HN user

2ndorderthought

1,307 karma
Posts1
Comments635
View on HN

Yes that strong. Its only lacking in context length, but it's not that small there and it gets caught in circles more often then say a 1t parameter model does.

That's why a lot of people have been freaking out about local LLMs since april. There's finally a decent model that runs locally on a GPU or two that can do agentic programming at a reasonable enough tokens per second.

It's an important touch point for other code owners. I guess if no one is looking at the code anymore why even do an AI code review. It's kind of theatrical?

I seriously don't know how people are working like this now. I'm on my ass looking for work and in the last month it feels like everyone has completely lost their minds.

Correct they aren't opus. They are sonnet with a little hand holding. They also run on a single GPU at 40 tps.

No one is saying a local model will give you anthropics business in a 5min download. People are saying, "hmm, maybe I should do this one locally". People are also saying "this is surprisingly good enough for me given the trade offs"

As someone who watched one of their heros fall for some stupid cult like thing ten years ago and wondered the same thing. Then many years later fell for some dumb stuff. The answer is you probably will. Try to stay intellectually flexible, it'll be okay.