←back to thread

413 points martinald | 1 comments | | HN request time: 0.196s | source
Show context
blobbers ◴[] No.46203026[source]
I am shocked by the number of people who are dismissive of AI, or have stuck to the whole copy and paste into a chatbot approach to development.

I'm finding this stuff, when given proper guidance, can reproduce experiments I've run incredibly fast. Weeks of typing done in minutes of talking to Claude Code.

In the working world, a lot of the time what matters is getting results, not writing 'perfect' code the way software engineers would like to.

concerns: - security bugs - business logic errors that seem correct but are wrong

as long as you have domain experts, I suspect these will gradually go away. hopefully LLMs can be trained not to do insecure things in code.

replies(3): >>46204263 #>>46205571 #>>46207305 #
1. thingortwo ◴[] No.46205571[source]
I'm not dismissive of AI but I still do the whole "copy and paste" into chatbot approach simply because I use it as a boilerplate or research tool where the intent or workflows are already established and is targeted so it doesn't really matter how it writes since I can "parse" it's output quickly kind like an advance version of vscode saved snippet templates. I never use it do software design for me since this actually requires you understanding the problem but I can still use it to research existing stuff which is pretty cool.