I find that llms are mostly useful for people who are experts looking to make things faster. Today. For instance, I asked it how to do an update in Amazon Linux 2023. The answer it gave me was completely wrong. I said that answer is wrong. I said oh Amazon 2023 really does this. If I didn’t know that it was wrong, I could have waste quite a bit of time trying to figure this out. So in some senses llms are great if you know what you’re doing and want to speed things up, but if you don’t they can really waste a lot of time.
This is gonna be all production code within a few years unless they bubble pops. It was always obvious that relying on LLMs to generate code would lead to what is described.
I find that llms are mostly useful for people who are experts looking to make things faster. Today. For instance, I asked it how to do an update in Amazon Linux 2023. The answer it gave me was completely wrong. I said that answer is wrong. I said oh Amazon 2023 really does this. If I didn’t know that it was wrong, I could have waste quite a bit of time trying to figure this out. So in some senses llms are great if you know what you’re doing and want to speed things up, but if you don’t they can really waste a lot of time.
This is gonna be all production code within a few years unless they bubble pops. It was always obvious that relying on LLMs to generate code would lead to what is described.