| ▲ | red_hare 2 hours ago |
| How is OP using Claude relevant? |
|
| ▲ | gritzko an hour ago | parent | next [-] |
| OK for prototyping. Not OK for prod use if noone actually read it line by line. |
| |
| ▲ | odvcencio an hour ago | parent | next [-] | | ii am trying to not take issue with this comment because im aware of the huge stigma around ai generated code. i needed this project so i made it for my use case and had to build on top of it. the only way to ensure quality is to read it all line by line. if you give me code that you yourself have not reviewed i will not review it for you. | |
| ▲ | znpy an hour ago | parent | prev | next [-] | | That ship has sailed, man… | | |
| ▲ | overfeed 41 minutes ago | parent [-] | | No it has not - if it had, there'd be no need to shout down folk who disagree. Not everyone buys into the inevitabilism. Why should I read code "author" didn't bother to write? |
| |
| ▲ | atonse 20 minutes ago | parent | prev [-] | | Sorry but these are just not accurate as blanket statements anymore, given how good the models have gotten. As other similar projects have pointed out, if you have a good test suite and a way for the model to validate its correctness, you can get very good results. And you can continue to iterate, optimize, code review, etc. |
|
|
| ▲ | ks2048 an hour ago | parent | prev | next [-] |
| People should say what models/tools they used in even show the prompts. |
|
| ▲ | up2isomorphism 19 minutes ago | parent | prev | next [-] |
| Because OP obviously downplayed this important fact, which typically shows lower quality/less tested code. |
|
| ▲ | DeepYogurt 2 hours ago | parent | prev | next [-] |
| maintenance burden |
|
| ▲ | IshKebab an hour ago | parent | prev [-] |
| AI often produces nonsense that a human wouldn't. If a project was written using AI the chances that it is a useless mess are significantly higher than if it was written by a human. |
