sheeshkebab

there are plenty of orgs where writing more code is not a good thing, in fact it's the last thing they want. but yet these orgs would still employ 80%+ of all developers, not necessarily to write code though.

unless they launched 10t param models, or figured out some amazing new way to compress as many params into say 100b, I doubt it's anywhere near "mythos level". and I have no idea how many params mythos has but that was just some hear say.

it’s not been useful anywhere else - no self driving cars, no laundry helpers - just some idiotic animatronic carcasses that are barely able to walk around, and semi autonomous killer bots on ukraine frontlines.

Qwen models are actually very competitive with frontier models, and you can run them on your local computer. Gotta have a decent graphics card and by that time the current cost of the rig may not justify it over paying $100/month for cloud model but it’s all out there.

Well, it was great while it lasted - I had fable build me a bunch of stuff this week that opus was just screwing up too much and could never finish. Good thing there are plenty of choices now even if US gov fucks up US AI.

Pro/max subs are not as flexible as bedrock in api use and don’t seem to run the same models either - often times they are notably dumber (quantized I guess) than bedrock equivalent.

I’ll ask it to write me some win32 ui crap when I get hands on it, it will need all its brainpower to get that idiocy right.

Opus regularly bitches and wines to me how long something will take and that I should think before asking it to do it. But then it does it anyway in 15 minutes.

considering they work with any architecture/configuration given enough compute, just more or less efficiently - then maybe it's fundamental, in the same sense as why electricity works...

I like gpt oss - great model even if not too smart.. runs on my laptop at over 100ts has a certain tone that I like over all these qwens stuck up their asses.

27b is slow as molasses vs 35b on local stuff I have (m5 max). Mtp doesn’t make any difference either.

…but they reason well enough given enough context (using their matmuls).

One of these days you’ll learn about “enterprise” code

Mist of human written codebases are unusable for llm dev by that definition.

It’s great laptop to mess around with llms, it won’t replace claude opus or even sonnet.

You can only run heavily quantized models on all 3/4/5 rtx gpus (with 32gb or less vram) - and you probably want moe versions like Qwen 35b for this to run at speed somewhat comparable to Claude. It’s still not there to be honest but getting there. Personally I mess around with llama.cpp on m5 max with 128gb - it’s a decent setup to try various medium sized things, and runs llms surprisingly well without quantization, at least the moe models.

The more Dario talks the less I want to have anything to do with his wares.

Ask it if there was a Tiananmen square massacre. Then decide if you really want to be part of this murderous propaganda.

IntelliJ is a bit dated, and its plugins are too. I use IntelliJ all the time, in its various incarnations, but vscode is really up there now.

So they nixed the fun part of working with the bot - reading its thinking output. Now this thing just plain unfun and often stupid.

So, yeah, good job anthropic. Big fuck you to you too.

Again, wake me up when it can do laundry.

It’s very likely their initial shock now wore off, and they got resupplied by putin and xi. We might start seeing much more damage going forward. US hasn’t fought a proxy war of this kind in many decades.

These traitors will eventually be all prosecuted. They are all traitors with putin connections, every one of them.

Yes

bc I build stuff like this myself - it doesn’t take anything to build a wrapper client around a good llm, including using another llm.

Obfuscated ts/js code is not machine code to begin with, so not sure what’s the big deal.

Also, not sure why anthropic doesn’t just make their cli open source - it’s not like it’s something special (Claude is, this cli thingy isn’t)

Human devs rarely need to create compilers. Those that do would do much better job.

what’s your point again?

The only model that works well for complex things is Opus, and even then barely (but it does and you need to use api/token pricing if you want guarantee it’s the real thing).

In those situations you basically need to guide llm to do it properly. It rarely one shots complex problems like this, especially in non web dev, but could make it faster than doing it manually.

Agree on the gap - in my own complex greenfield software dev spec test, opus 4.6 blows codex 5.3 out of the water, by wide margin, both in ui and backend.