logoalt Hacker News

hopa • today at 12:57 AM • 10 replies • view on HN

I feel like AI is amazing for read only “search” tasks (query this, look for bugs, find vulnerabilities) but it’s not quite as good for “write” tasks like “add this feature”. Search tasks are easily verified, code changes are much harder to verify


Replies

bheztio • today at 1:06 AM

"Add this feature" is often too vague, unless it's yet another button to a list of buttons. If you want your feature in a particular way, you need to specify it. If you're not even sure what you want, it's granted you won't be satisfied by the result, so you need to spend time figuring that out first. In other words, they're definitely great for write tasks too, but it does require more effort from the operator to formulate the problem.

➕ show 2 replies
simonw • today at 1:00 AM

I'm not sure about that. The most common error for a search task is omission, and that's really hard to spot - how do you verify that some answer that should be there wasn't included?

For things like "add this feature" you can verify by trying out the feature and seeing if it works. Of course, that won't tell you if there are edge-case bugs or security holes or other design flaws, but you can get to a positive confirmation of the happy case pretty quickly.

➕ show 1 reply
ipdashc • today at 1:00 AM

I've slowly been coming around to this viewpoint as well. It's interesting that there's so much focus on using AI to write code (which, don't get me wrong, does work well but makes you lose track of what you're building so quickly) and seemingly less on analyzing code, finding bugs, etc

➕ show 2 replies
MBCook • today at 1:05 AM

But it DIDNT “write that feature”. They made it extremely clear on the delay announcement the code was written without AI.

AI’s only part of this was helping review things and finding bugs. More bugs, bugs that would have been found later, whatever.

Postgres did not have a slop issue and it’s wrong for people to insinuate it.

➕ show 2 replies
r_lee • today at 1:19 AM

I mean the transformer model came out of Google, and it's literally a query thing so yeah.

any kind of pattern matching / transformation is going to be an ideal task for LLMs

➕ show 1 reply
vatsachak • today at 1:14 AM

What? AI can't easily implement features. Just write a spec, ask if to expand it and then ask it to implement it

xyzsparetimexyz • today at 4:06 AM

No offense but this is not exactly a groundbreaking statement. We've known about this verifiable tasks thing for a while.

milojy8 • today at 6:41 AM

[flagged]

DIE_DIE_DIE • today at 1:02 AM

[dead]

hoppp • today at 1:43 AM

If the entire project is developed with AI it can add features effectively but for large old codebases it becomes an issue