#computermath — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #computermath, aggregated by home.social.
-
New blog post: “The Hard Limits of AI“(quoting myself, from the article, slightly edited)
Seriously, we all need to just chill out and wasting money on these agentic AI loops to generate slop code. The invention of the LLM did not settle the question of whether or not all NP class problems are in the set of P class problems.
By all means, keep using your AI coding assistants to help you write software, if it makes you more productive. But you still need to provide a lot of guidance to the AI assistant to ensure the code that was written was correct. Don’t let it get into a loop trying to solve an NP-Complete coding challenge. And please, at least attempt to make it a little more efficient before you have other people start using it.
I wanted to write this article because of a discussion I had with my friends recently about how, in my experience, although AI coding assistants can write SQL code very well, they tend to have a lot of trouble crafting SQL schemas, because relational logic is a very hard thing to do for both computers and humans. And then I read this excellent article by Ed Zitron about people trying to solve these hard problems with “Agentic AI Loops”, that is, feeding LLM output into another LLM some number of times. So I want to explain why using Agentic Loops does not make hard problems easier to solve. In fact it is probably a bad idea to write large software applications with Agentic AI Loops, generally a very bad idea.
We are scheduled to discuss this article on the Lispy Gopher Climate podcast tomorrow.
(alternate link: https://ramin-honary.neocities.org/articles/the-hard-limits-of-ai)
#tech #AI #LLM #LLMs #ComplexityTheory #ComputerMath #Math #TuringComplete #NPComplete #LispyGopherClimate
-
New blog post: “The Hard Limits of AI“(quoting myself, from the article, slightly edited)
Seriously, we all need to just chill out and wasting money on these agentic AI loops to generate slop code. The invention of the LLM did not settle the question of whether or not all NP class problems are in the set of P class problems.
By all means, keep using your AI coding assistants to help you write software, if it makes you more productive. But you still need to provide a lot of guidance to the AI assistant to ensure the code that was written was correct. Don’t let it get into a loop trying to solve an NP-Complete coding challenge. And please, at least attempt to make it a little more efficient before you have other people start using it.
I wanted to write this article because of a discussion I had with my friends recently about how, in my experience, although AI coding assistants can write SQL code very well, they tend to have a lot of trouble crafting SQL schemas, because relational logic is a very hard thing to do for both computers and humans. And then I read this excellent article by Ed Zitron about people trying to solve these hard problems with “Agentic AI Loops”, that is, feeding LLM output into another LLM some number of times. So I want to explain why using Agentic Loops does not make hard problems easier to solve. In fact it is probably a bad idea to write large software applications with Agentic AI Loops, generally a very bad idea.
We are scheduled to discuss this article on the Lispy Gopher Climate podcast tomorrow.
(alternate link: https://ramin-honary.neocities.org/articles/the-hard-limits-of-ai)
#tech #AI #LLM #LLMs #ComplexityTheory #ComputerMath #Math #TuringComplete #NPComplete #LispyGopherClimate
-
Floating point numbers were a mistake.
https://wandering.shop/@aleen/112731112088617287 -
Floating point numbers were a mistake.
https://wandering.shop/@aleen/112731112088617287 -
NOT fun...but if you know and importantly understand why it is needed, you will always be ahead of the curve.
So, pay attention! 😜
