Mark LevisonFeb 4

AI is making us write more code. That's the problem.

I analyzed research papers on AI-generated code quality. The findings:

→ 1.7x more issues than human-written code
→ 30-41% increase in technical debt
→ 39% increase in cognitive complexity
→ Initial speed gains disappear within a few months

We're building the wrong thing faster and calling it productivity.

Show threadGothmogFeb 5
@mlevison I use LLMs to help me with basic code writing tasks, generating the structural frameworks, saving me a lot of typing time. However, I never rely on that code out of the box, I always review it thoroughly and often just snip and prune. I would never attempt to give an LLM a complicated set of instructions, it's going to fail every time.
Show threadalways tiredFeb 5

@crackhappy @mlevison

Couldn't human made deterministic tools (or changes to programming languages) help with boilerplate work instead of indeterministic intransparent generative AI?

Show threadGothmogFeb 5
@project1enigma OOP is exactly what you're describing. That was the tool, and still is the tool we're using to turn natural language coding into machine language. LLMs are just another layer on top of that, and a bad one.
Show threadalways tired

@crackhappy

"LLMs are just another layer on top of that, and a bad one"

That's my point. After you told about using those for tedious tasks.

Feb 5 at 1:42pmWeb