[evilduck]

You can accomplish quite a lot with smaller local models on reasonably priced pro tier hardware (not cheap hardware, but very attainable hardware for anyone making average software engineer money). Qwen 3.6 27B and 35BA3, Gemma 28B, and so on are incredibly beneficial even if Anthropic and OpenAI produce better options.

Failing that, GLM 5.2 is open weights, trades blows with current frontier models and widely available on commodity inference providers. And you could run it yourself if you do actually have the resources.

[asdff]

Why pay for hardware for local model when you have a working local brain?

[fragmede]

Because I'm using my local working brain to work on other things. If I'm thinking about my family or making dinner I'm not thinking about the code I need to write. Or the email that needs to get sent, or setting up an eye doctors appointment. I'd pay for something to deal with that.

[asdff]

Do you frequently think of the code you are needing to write when you are thinking about your family or making dinner?

[fragmede]

I find inspiration often strikes while taking a shower or after a good sleep.

[asdff]

It stopped striking like that when you let agents write the code? You don’t think about what agents you can direct while taking a shower or making dinner?

[fragmede]

I wish I could stop thinking when I wanted to. The problem is my working memory is very full and being able to hand some of that off, to a paper notebook or a todo app on my phone, or an agent, is valuable.

[evilduck]

Why pay for a car to drive when you have working legs? To go further, faster.

[asdff]

Was velocity of writing the code ever the limiting factor in this business? If it was/is, why pay for westerners to prompt agents when you can pay for 10 fold more southeast asians to prompt agents?