Post #1926512
2026-03-14 12:24 UTC
@fvsch i think consensus is they got a lot better, but they still require supervision and help, thinking they can replace devs fully is foolish, but they can be force multipliers, (including when you mess up). That was already the case last year, but they need less help now.
Replies (1)
-
@tshirtman@mas.to 2026-03-14 12:34
@fvsch there are definitely reasons to be concerned about code quality if trusting these models too much, and code reviews only have immediate effects, they don't learn good practices like a human would. agents files and skills can help, but no avoiding knowing the codebase. there are free options, like qwen and deepseek (chinese) if you don't want to use american companies, or run localy (but expensive hardware needed for even moederately sized models, the frontier ones are out of reach.)