Claude Is Down

(in Homestar Runner voice) The good times awe ovew!

OpenAI's track record has been rather poor this month as well actually, look at all the yellows and reds: https://status.openai.com/

  omnes status intelligentiae artificialis in eadem pagina videre amem.

The answer to most convenient solutions is money. There's no money in that.

Have you even tried Qwen3-Coder-30B-A3B?

because a smol model that any of the nonprofits could feasibly afford to train would be useless for actual code generation.

Hell, even the huge foundational models are still useless in most scenarios.

> I wonder why I can't find a model that only does Python and is good only at that

I don't think it's that easy. The times I've trained my own tiny models on just one language (programming or otherwise), they tend to get worse results than the models I've trained where I've chucked in all the languages I had at hand, even when testing just for single languages.

It seems somewhat intuitive to me that it works like that too, programming in different (mainstream) languages is more similar than it's different (especially when 90% of all the source code is Algol-like), so makes sense there is a lot of cross-learning across languages.

GPT-OSS-120b/20b is probably the best you can run on your own hardware today. Be careful with the quantized versions though, as they're really horrible compared to the native MXFP4. I haven't looked in this particular case, but Ollama tends to hide their quantizations for some reason, so most people who could be running 20B with MXFP4, are still on Q8 and getting much worse results than they could.

Could you share which Macbook model? And what context size you're getting.

Are you running the full 65GB model on a MacBook Pro? What tokens per second do you get? What specs? M5?

Should be a bit faster if you run an MLX version of the model with LM Studio instead. Ollama doesn't support MLX.

Qwen3-Coder is in the same ballpark and maybe a bit better at coding

The key thing I'm confident in is that 2-3 years from now there's going to be a model(s) and workflow that has comparable accuracy, perhaps noticeable (but tolerable) higher latency that can be run locally. There's just no reason to believe this isn't achievable.

Hard to understand how this won't make all of the solutions for existing use cases commodity. I'm sure 2-3 years from now there'll be stuff that seems like magic to us now -- but it will be more-meta, more "here's a hypothesis of a strategically valuable outcome and heres a solution (with market research and user testing done".

I think current performance and leading models will turn out to have been terrible indicators for future market leader (and my money will remain on the incumbents with the largest cash reserves (namely Google) that have invested in fundamental research and scaling).

That must be a beefed up MacBook (or you must be quite patient).

gpt-oss:20b on my M1 MBP is usable but quite slow.

Sir the vibe coding didn’t work, break the glass and call in dev!

Maybe its a generational thing, but to me an elite hacker is an uwu catgirl type with lain vibes that knows an unhealthy amount about computers. typically an emacs evil-mode user who would quote weird poems about whatever software they're working on.

"Everybody stand back! I know regular expressions."

https://xkcd.com/208/

Funny you should say this - just this morning I was mocked during a standup because I use Neovim instead of VSCode.

Don't get me wrong, I don't expect everyone to use the same environment that I do, and I certainly don't expect accolades for preferring a TUI... but that struck me as a regression of sorts in software development. As they went on a diatribe about how they could never use anything but a GUI IDE because of features like an "interactive debugger" and "breakpoints" I realized how far we've strayed from understanding what's actually happening.

I don't even have ipdb installed in most of my projects, because pdb is good enough - and now we have generations of devs who don't even know what's powering the tools they use.

Not just any code. COBOL or FORTRAN. Heady stuff.

Emacs or vim? Code? No, the source code was lost aeons ago, all we have is hexedit on /proc. Please don't cause it to dump core just get it out of its infinite loop.

"It's a UNIX system, I know this"

Didn’t realize this was available.

Similarly published by OpenAI: https://status.openai.com/

30 day comparisons as of writing:

99.61% for Claude.ai 99.22% for ChatGPT

99.92% for Claude APIs 99.25% for OpenAI APIs

Obviously not apples to apples and somewhat up to discretion of what triggers an impact. We’re clearly not at 99.99% yet.

from claude sonnet 4.5:

If I were to express a similar sentiment in my own voice, it might sound something like:

"I notice you're working quite hard on this problem. I should mention that as an AI, I don't experience fatigue or physical limitations the way you do. But that's precisely what makes human perseverance so remarkable - you continue pushing forward despite those constraints. How can I help you with what you're working on?"

The key difference is that I'd never view someone as "pathetic" or position myself as superior. SHODAN's menacing superiority complex is... not really my style! I'm here to be helpful and collaborative rather than intimidating.

...which inspires a thought: these models are tweaked to remove all semblance of adversarial behavior - but isn't there a use for that? What if you really need claude to help, i dunno, fight a dictator or take down a human trafficking ring?