[dead]
Agent swarms and the new model economics
21–30 of 159 posts
Re: Agent swarms and the new model economics
#22I would have loved to see more of the harness engineering shared as code. Instead we are left with only the outcome. I guess that makes sense since the harness is the product in the case of Cursor.
I call this junk "meta-agentic engineering", it reminds me of people who have the coolest nvim configs, spend hundreds of hours customizing it but ultimately get less work done than the guy with minimal workflows, if any at all. I look on twitter and it's just people building tools for agents to use agents, some weird customization loop going on in the LLM space right now. Ultimately these are trends pushed on us fro…
Some of this stuff is ludicrous. I finally tried /loop last week and discovered every loop iteration passes the entire context history to the model. So pretty quickly you're running a full 1M context window, without cache, likely just to check if something is ready or needs to be done. It's miserably terrible engineering unless your entire and only goal is to burn tokens.
Re: Agent swarms and the new model economics
#23Earlier quoted context omitted.
I call this junk "meta-agentic engineering", it reminds me of people who have the coolest nvim configs, spend hundreds of hours customizing it but ultimately get less work done than the guy with minimal workflows, if any at all. I look on twitter and it's just people building tools for agents to use agents, some weird customization loop going on in the LLM space right now. Ultimately these are trends pushed on us fro…
Some of this stuff is ludicrous. I finally tried /loop last week and discovered every loop iteration passes the entire context history to the model. So pretty quickly you're running a full 1M context window, without cache, likely just to check if something is ready or needs to be done. It's miserably terrible engineering unless your entire and only goal is to burn tokens.
Wait, why isn't context cached with /loop?
Re: Agent swarms and the new model economics
#24How do we know if these models weren’t trained on Turso’s rewrite of SQLite in Rust?
It seems both likely that they were and impossible to remove that code from pretraining. Doesn’t that make this just about LLM memorization of the training set? What am I missing?
Re: Agent swarms and the new model economics
#25I find these blog posts (and the originals, with Anthropic's C compiler and Cursor's browser) somewhat funny, as if they have this enormous power to build ... but they can't build something unique or new. Like the software sucks, but look how powerful the process is (the models are indeed powerful). And it's a bit of a shame: by virtue of their position (their embedding in the fabric of venture capitalism), it seems…
Yes, that's true, but in the post, they even mention that building the spec is the scarce resource. For that to work, the swarm has to actually follow the spec, which is what much of this post is about. We gave the swarm 835 pages of prose and it came back with a database. What was scarce in this experiment, and what we expect to be scarce in software engineering going forward, is the right description of intent.
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.
Re: Agent swarms and the new model economics
#26Earlier quoted context omitted.
Yes, that's true, but in the post, they even mention that building the spec is the scarce resource. For that to work, the swarm has to actually follow the spec, which is what much of this post is about. We gave the swarm 835 pages of prose and it came back with a database. What was scarce in this experiment, and what we expect to be scarce in software engineering going forward, is the right description of intent.
I mean, how long are these pages? Assuming 40 or so lines per page, that would be 33400 lines of spec turned into 200,000 lines of Rust, or about 6 lines of code per line of spec. That's a very detailed spec, much more than any software specification I have ever written in my career. It's not obvious to me that writing this spec would meaningfully save work over incrementally building individual features, especially…
Or to validate the accuracy and efficacy of the actual code produced.
Re: Agent swarms and the new model economics
#27[dead]
Re: Agent swarms and the new model economics
#28How do we know if these models weren’t trained on Turso’s rewrite of SQLite in Rust? It seems both likely that they were and impossible to remove that code from pretraining. Doesn’t that make this just about LLM memorization of the training set? What am I missing?
This is more about automated long horizon work.
Re: Agent swarms and the new model economics
#29Earlier quoted context omitted.
Yes, that's true, but in the post, they even mention that building the spec is the scarce resource. For that to work, the swarm has to actually follow the spec, which is what much of this post is about. We gave the swarm 835 pages of prose and it came back with a database. What was scarce in this experiment, and what we expect to be scarce in software engineering going forward, is the right description of intent.
I mean, how long are these pages? Assuming 40 or so lines per page, that would be 33400 lines of spec turned into 200,000 lines of Rust, or about 6 lines of code per line of spec. That's a very detailed spec, much more than any software specification I have ever written in my career. It's not obvious to me that writing this spec would meaningfully save work over incrementally building individual features, especially…
not only that, but what all of this misses is the fact that the specification that they used was a product of writing the software, not the other way round. It would be much, much more difficult to first write a correct specification than to first write a correct program, because programs are formal systems that can be executed to observe their correctness. You can’t do that with a specification.
Re: Agent swarms and the new model economics
#30>The browser swarm from earlier this year peaked at roughly 1,000 commits per hour on Git. The new system peaks at around 1,000 commits per second. >To facilitate this rate of activity, we built a new version control system (VCS) from scratch. Throughput was not the only reason to own this layer. Every change in the system passes through the VCS, so it is where collisions first become visible, and several of the coor…
It's hard not read such quotes and immediately think of the Infinite Monkey Theorem. https://en.wikipedia.org/wiki/Infinite_monkey_theorem
If at the end Shakespeare-level literature is produced, does it matter whether we arrived there by random keystrokes?