That sounds like 1) 2.5 Years are the new 10+ years and 2) My 15 year old Laptop can write Space invaders in Js, it just needs someone to touch the keyboard

So can my 12 year old ThinkPad. You do not need brand new hardware to run ai models, average hardware can do the same.

I still contend that this sort of task is uniquely positioned to show off LLMs. The idea that they’ll turn into agents that can do real-world tasks remains a fantasy. Despite how impressive this is, they’re losing money and have no real path to profitability.

I'm curious. What would it take to change your mind? I'd like to check in with you in two years to see what you think then.

but can it do it in assembly?

The local model scene is getting really good, I just wish I’d sprung for more RAM and GPU when I bought my macbook m1.

Even then, I can still run 8-12gb models that are decently good, and I’m looking forward to the new Qwen3 30b to move my tool use local.