brie

Grape, my nigga.

Large context window LLMs are able to do quite a bit more than filling the gaps and completion. They can edit multiple files.

Yet, they’re unreliable, as they hallucinate all the time. Debugging LLM-generated code is a new skill, and it’s up to you to decide to learn it or not. I see quite an even split among devs. I think it’s worth it, though once it took me two hours to find a very obscure bug in LLM-generated code.

Good, because it’s not of interest.

Even better for your career is being an actual researcher with a good grasp on heap grooming, MAC circumvention instead of spreading FUD over something that can easily be detected with burp.

LLMs are not programmed in a traditional way. The actual code is quite small. It mostly runs backprop, filters the data. It is already easily generated by LLMs.