| ▲ | SoftTalker 6 hours ago | |
I've never had AI one-shot even a 10 line script that I didn't manually revise. To be fair, it usually produces something that works, but after seeing it I'll realize that my prompt was too vague or I left out some edge case. So it's the old problem with software "it does what was asked for but not what was needed." So I speculate that a lot of problems with AI code are just that it is accepted uncritically because it builds and doesn't have any syntax errors. | ||
| ▲ | skydhash 5 hours ago | parent [-] | |
There’s a pressure to deliver more and faster from management. So instead of using LLM to reduce the coding time and allocate more time for review, everything is scaled down and there’s even less time for review. And you’re responsible for more as teams are also scaled down. Not really a great recipe for good code. | ||