Post #1462022
2026-03-14 12:16 UTC
Replies (4)
-
@fvsch@hachyderm.io 2026-03-14 12:20
Also I don't have a job currently, I'm busy full time with childcare and prepping our move abroad, and plan to look for a job or freelance contracts right after that. I feel like trying out some AI coding tools is going to be a requirement in my job search, so not sure I have the luxury to have a strict "AI, not even once" policy.
-
@tshirtman@mas.to 2026-03-14 12:24
@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.
-
@williamoconnell@mas.to 2026-03-14 13:14
@fvsch My work pays for an IDE with Claude built in, I like it but it definitely still makes mistakes sometimes and it's kinda slow. I can't really answer the ethics question for you; Gemini/Antigravity is another one to consider but of course that's tied to Google.
-
@0gust1@merveilles.town 2026-03-14 13:59
@fvsch I currently don't have the luxury to have a strict "AI, not even once" policy too (at work). And as a former cogsci/AI student, I'm too interested by the topic – but disgusted by the industry. I'm in line with the "extra background" too (lot of moral self-reflexions), and try to keep a critical and attentive posture. I use GH copilot at work since the private beta, it's not a bad solution if you use VSCode: - you can try a lot of models - it's not too expensive - you can cap your consumption - you can hook local-running models (but to have an efficient local setup, you'll need a powerful machine, think "beefed-up gaming PC/Mac Studio/Pro " with loads of RAM and GPU cores). It's not that "easy" to use, and being efficient with them is a bit far from the hype and inflated discourses you see online. Andrej Karpathy (who I find always reliable and honest, despite being in the "pro" camp) summed it up well here: https://xcancel.com/karpathy/status/2015883857489522876 Carefully craft your project's context file (claude.md, copilot-instructions.md, whatever). Stay away from hand-off tools/workflow (often promoted by CLI tools), keep yourself in the loop, always challenge the answers and beware of models idiosyncrasies. My most efficient uses are mostly: - brainstorming partner / answering rubber duck, when I feel stuck or want another take on conception and debugging - exploring unfamiliar or legacy codebases / tools (e.g. projects I didn't work on since several months, infra/ops tools) - smart autocomplete for "glue code" (I always start by writing myself tests or types / typechecked skeleton first - it helps tremendously).