←back to thread

AI 2027

(ai-2027.com)
949 points Tenoke | 3 comments | 03 Apr 25 16:13 UTC | HN request time: 0.678s | source
Show context
amarcheschi ◴[03 Apr 25 17:15 UTC] No.43572698[source]▶
I just spent some time trying to make claude and gemini make a violin plot of some polar dataframe. I've never used it and it's just for prototyping so i just went "apply a log to the values and make a violin plot of this polars dataframe". ANd had to iterate with them for 4/5 times each. Gemini got it right but then used deprecated methods

I might be doing llm wrong, but i just can't get how people might actually do something not trivial just by vibe coding. And it's not like i'm an old fart either, i'm a university student

replies(5): >>43572975 #>>43573061 #>>43573105 #>>43573520 #>>43576238 #
hiq ◴[03 Apr 25 18:26 UTC] No.43573520[source]▶
> had to iterate with them for 4/5 times each. Gemini got it right but then used deprecated methods

How hard would it be to automate these iterations?

How hard would it be to automatically check and improve the code to avoid deprecated methods?

I agree that most products are still underwhelming, but that doesn't mean that the underlying tech is not already enough to deliver better LLM-based products. Lately I've been using LLMs more and more to get started with writing tests on components I'm not familiar with, it really helps.

replies(3): >>43575091 #>>43575868 #>>43576566 #
1. henryjcee ◴[03 Apr 25 20:39 UTC] No.43575091[source]▶
> How hard would it be to automate these iterations?

The fact that we're no closer to doing this than we were when chatgpt launched suggests that it's really hard. If anything I think it's _the_ hard bit vs. building something that generates plausible text.

Solving this for the general case is imo a completely different problem to being able to generate plausible text in the general case.

replies(1): >>43575200 #
2. HDThoreaun ◴[03 Apr 25 20:49 UTC] No.43575200[source]▶
This is not true. The chain of logic models are able to check their work and try again given enough compute.
replies(1): >>43575937 #
3. lelandbatey ◴[03 Apr 25 21:53 UTC] No.43575937[source]▶
They can check their work and try again an infinite number of times, but the rate at which they succeed seems to just get worse and worse the further from the beaten path (of existing code from existing solutions) that they stray.