Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Throw more AI at your problems

frontierai.substack.com

Post reply on HN
Print view View original

11–20 of 59 posts

Re: Throw more AI at your problems

#11

Post by ToucanLoucan »

crooked-v wrote: post #3

With the current state of "AI", this strikes me as a "I had a problem and used AI, now I have two problems" kind of situation in most cases.

All the snark contained within aside, I'm reminded of that ranting blog post from the person sick of AI that made the rounds a little ways back, which had one huge, cogent point within: that the same companies that can barely manage to ship and maintain their current software are not magically going to overcome that organizational problem set by virtue of using LLMs. Once they add that in, then they're just going to have late-released, poorly made software that happens to have an LLM in it somewhere.

Re: Throw more AI at your problems

#12

Post by cyrillite »

headcanon wrote: post #2

I'll stay out of the inevitable "You're just adding a band aid! What are you really trying to do?" discussion since I kind of see the author's point and I'm generally excited about applying LLMs and ML at more tasks. One thing I've been thinking about is if an agent (or collection of agents) can solve a problem initially in a non-scalable way through raw inference, but then develop code to make parts of the solution…

Well, the standard advice for getting off the ground with most endeavours is “Do things that don’t scale”. Obviously scaling is nice, but sometimes it’s cheaper and faster to brute force it and worry about the rest later.

The unscalable thing is often like “buy it cheap, buy it twice” but it’s also often like “buy it cheap, only fix it if you use it enough that it becomes unsuitable”. Makers endorse both attitudes. Knowing when which applies is the challenging bit

Re: Throw more AI at your problems

#13

Post by simonw »

l5870uoo9y wrote: post #5

RAG doesn’t necessarily give the best results. Essentially it is a technically elegant way to semantic context to the prompt (for many use cases it is over-engineered). I used to offer RAG SQL query generations on SQLAI.ai and while I might introduce it again, for most use cases it was overkill and even made working with the SQL generator unpredictable. Instead I implemented low tech “RAG” or “data source rules”. It’…

What do you mean by "RAG SQL query generations"? Were you searching for example queries similar to the questions the user's asked and injecting those examples into the prompt?

Re: Throw more AI at your problems

#15

Post by pqdbr »

glial wrote: post #14
hggigg wrote: post #8

I wish this was funny but it’s not. We are doing this now. It has become like “because it’s got electrolytes” in our org.

Well, at least it's not blockchain or Kubernetes.

The blockchain hype train was ridiculous. Textbook "solution looking for a problem" that every consultant was trying to push to every org, which had to jump onboard simply because of FOMO.

Re: Throw more AI at your problems

#16

Post by WesleyLivesay »

ToucanLoucan wrote: post #11
crooked-v wrote: post #3

With the current state of "AI", this strikes me as a "I had a problem and used AI, now I have two problems" kind of situation in most cases.

All the snark contained within aside, I'm reminded of that ranting blog post from the person sick of AI that made the rounds a little ways back, which had one huge, cogent point within: that the same companies that can barely manage to ship and maintain their current software are not magically going to overcome that organizational problem set by virtue of using LLMs. Once they add that in, then they're just going to…

I believe you mean this one: https://ludic.mataroa.blog/blog/i-will-fucking-piledrive-you...

Re: Throw more AI at your problems

#17

Post by fluoridation »

pqdbr wrote: post #15
glial wrote: post #14

Earlier quoted context omitted.

Well, at least it's not blockchain or Kubernetes.

The blockchain hype train was ridiculous. Textbook "solution looking for a problem" that every consultant was trying to push to every org, which had to jump onboard simply because of FOMO.

I don't think that's quite right. It was businesses who were jumping at consultants to see how they stuff a blockchain into their pipeline to do the same thing they were already doing, all so they could put "now with blockchain!" on the website.

Re: Throw more AI at your problems

#18

Post by pizza »

keeganpoppen wrote: post #7

YES (although i'm hesitant to even say anything because on some level this is tightly-guarded personal proprietary knowledge from the trenches that i hold quite dear). why aren't you spinning off like 100 prompts from one input? it works great in a LOT of situations. better than you think it does/would, no matter your estimation of its efficacy.

100 prompts doing what? Something like more selective, focused extraction of structured fields?

Re: Throw more AI at your problems

#20

Post by pizza »

TZubiri wrote: post #6
Stoids wrote: post #4

We aren’t good at creating software systems from reliable and knowable components. A bit skeptical that the future of software is making a Rube Goldberg machine of black box inter-LLM communication.

I'm pretty sure this is a satire post

Here's a practical in this vein but much simpler - if you're trying to answer a question with an LLM, and have it answer in json format within the same prompt, for many models the accuracy is worse than just having it answer in plaintext. The reason is that you're now having to place a bet that the distribution of json strings it's seen before meshes nicely with the distribution of answers to that question.

So one remedy is to have it just answer in plaintext, and then use a second, more specialized model that's specifically trained to turn plaintext into json. Whether this chain of models works better than just having one model all depends on the distribution match penalties accrued along the chain in between.

Post reply on HN