WSL + Docker is actually slightly better than the Docker experience on Mac. There's plenty that I really do hate with Windows though. I'd rather run Linux but most corp environments just don't have the tooling for it.
Windows laptops suck ass compared to an MBP. Windows desktops are pretty nice, you just need to do a lot of first time setup to remove all of the cruft and make sure you have a local user account etc. But for a typical dev building a desktop every 5 years or so that isn't a big deal.
One thing to consider is non-office whether remote or personal projects.
A lot of devs like gaming. Gaming is more simple on windows. Gaming PCs are usually high spec. High spec is good for most coding.
That's why I use windows quite often. My laptop is Linux, but when I'm running heavy models I'll still remote into my main Windows PC, which I also use for gaming.
Though in terms of workplaces - sure, I reckon you're on the money. Big corps often still force windows onto their Devs.
My biggest client right now is about 2/3 Windows 1/3 OS X in the dev team. It was very surprising to me, but I think I freak then out with my maximised tiled iTerms on multiple screens...
I'm a professional C++ dev working in games, and windows is used everywhere , from games themselves to the network infrastructure(I've worked for 3 of the largest games publishers too).
Windows really has a fantastic support for C++ and rendering programmers imho, the tooling is world class and Visual Studio has no match as an IDE. Even if somehow my tools worked on Mac or Linux I'd still pick windows out of sheer convenience of using it for work.
But as things stand - all major console toolchains are windows only. If you're making a game for PlayStation, Xbox or Switch, you have to be on windows.
Anthropic's and OpenAI's products are janky and their services are unreliable, but they have incredible product-market fit and revenue growth. They deserve a ton of credit for getting the big things right.
The risk for them is that someone matches their products while also having non-janky products and reliable services.
Distributed systems infrastructure, especially, is much less forgiving of vibe coding than application code. Coding agents are not even close to being good enough to design and build large-scale systems the way expert humans can.
There is nothing wrong with using agents to help write infrastructure code, but these systems have a way of punishing anyone who builds things they do not fully understand.
I'd love to see either Anthropic or OpenAI really step up their infrastructure game.
Coding is probably solved, at least to a large extent, but that doesn't mean engineering is solved too.
This is like someone saying that the wright brothers solved sustained/powered human flight, and another person saying "well if that's the case, why do planes still crash? obviously flight isn't solved.". Well, there are always improvements, but planes can fly and llm's can code.
Regardless of what? Programming is solved, I hear, with all the 100x productivity PhD-level automated coding loops they have going. Don't make excuses for them when they disprove their own bullshit.
Claude Code is notably better than Pi, although I wish them the best of luck in their efforts. As https://c-daniele.github.io/en/posts/2026-05-18-coding-harne... notes, "Pi's lightness comes from a default setup that does not survive contact with reality."
The same post on Claude Code: "Even though the System Prompt and tool descriptions are clearly more verbose, most of the extra tokens encode product features and rational design choices: a memory system, scheduled tasks, sub-agents, plan mode, worktree support. Whether those features are worth paying for depends on your needs. Calling the prompt 'bloated' without looking at the whole picture feels wrong to me."
The "guardrails" are bloat if you're using a proper sandbox. This seems like a matter of using the right harness for the environment it's running in, rather than one always being better than the other.
I ask Claude to implement non-regression tests. It works like magic. With a couple of modules checking for code quality, more magic. Add some online performance tests if relevant, and it is close to paradise. From time to time, send it to some blog pages and articles with implementation ideas and recommendations. Look for best practices and let it do the analysis and implementation job if it makes sense... T
How is text editing in it? This is what I hate about terminal coding UIs the most - all the text editing experience is often broken, the basic stuff (moving the cursor around, copying, pasting)
It's not just Windows where the rendering goes to shit immediate: any time I've got it open in tmux on Linux, it becomes a basket case in probably a few hours or less.
I've seen this too. I had a couple of instances inside a tmux session, and after some time, everything in there slowed down to a crawl. What I found interesting is that terminals outside tmux were fine.
That's interesting - I just fixed my terminals rendering by having Claude build a test harness that used tmux as an oracle, and one of the programs it fixed the rendering of by reading out the tmux pane was Claude Code itself...
Is this a new regression for others? I feel like I used it in a tmux setup without issues for 6+ months and only recently am I forced to Ctrl+L or resize the window constantly.
FWIW Codex TUI is written (in large part) in Rust and is way less buggy, and a lot faster. When I was a regular Claude Code user I'd routinely get bizarre "scroll everything since the beginning of time in one massive flash on every update" bugs ... for months. Like, just there from the time I started using it in June '25 or so until I quit in March.
I prefer it over opencode, which is my other option I use with my Codex sub
That particular bug seems to be gone. I'm using my own Ruby terminal, and it's more than fast enough for normal stuff, but it made that bug 10x more painful so I am particularly sensitive to it... Not seen it at all recently.
Would it not be hysterically funny, if they starting expanding their job openings for Software Developers ? Or they will be too ashamed of calling them that?
On the other hand, my last experience with gemini was like "don't give your sandwich to the dog again" whereas with opus it was more "let's debug why this uncrustables factory is having breakdowns".
Claude harnesses have plenty of bugs but I prefer capability over interface shininess any day. (though if I were running the show I'd have a sizable team set aside to do exclusively boring stability and polish work)
The errors are infrequent enough that this normally wouldn't be an issue for me.
Except, starting this morning, one very long running session decided to start spawning subagents for each task. I'm not sure what caused this emergent behavior, but it seemed to be working fine, so I was eager to see where it went.
Except, as soon as a subagent hits a 500 error, the main agent seemingly doesn't know what to do. It kind of panics ("now the tree/install state is unknown!") and ultimately does a git checkout "to verify and restore a known-good state before anything else".
I've paused the job for now since it's a sort of background experiment.
This is every few weeks, I cancelled Anthropic and now use Codex only. Anthropic has been a hot mess since at least december in my usage, and has only gotten worse in 2026.
Yeah, it's been a hot mess since everyone started using it all the time. Which is not all that surprising. It's really hard to scale fast, and even more so when the resources you depend on (GPUs) are extremely hard to acquire.
I'm not sure about that. Claude has some bugs, but Codex is not as polished and doesn't have as many features. For example, you need to add MCP servers manually. There's no Plugin/Skill/Connector marketplace that is accessible from within the app, like there is with Claude Desktop. The Cowork-equivalent is nowhere as powerful. And so on.
I still use Codex, but mostly when I need to check Opus 4.8's work. Pretty sure I will stop doing that soon, because during the short time Fable was available, Codex was not able to find any important issues with the code Fable wrote.
But how many plugins are people actually using? I can think of one MCP server I find valuable (context7) and one plugin that i've installed, but continuously think about uninstalling (obra/superpowers).
It's a good thing. I hate MCPs from the bottom of my heart because they always stay there and bloat the context window. Also, usually developers who develop them don't know what they're doing, so the MCP responses also bloat your context even further.
That's the first time I saw someone prefering GPT-styled output over Claude ;) It's the complete opposite for me, GPT is way too verbose (even after telling it to STFU), overwhelms the user with thousands of options and doesn't just answer a question without shitting out thousands of paragraphs. Also the overall tone is way too enthusiastic.
I strongly prefer codex. Claude is annoying. Codex provides descriptions where I want them and more touchpoints to audit the quality of work. Claude code on experimental seems to not even show diffs when asked anymore, and it's much less clear what is being shipped.
Dunno, I prefer GPT 5.5 too for the same reasons as the parent. Extremely subjective but had better results with it too. Maybe I just got unlucky with Claude a few times, but even the latest Opus was dumb.
Only getting errors with Auto Mode's safety classifier, switched to Accept Edits mode and the same bash operations triggering the errors executed with no issue.
Working for me but it's funny that Opus 4.8 is draining usage exactly as quickly as Fable did. It's all made up; they succeeded at making us ok with a black box for these subscription plans.
Anthropic is full of junior devs, not knowing any better, vibe coding themselves into a huge mess. They are so young and dumb they don't know what they don't know, but they assume they do (of course). Their hiring pipeline is also brain dead, so I don't think it's going to get better. It's the blind leading the blind.
Claude Code is especially buggy in windows terminal. The rendering is quite slow, choppy and lines frequently get garbled.
In contrast, using antigravity cli is the exact opposite: fast, smooth and very responsive.
This is an aside, but I'm really struck by how many people on HN use Windows (based on repeated mentions I've seen in comments). I've worked for a pretty wide range of companies over the last decade and only one, maybe two companies even had any people that worked on Windows machines. I haven't worked at a company where devs used Windows in 15 years (and even that company eventually switched to linux).
As I've gotten deeper into LLMs/AI roles even Macs have seemed to start having equal share compared to devs running full Linux setups.
Is this just a sign of that a larger and larger portion of HN users are working for large corporations? I honestly can't even remember that last time I saw a serious developer pull out a Windows laptop.
For a long time, high end graphics and games was mainly done on Windows and Visual Studio. I'm from that world, and only made the Linux transition last year November after Microsoft forced everyone's hand.
A lot of devs like gaming. Gaming is more simple on windows. Gaming PCs are usually high spec. High spec is good for most coding.
That's why I use windows quite often. My laptop is Linux, but when I'm running heavy models I'll still remote into my main Windows PC, which I also use for gaming.
Though in terms of workplaces - sure, I reckon you're on the money. Big corps often still force windows onto their Devs.
Windows really has a fantastic support for C++ and rendering programmers imho, the tooling is world class and Visual Studio has no match as an IDE. Even if somehow my tools worked on Mac or Linux I'd still pick windows out of sheer convenience of using it for work.
But as things stand - all major console toolchains are windows only. If you're making a game for PlayStation, Xbox or Switch, you have to be on windows.
The risk for them is that someone matches their products while also having non-janky products and reliable services.
Distributed systems infrastructure, especially, is much less forgiving of vibe coding than application code. Coding agents are not even close to being good enough to design and build large-scale systems the way expert humans can.
There is nothing wrong with using agents to help write infrastructure code, but these systems have a way of punishing anyone who builds things they do not fully understand.
I'd love to see either Anthropic or OpenAI really step up their infrastructure game.
Coding is probably solved, at least to a large extent, but that doesn't mean engineering is solved too.
This is like someone saying that the wright brothers solved sustained/powered human flight, and another person saying "well if that's the case, why do planes still crash? obviously flight isn't solved.". Well, there are always improvements, but planes can fly and llm's can code.
Claude Code is sluggish, buggy, slow. Typical big enterprise garbage. The only good thing at Anthropic are the models.
The same post on Claude Code: "Even though the System Prompt and tool descriptions are clearly more verbose, most of the extra tokens encode product features and rational design choices: a memory system, scheduled tasks, sub-agents, plan mode, worktree support. Whether those features are worth paying for depends on your needs. Calling the prompt 'bloated' without looking at the whole picture feels wrong to me."
Or possibly as a result of.
Can you post some images of lines getting garbled. That sounds like a genuine bug Anthropic might want to look into. I haven't seen that ever.
I prefer it over opencode, which is my other option I use with my Codex sub
Claude harnesses have plenty of bugs but I prefer capability over interface shininess any day. (though if I were running the show I'd have a sizable team set aside to do exclusively boring stability and polish work)
That sounds like a you issue.. it's wonderful on the terminal. It's their GUI which needs work (they have been improving, but still not a fan).
I've been using it on multiple computers for months and it's generally rock solid and lovely.
Except, starting this morning, one very long running session decided to start spawning subagents for each task. I'm not sure what caused this emergent behavior, but it seemed to be working fine, so I was eager to see where it went.
Except, as soon as a subagent hits a 500 error, the main agent seemingly doesn't know what to do. It kind of panics ("now the tree/install state is unknown!") and ultimately does a git checkout "to verify and restore a known-good state before anything else".
I've paused the job for now since it's a sort of background experiment.
Can you move it to background connection?
I still use Codex, but mostly when I need to check Opus 4.8's work. Pretty sure I will stop doing that soon, because during the short time Fable was available, Codex was not able to find any important issues with the code Fable wrote.
Both were trivial to set up with codex.
This is all wrong.
Haven’t tried Cowork, interesting. Isn’t it just the same agent minus the git worktree based UI?
Frankly, neither Claude nor Codex are as good as hype entails.
Crazy thing is ... its true.
Can't wait for debugging to be solved. Hell, I might even subscribe for 'mostly'.
You just have to pay API prices.
Don't jinx it. They might use that name for their next model.
Yes I know you can run offline models, but it's hard to pass up on a little bit of snark.
https://en.wikipedia.org/wiki/Rational_Software
https://en.wikipedia.org/wiki/Rational_unified_process
What do we do?