←back to thread

The AI Investment Boom

(www.apricitas.io)
271 points m-hodges | 7 comments | | HN request time: 0.407s | source | bottom
Show context
apwell23 ◴[] No.41896263[source]
> AI products are used ubiquitously to generate code, text, and images, analyze data, automate tasks, enhance online platforms, and much, much, much more—with usage expected only to increase going forward.

Why does every hype article start with this. Personally my copilot usage has gone down while coding. I tried and tried but it always gets lost and starts spitting out subtle bugs that takes me more time to debug than if i had written it myself.

I always have this feeling of 'this might fail in production in unknown ways' because i might have missed checking the code throughly . I know i am not the only one, my coworkers and friends have expressed similar feelings.

I even tried the new 'chain of thought' model, which for some reason seems to be even worse.

replies(10): >>41896295 #>>41896310 #>>41896325 #>>41896327 #>>41896363 #>>41896380 #>>41896400 #>>41896497 #>>41896670 #>>41898703 #
bongodongobob ◴[] No.41896295[source]
Well I have the exact opposite experience. I don't know why people struggle to get good results with llms.
replies(4): >>41896332 #>>41896335 #>>41896492 #>>41897988 #
1. threeseed ◴[] No.41897988[source]
I just asked Claude to generate some code using the SAP SuccessFactors API.

Every single example was completely useless. The code wouldn't compile, it would invent methods and variables and the instructions to go along with it were incoherent. All whilst gaslighting along with the way.

I have also previously tried using it with some Golang code and it would constantly add weird statements e.g. locking on non-concurrent operations.

LLMs are great when you are doing the same things as everyone else. Step outside of that and it's far more trouble than it's worth.

replies(2): >>41900666 #>>41900693 #
2. dankwizard ◴[] No.41900666[source]
"LLMs are great when you are doing the same things as everyone else. Step outside of that and it's far more trouble than it's worth."

If you're doing something in a way it's not in the training data set, maybe your way of approaching the problem is wrong?

replies(2): >>41902364 #>>41904523 #
3. attentive ◴[] No.41900693[source]
for obscure API or SDK, upload docs and/or examples to Claude projects.
replies(1): >>41904540 #
4. threeseed ◴[] No.41902364[source]
Sorry but some of us aren't building the ten millionth CRUD app.

SuccessFactors is a popular HR platform and I was asking it any question and getting the wrong answer every time.

5. johnnyanmac ◴[] No.41904523[source]
>If you're doing something in a way it's not in the training data set

in my industry, the "training data set" won't get much farther from public code than the barebones, generated doxygen comments we call "documentation".

But in a way you're also right. The industry's approach is fundamentally wrong, making 20 solutions to a problem with plenty of room to standardize a proper approach (plenty of room where you need proprietary techniques, but that's getting less true by the month). But an LLM isn't going to fix that cultural issue and will suffer from it.

replies(1): >>41905978 #
6. johnnyanmac ◴[] No.41904540[source]
That sounds like you might potentially break some copyright of your tools. Not all our tools are FOSS (and even some FOSS licenses may not allow that).
7. warkdarrior ◴[] No.41905978{3}[source]
> The industry's approach is fundamentally wrong, making 20 solutions to a problem with plenty of room to standardize a proper approach [...]. But an LLM isn't going to fix that cultural issue and will suffer from it.

LLM-powered development may push the industry towards standardization. "Oh, CoPilot cannot generate proper code for your SDK/API/service? Sorry, all my developers use CoPilot, so we will not integrate with your SDK/API/service until you provide better, CoPilot-friendly docs and examples."