Hacker News new | ask | show | jobs
by Quothling 4 days ago
> So far, LLMs seem to deliver code with "Louie Da Loan Shark"-levels of tech debt.

Maybe a couple of years ago, but these days, Opus 4.8 is frankly writing better software than what I've seen over the previous decades in non-tech enterprise. These previous two months, we've replaced so much technical debt we've been dragging along for the previous 5 years as our team went from 25 to 3 people.

This is in non-tech enterprise in Denmark and AI had absolutely no impact on us going from 25 to 3. That was all Putin and bad business decisions on the c-levels. Like keeping flexible loans to fund projects on the books when the interests rates were 0.01% because they might go to 0.001%. Anyway, I'm getting to the point where the AI does 100% of the work, but only if it's piloted by people who know what security, resource consumption and compliance is. The code itself is excellent though.
2 comments
ChrisMarshallNY 4 days ago
Not sure why this got dinged.

It likely depends on the implementation, and the tool.

In my work, the Swift code is not really that good (but it’s not terrible), but the PHP code is very good (better than mine). I use ChatGPT. Maybe Claude might give better Swift, but I’ve invested quite a bit of context in ChatGPT.

link
bigstrat2003 4 days ago
> Maybe a couple of years ago, but these days, Opus 4.8...

No. Opus 4.8 still writes bad code, just like every other time AI boosters have claimed "but the newest models are really good".

link
9cb14c1ec0 4 days ago
The code I get out of Opus 4.8 is better than the code produced by most programmers I've met.
link
Quothling 4 days ago
Your experience is apparently different than mine. I went from using our corporate tool to copilot cowork when it became available to us. From opus 4.6 to 4.8 and there has been a massive difference. It's ridiculously good at programming in the right hands, but the right hands is frankly becoming more and more automatable as well, since you can input design documents, compliance policies and allowed packages and it'll do fine.

If you want, you can go through my history and you'll find that I haven't exactly been a fan of AI, but it's silly to deny that it's gotten good.

link