←back to thread

A PM's Guide to AI Agent Architecture

(www.productcurious.com)
205 points umangsehgal93 | 6 comments | 04 Sep 25 16:45 UTC | HN request time: 1s | source | bottom
Show context
ramesh31 ◴[04 Sep 25 18:14 UTC] No.45130377[source]▶
Stop trying to treat these things as more than they are. Stop trying to be clever. These models are the single most complex things ever created by humans; the summation of decades of research, trillions in capex, and the untold countless hours of thousands of people smarter than you and I. You will not meaningfully add to their capabilities with some hacked together reasoning workflows. Work within the confines of what they can actually do; anything else is complete delusion.
replies(2): >>45130538 #>>45131022 #
sixo ◴[04 Sep 25 19:07 UTC] No.45131022[source]▶
This is a nonsensical opinion by a person who doesn't know what they're talking about, and probably didn't read the article.

These models are tools, and LLM products bundles these tools with other tools, and 90% of UX amounts to bundling these well. The article here gives a great sense of what this takes.

replies(2): >>45131714 #>>45131742 #
CuriouslyC ◴[04 Sep 25 20:14 UTC] No.45131742[source]▶
The AI bundling problem is over. The user interface problem is over. You won't need a UI for your apps in a few years, agents are going to drive _EVERYTHING_. If you want a display for some data, the agent will slap together a dashboard on the fly from a composable UI library that's easy to work with, all hot loaded and live-revised based on your needs.
replies(5): >>45131916 #>>45131951 #>>45132407 #>>45132431 #>>45133170 #
1. ares623 ◴[04 Sep 25 22:53 UTC] No.45133170[source]▶
The Juicero moment for software
replies(1): >>45133292 #
2. CuriouslyC ◴[04 Sep 25 23:12 UTC] No.45133292[source]▶
Tell me you don't want to go hands free and have the star trek computer do everything for you. We could be there in ~5 years.
replies(2): >>45133400 #>>45135572 #
3. bopbopbop7 ◴[04 Sep 25 23:27 UTC] No.45133400[source]▶
We also could have warp drives next year!
replies(1): >>45133435 #
4. CuriouslyC ◴[04 Sep 25 23:34 UTC] No.45133435{3}[source]▶
Except that the main blocker on the star trek computer is the hooks we wire into the agent to manage the computer. Current gen models are almost smart enough, though their long context support and ability to use tools are a little shaky in general (I have walked a lot of agents through using tools, correct shell command use needs more RL for sure). None of this is outlandish advances, it's all just the natural progression of the track we're on.
replies(1): >>45133492 #
5. bopbopbop7 ◴[04 Sep 25 23:42 UTC] No.45133492{4}[source]▶
You’re either a decent troll, or absolutely delusional.
6. bluefirebrand ◴[05 Sep 25 06:34 UTC] No.45135572[source]▶
I genuinely do not want this, it sounds like shit