| ▲ | himata4113 4 days ago |
| ehh, they're pretty good at automated performance research and bug fixes, especially when spanned across hundreds of them. |
|
| ▲ | pydry 4 days ago | parent [-] |
| bug fixes not so much. when I encounter a bug the first thing I do is ask an LLM and not only do they usually fail to get the correct solution, they often slap virtual duct tape on it which makes other bugs more likely. |
| |
| ▲ | himata4113 4 days ago | parent [-] | | feels like a harness issue, bug fixes work out fine with omp.sh as long as it can be tested properly. Untestable things tend to lead to hallucinated results though. | | |
| ▲ | pydry 4 days ago | parent [-] | | might be a symptom of writing complex code. I'm sure on basic CRUD they can figure out most bugs since most of them have happened 1000 times before. | | |
| ▲ | himata4113 4 days ago | parent [-] | | I doubt it, a lot of what I use llms for is on the very edge of what these models are trained for. |
|
|
|
