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

Agent swarms and the new model economics

cursor.com

Post reply on HN
Print view View original

91–100 of 159 posts

Re: Agent swarms and the new model economics

#91

Post by viccis »

chrisweekly wrote: post #54
viccis wrote: post #25

Earlier quoted context omitted.

We're rediscovering the "architect" job role a decade or so after switching to agile processes and staff engineers largely replaced it. God help us when they rediscover UML for agents.

I feel like the scarcity of (idealized) Product Managers is even more acute.

Easily the biggest delta between a good one and a bad one I've ever encountered. It's so easy to test too. Just ask a product manager if they can give a talk on in 2 hours. If they respond by slacking all of the engineers that work under them to stop what they're doing and give them the info to give that talk, fire them. If they are ready to talk right now then give them a raise.

Re: Agent swarms and the new model economics

#92

Post by gritzko »

wordpad wrote: post #90
sawyers wrote: post #87

Earlier quoted context omitted.

People often think of tech/business as bottleneck issues ie whats my limiting factor. That's relevant to pre-ai business as humans are relatively self organizing. The issue with AI is it has no real memory, context, long term reasoning, etc. These are a lot of what we use to determine how well we're doing something as well as why. The "bottleneck" so to speak with ai is that it will just circularly build junk forever…

But that's mostly just vanilla models. Some critical parts of agentic development are literally months old while most mature ones are merely a couple years old. Critical thinking was the most critical checkpoint for models to reach. Now its only a matter of time for the right tooling and orchestration to come along. Once agent memory and recall works well, all of those bottlenecks will go away one by one.

Back in my early career days, CPUs were clocked at 1GHz. That was 20-25 years ago.

Re: Agent swarms and the new model economics

#94

Post by solumunus »

thewhitetulip wrote: post #79
jnwatson wrote: post #68

Earlier quoted context omitted.

They've said for some time that Claude Code is 90% LLM generated code.

Yeah and it's still a cli tool running on JS So it's not a brag They could just write in Rust directly can't they? If they do that then they're doing what they preach

My app is written in TypeScript. With agents I could rewrite it in Rust, I just don’t need to so I don’t. It doesn’t warrant that level of performance and the business logic is more digestible in its current form. Given the amount of reviewing I need to do now, readability is worth more than performance. There are always tradeoffs.

Are you implying that them attempting a Rust rewrite would fail, and this is why they’re not doing it?

Re: Agent swarms and the new model economics

#95

Post by edg5000 »

I initially thought that getting agents to work for longer and in large groups was the future, but I'm increasingly thinking that, at least for engineering, just one thread makes more sense. The agent pulls things into context as needed. One thing that I've been experimenting with is also letting the agent remove things from context, such as files. But just adding to the context and compacting when it's full seems like it might beat a lot of more advanced options. Because the model is good, it knows what to put in the summary; just enough for the model to be able to rebuild the context from that seed (e.g. pulling in relevant files/data into the context).

Re: Agent swarms and the new model economics

#96

Post by attentive »

solumunus wrote: post #94
thewhitetulip wrote: post #79

Earlier quoted context omitted.

Yeah and it's still a cli tool running on JS So it's not a brag They could just write in Rust directly can't they? If they do that then they're doing what they preach

My app is written in TypeScript. With agents I could rewrite it in Rust, I just don’t need to so I don’t. It doesn’t warrant that level of performance and the business logic is more digestible in its current form. Given the amount of reviewing I need to do now, readability is worth more than performance. There are always tradeoffs. Are you implying that them attempting a Rust rewrite would fail, and this is why they’…

claude code VSS - 70Gb

codex VSS - 600Mb

Re: Agent swarms and the new model economics

#97

Post by NitpickLawyer »

mrtesthah wrote: post #84
wrs wrote: post #45

Earlier quoted context omitted.

Then you would expect the implementation to be structured the same as SQLite, and having glanced at the result, it looks like at least some things aren't. For example, it seems to use an operator-tree executor rather than SQLite's bytecode interpreter.

To test this hypothesis you would need to look at the initial version before subsequent agents started refactoring it.

Why tho? The whole point of agentic is that it takes several passes to get to a result. If step a) is a non-idiomatic transpile, but step b) c) and ... z) make it idiomatic and performant and efficient, why look at step a)? That was just the beginning. The idea with "agents" and "swarms" and dynamic this and that is that you only look at the last step.

This strictly follows the early agentic usage, where people were complaining of code full of errors and such. But having the loop do plan-write-verify is the thing that got us from that state to today. And it works. If you look at the code and it has errors (linting, etc) then your loop is not properly setup. You should only be called upon when all that can and should pass does. Your role is "direction/taste/human-common-sense-at-a-glance".

Re: Agent swarms and the new model economics

#98

Post by gritzko »

anthonypasq wrote: post #4

Love to see these crazy kinds of experiments going on. Even if this doesn't 100% work or is prohibitively expensive for now, these are glimpses into the future in the same way people were talking about coding agents in 2023 when we just had tab complete.

I am afraid the folks are still busy playing with familiar toys. "Let's extract more code out of LLM's inner layers!" SQLite we already have. That's where their "spec" came from.

The interesting frontier is elsewhere: how to fit it into the pipeline to build new useful things. I felt motivated enough to write a follow-up/reply post http://replicated.live/blog/follow-up

Re: Agent swarms and the new model economics

#99

Post by asim »

Anything architectural like this is super interesting. We keep getting more powerful models sure. We're getting agents ok. But this coordination of many agents. This is the part that's really going to scale very fast and across many many machines in parallel. Very cool.

Re: Agent swarms and the new model economics

#100

Post by kgeist »

wrs wrote: post #45
kgeist wrote: post #31

Earlier quoted context omitted.

Even if no Rust code for it was seen during training, an LLM can trivially transpile SQLite's C codebase to Rust on the fly. For example, I just asked ChatGPT to write John Carmack's famous Fast Inverse Square Root algorithm in Erlang, without searching online or thinking, and it transpiled it immediately (while also extracting the knowledge in the same step). SQLite's semantics/code are stored in the middle layers o…

Then you would expect the implementation to be structured the same as SQLite, and having glanced at the result, it looks like at least some things aren't. For example, it seems to use an operator-tree executor rather than SQLite's bytecode interpreter.

The knowledge is lossy, and code generation itself is non-deterministic (temperature), so the operator-tree executor must be interference from other DB implementations, because it's uncommon to have a bytecode interpreter
Post reply on HN