Comments by "Brent Jacobs" (@br3nto) on "Mastery Learning" channel.

LLMs are interesting. They can be super helpful to write out a ton of code from a short description, allowing you to formulate an idea really quickly, but often the finer details are wrong. That is using an LLM to write unique code is problematic. You may want the basic structure of idiomatic code, but then introduce subtle differences. When doing this, the LLM seems to struggle, often suggesting methods that don’t exist, or used to exist, or starts mixing methodologies from multiple versions of the library in use. E.g trying to use WebApplicationFactory in C#, but introducing some new reusable interfaces to configure the services and WebApplication that can be overridden in tests. It couldn’t find/suggest a solution. It’s a reminder that it can only write code it’s seen before. It can’t write something new. At least not yet.
16
@elle305 I don’t think that’s accurate. Sure, you need the expertise to spot errors. Sure, you need the expertise to know what to ask for. But I don’t agree with the idea that you’ll take more time with LLMs than without. It’s boosted by productivity significantly. It’s boosted my ability to try new ideas quickly and iterate quickly. It’s boosted my ability to debug problems in existing code. It’s been incredibly useful. It’s a soundboard. It’s like doing pair programming but you get instant code. I want more of it, not less.
4
@chunkyMunky329 that innovation is happening constantly. There are so many ways the current architectures could and should be improved. Ability to append/modify trained models would be a start. Connecting disparate model, so you can combine public and private models together. Have ongoing processes that constantly evaluate and modify the models. We know AI in all its forms can do better because there are examples of what better looks like in nature.
2
⁠ @elle305 you don’t need to validate my personal experience. Just take a look at the latest StackOverflow survey.
1