←back to thread

AI makes tech debt more expensive

(www.gauge.sh)
466 points 0x63_Problems | 8 comments | 14 Nov 24 16:01 UTC | HN request time: 1.259s | source | bottom
Show context
perrygeo ◴[14 Nov 24 16:50 UTC] No.42138092[source]▶
> Companies with relatively young, high-quality codebases benefit the most from generative AI tools, while companies with gnarly, legacy codebases will struggle to adopt them. In other words, the penalty for having a ‘high-debt’ codebase is now larger than ever.

This mirrors my experience using LLMs on personal projects. They can provide good advice only to the extent that your project stays within the bounds of well-known patterns. As soon as your codebase gets a little bit "weird" (ie trying to do anything novel and interesting), the model chokes, starts hallucinating, and makes your job considerably harder.

Put another way, LLMs make the easy stuff easier, but royally screws up the hard stuff. The gap does appear to be widening, not shrinking. They work best where we need them the least.

replies(24): >>42138267 #>>42138350 #>>42138403 #>>42138537 #>>42138558 #>>42138582 #>>42138674 #>>42138683 #>>42138690 #>>42138884 #>>42139109 #>>42139189 #>>42140096 #>>42140476 #>>42140626 #>>42140809 #>>42140878 #>>42141658 #>>42141716 #>>42142239 #>>42142373 #>>42143688 #>>42143791 #>>42151146 #
cheald ◴[14 Nov 24 18:03 UTC] No.42139109[source]▶
The niche I've found for LLMs is for implementing individual functions and unit tests. I'll define an interface and a return (or a test name and expectation) and say "this is what I want this to do", and let the LLM take the first crack at it. Limiting the bounds of the problem to be solved does a pretty good job of at least scaffolding something out that I can then take to completion. I almost never end up taking the LLM's autocompletion at face value, but having it written out to review and tweak does save substantial amounts of time.

The other use case is targeted code review/improvement. "Suggest how I could improve this" fills a niche which is currently filled by linters, but can be more flexible and robust. It has its place.

The fundamental problem with LLMs is that they follow patterns, rather than doing any actual reasoning. This is essentially the observation made by the article; AI coding tools do a great job of following examples, but their usefulness is limited to the degree to which the problem to be solved maps to a followable example.

replies(3): >>42140322 #>>42143531 #>>42143847 #
MarcelOlsz ◴[14 Nov 24 19:43 UTC] No.42140322[source]▶
Can't tell you how much I love it for testing, it's basically the only thing I use it for. I now have a test suite that can rebuild my entire app from the ground up locally, and works in the cloud as well. It's a huge motivator actually to write a piece of code with the reward being the ability to send it to the LLM to create some tests and then seeing a nice stream of green checkmarks.
replies(3): >>42140464 #>>42140879 #>>42143641 #
sarchertech[dead post] ◴[14 Nov 24 19:55 UTC] No.42140464[source]▶
[flagged]
1. PaulHoule ◴[14 Nov 24 20:37 UTC] No.42140932[source]▶
I had Codeium add something to a function that added a new data value to an object. Unbidden it wrote three new tests, good tests. I wrote my own test by cutting and pasting a test it wrote with a modification, it pointed out that I didn’t edit the comment so I told it to do so.

It also screwed up the imports of my tests pretty bad, some imports that worked before got changed for no good reason. It replaced the JetBrains NotNull annotation with a totally different annotation.

It was able to figure out how to update a DAO object when I added a new field. It got the type of the field wrong when updating the object corresponding to a row in that database column even though it wrote the liquibase migration and should have known the type —- we had chatted plenty about that migration.

It got many things right but I had to fix a lot of mistakes. It is not clear that it really saves time.

replies(2): >>42141053 #>>42141069 #
2. imp0cat ◴[14 Nov 24 20:48 UTC] No.42141053[source]▶
Let's be clear here, Codeium kinda sucks. Yeah, it's free and it works, somewhat. But I wouldn't trust it much.
3. MarcelOlsz ◴[14 Nov 24 20:50 UTC] No.42141069[source]▶
Try using Cursor with the latest claude-3-5-sonnet-20241022.
replies(2): >>42141154 #>>42148341 #
4. PaulHoule ◴[14 Nov 24 21:00 UTC] No.42141154[source]▶
Unfortunately I “think different” and use Windows. I use Microsoft Copilot and would say it is qualitatively similar to codeium in quality, a real quantitative eval would be a lot of work.
replies(1): >>42141165 #
5. MarcelOlsz ◴[14 Nov 24 21:01 UTC] No.42141165{3}[source]▶
Cursor (cursor.com) is just a vscode wrapper, should work fine with Windows. If you're already in the AI coding space I seriously urge you to at least give it a go.
replies(1): >>42141385 #
6. PaulHoule ◴[14 Nov 24 21:23 UTC] No.42141385{4}[source]▶
I'll look into it.

I'll add that my experience with the Codium plugin for IntelliJ is night and day different from the Windsurf editor from Codium.

The first one "just doesn't work" and struggles to see files that are in my project, the second basically works.

replies(1): >>42141405 #
7. MarcelOlsz ◴[14 Nov 24 21:27 UTC] No.42141405{5}[source]▶
You can also look into https://www.greptile.com/ to ask codebase questions. There's so many AI coding tools out there now. I've heard good things about https://codebuddy.ca/ as well (for IntelliJ) and https://www.continue.dev/ (also for IntelliJ).

>The first one "just doesn't work"

Haha. You're on a roll.

8. lubujackson ◴[15 Nov 24 16:24 UTC] No.42148341[source]▶
Seconding Cursor. I have a friend who used Copilot 6 mo. ago and found it vaguely helpful... but turned him on to Cursor and it's a whole new ballgame.

Cross between actually useful autocomplete, personalized StackOverflow and error diagnosis (just paste and error message in chat). I know I am just scratching the usefulness and I pretty much never do changes across multiple files, but I definitely see firm net positives at this point.