Comment by glennfiedler

13 days ago

Can't work on a single project, Amdahl's law gets you then. Try to work on as many different unrelated projects as possible, so I can get maximum throughput.

I break work up into four loose tiers:

1. flash - deepseek flash 4.1 / luna / haiku

2. pro - mercury 3 / terra / sonnet

3. heavy - opus 5.5 / sol

4. frontier - fable 5.1 / astra / argon

The decision of how to classify each piece of work is done by the coordinator (typically Opus 5.5...). If a card fails at a particular tier, it's going to get escalated up tiers until it gets sorted.

Each card has multiple readers (code review). I find mercury is very good at reading quickly. Deepseek as well. I will be honest, I think for 99% of stuff I need to do Opus 5.5 @ medium is ideal. I just use the additional models for different points of view, especially the absolute frontier models fable, astra, argon at max effort for security audits and code review.

What kind of "things" are you making? I can't process this much information, so I would inevitable be outsourcing most decision making. That could be fine for some products, but not for mine, where data model and RBAC model (among others) all require alignment between multiple stakeholders.

I have one agent and already find it quite intense to outsource code writing and basically just make and document decisions.

I feel like I could be rich working like you, I also feel like it is impossible for me to meet the needs of my clients if I'd work like this (so I can't be rich, it's a paradox). I wouldn't be able to answer their questions (without the active agent on-call, context window fully loaded), I wouldn't be able to explain just where the data model needs changing, or why some role really can't exist they way they envision etc, etc, etc.

I could of course branch the whole project and basically discuss multiple implementations during stakeholder meetings, but then still I'd need to explain the advantages/disadvantage of choosing one system over the other and guide them through it.

  • So, in essence, my added value is translating the vaque demands of my clients into as efficient as system as can be.

    Can the AI do it? Not yet I think. Maybe someday, for now I feel like clients of mine simply have the vocabulary, nor the mental models, to guide the LLMs. Ie, they have no idea of what one-to-many is, or why it's smart to put some information in separate tables, whereas some information is ok to filter row-based on a user attribute, etc.

    • I guess my trick is that mostly I'm my own customer. I'm a late stage career expert in netcode, so I pretty much have this long list of things I've been wanting to create for 20-30 years now... I'm still working through this, and each new thing I make, it creates 2-3 new ideas to explore! It's fun times :)

      4 replies →

The sort of work I pass through this system, it's mostly library work for multiplayer games.

For example, my work on schema, my protobufs/flatbuffers language replacement for multiplayer games, parallelizes very nicely across 15 languages on the sprint system. https://github.com/mas-bandwidth/schema.

See roadmap here: https://github.com/mas-bandwidth/schema/blob/main/ROADMAP.md

Very difficult to coordinate this amount of work in || without some sort of structured work system.

Even more AI coding work here if you are curious: https://patreon.com/masbandwidth

  • Thanks for sharing. Really interesting.

    At what point do you think you tip over from getting away with a handful of agents working on different things in one repo, to needing a comms/coordination system for your tasks?

    I think there must be a burden to run this and I'm guessing it only pays off when you get to some kind of scale. What is that scale? Other human team members? Sheer workload?

    • Great question. It's really the number of different things you are working on at the same time.

      Past a certain number of things, you can have a conversation with Claude in one session but even in Fable 5.1 or Opus 5.5 it's going to forget some and they just scroll out of context and get compacted away. Once enough things are in flight they start getting forgotten, or half-started, then the next thing is in flight and so on. When I start noticing this, I know it's time to switch over to the sprint system.

      The other thing is simply I want to go really wide and work on something and it's too slow when working with traditional child agents per-model. The LLMs generally won't "work to width" naturally (for whatever reason) and the sprint system is really good at pushing and ensuring that each model involved in the sprint not only works, but works at whatever particular width they are assigned (16, 32, 64 cards...) and stays working that way.

      If you work without a sprint system, you'll find yourself continually reminding the AIs manually "hey, can you please work to width?", "hey, you have 10 cards ready can you please work on them now?". These things are "squishy" when worked on in LLM space, they'll kinda do it, then a few hours later forget, and by morning they're puttering along at a few cards each.

      But by putting everything into mechanical structure (sprint system that drives all the LLMs via push notifications), they will more reliably remember to work at width, they will not forget anything they were assigned to work on (this is stored in redis cards, not in their memory that compacts), and the whole system can work much wider and you get done a lot faster!

      4 replies →

  • Thank you. Moo looks really cool.

    I did some prototype games, one thing that worked really well for me was having a deterministic replay system where the agents could drive the gamestate via recorded inputs. Kept me from having to do any playtesting or debugging in the main agentic loop.

  • Interesting. Are you also targeting WebTransport for both reliable and unreliable transport?

    • Yes! Once again, some drudgery that I'd rather not do in the past is pretty easy to implement with AI coding :)