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 threadGothmog
@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.
Feb 5 at 8:07amWeb
Show threadGothmogFeb 5
@mlevison Intellisense, pretti, etc. are all just tools for a smart developer.
Show threadChris PittsFeb 5
@crackhappy @mlevison Jetbrains vanilla Intellisense was pretty good even before the latest epidemic of AI psychosis.
Show threadGothmogFeb 5
@thirstybear @mlevison I refuse to call what we currently have "Artificial Intelligence" because it is not. It's a fundamentally clever implementation of Markov chains with way way too much power applied.
Show threadMark LevisonFeb 5
@crackhappy Most of the time I call it GenAI. LLMS is a better choice, but I need to use the language of the audience. If I say LLM then I have to explain it, @thirstybear
Show threadGothmogFeb 5
@mlevison @thirstybear That's entirely valid, but thank you for putting the GenAI on the front. That makes it palatable for those Not In The Know.
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 threadalways tiredFeb 5

@crackhappy @mlevison

IIRC for some languages there also have been deterministic refactoring tools too that take over the tedious parts of refactorings (like "rename method" which exactly identified callers to adapt them).

Show threadGothmogFeb 5
@project1enigma @mlevison I think you're a bit in the weeds on this.
Show threadalways tiredFeb 5

@crackhappy

What does that mean?

Show threadGothmogFeb 5
@project1enigma Overthinking it.
Show threadalways tiredFeb 5

@crackhappy

Oh ok. Thanks but no thanks for being judgmental about my thinking process.

Show threadGothmogFeb 5
@project1enigma I apologize for offending you. That is not my intention.
Show threadMark LevisonFeb 5

@project1enigma these might help

The bigger issue is that GenAI has no judgment. No understanding of correctness; readability etc.

Better refactoring is great, but not enough.

Curious what languages are you referring to?

Show threadalways tiredFeb 5

@mlevison

I personally work with C++ and am old fashioned and code with a text editor.

But the first time I read about refactoring tools, it was about the so called "refactoring browser" for Smalltalk.

https://wiki.c2.com/?RefactoringBrowser

Show threadalways tiredFeb 5

@mlevison

IIRC nowadays there are tools for at least some of the usual refactoring steps in many IDEs for common programming languages. I'd be surprised if there were none for Java for example.

Show threadalways tiredFeb 5

@mlevison

I'm personally also somewhat in favor of code generation for example for data marshalling/unmarshalling, parsing etc.

But that's deterministic specific generators then, either existing (lex, yacc and successors, for example), or in house/ad hoc.

Show threadalways tiredFeb 5

@mlevison

Or using higher level languages where this can be done as libraries supporting domain specific languages instead.

(There is stuff like Boost.Spirit for C++, though that still feels less natural than say parser combinators for Haskell)

Show threadMark LevisonFeb 5

@project1enigma I do refactoring all the time. I still have a copy 1st edition of Refactoring - Martin Fowler.

They tools exist, but they don't necessarily help the genai tools. Maybe a Claude Plugin for refactoring?

Show threadalways tiredFeb 5
@mlevison I'd specifically want to avoid those tools
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 tiredFeb 5

@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.