Supreme Leader Wiggum

If I were to stream… and it was mostly just me doing my day to day work, while talking to chat, would anyone watch? Setup isn’t going to be anything stellar, no real agenda - I’d pretty much just go do stuff across 5 or 6 repos in parallel & talk through what I’m thinking

Always bet on Chad Xi

@cryptopunk7213 doesn't take much to beat claude

1. theres no way this beats opus 4.6 2. wtf is this chart crime??? 😂

I use codex app-server protocol for many things, have custom versions of codex as well. adding chat api support into the rust code cause too many rebase conflicts with upstream so its easier to just create responses api proxy for for chat endpoints. Codex subagent architecture is hard to beat imo

@ScriptedAlchemy What is the point ? The oficial apps are best to use with the models that they try to fine tune for them. You have Open Code and other open source harners if you want to use other models

Wrote a small proxy that converts the chat api into the responses api shape for codex. So you can use chat/completions model with codex, most features supported. Sessions is stored and encrypted in the database so that responses api can support retrieving conversations. chat-response.federation.workers.dev If you lose your ID, you lose all the chats in the database. I do not store any api keys etc. I only probe the model to see what features it supports to configure your endpoint, after that its passthrough.

@Yuval_Shimoni @elliot_braem Like how we say “continue” , I say “helm”

My plan format is copy past of cursors. So interchangeable. Enforcing it I just run subagent graph skill. Then after that I’ll just say “helm” which helm mentions subagent graph skill so helming will make it switch to subagent graph mode. So as it’s working I’ll just say helm occasionally

This is what the inventor of Module Federation is doing:

Yes but all interconnected. One designed for writing the plan files or tracking existing ones. The other is for subagent management. Plan graph skill like cursors plan mode, or if I pass it one of cursors plan files, it’ll parse and use that or break it up into mini plan per todo or phase etc. ultimately it’s designed to be like “how can I do this work in parallel with many agents without collision and without agent getting lazy on big work”

like i can just start with subagent graph skill, and then itll just helm a bunch of subagents to do the work. if i want more robust then i can use plan graph which makes the mini plans, then plan frontier finds then next series of parallel work that can be done and subagent graph then manages and launches the subagents according to the DAG. Helm steers them and watches for conflicting directions and bascially acts as me, but for the subagents its managing. For complex ones ill have the subagents become helms for their own subagent graphs. Graph Helm Agent->Graph Helm Agent-> Subagent workers being helmed

@Yuval_Shimoni @elliot_braem they are interconnected so you can call any skill and itll activate the other skill, dont always have to plan, but usually i start with that.

they all work on the same task / plan, in the same branch. Its about breaking the work down into enough independent lanes that the request can be delivered faster and larger requests can be one-shotted that might take a few days to build out. usually ill do one pr, if its large i have separate agents and skills designed for restacking a pr into a stacked pr. Mostly its about doing more work faster with less babysitting.

@ScriptedAlchemy @elliot_braem How does you execute so many in parallel? Each one create pr or it will create one pr quickly? How do you review it?

@Yuval_Shimoni @elliot_braem Cursor also limits subagent concurrency to 4. Typically I have 50 concurrent agents

@ScriptedAlchemy @elliot_braem Maybe with Composer 2 you can execute in Cursor as well 🙃

@Yuval_Shimoni @elliot_braem It’s a cost issue. Billions of tokens a day.

@MoonliteTechLLC @astrodotbuild All good! Astro islands are really great, but not necessarily great for the business needs at ByteDance scale. We have problems most others will never experience. RSPack and federation are more business tools than devtools.

@ScriptedAlchemy @astrodotbuild having a chuckle I recommended astro to the dev that wrote module federation... note to self, read bio!

Its official. Im giving up on nextjs & module federation webpack plugin. Deleted the package, writing new version of package for rspack only

@MoonliteTechLLC @astrodotbuild 🫶 federation solves a problem I hope you don’t have. But if you do, someone needs to serve that need!

@ScriptedAlchemy @astrodotbuild lol just read your bio, nm :D

@MoonliteTechLLC @astrodotbuild Also few micro solutions are capable of tree shaking shared code dynamically.

@ScriptedAlchemy @astrodotbuild number of modules scale or serving concurrent users scale?

Both. We have over 1000 apps, 20000 repos, billions of users. Federation was intended for large scale business challenges. There’s many micro solutions for smaller scale. Most micro solutions only think about frontend. Federation works in native apps, game consoles, backend services, and frontend. I’ve seen drones get OTA updates mid flight. You probably noticed game consoles have fewer updates that cause system reboot, that’s because they are delivering updates via federation.

@MoonliteTechLLC @astrodotbuild 200? lol. Try 9000

@ScriptedAlchemy Just use @astrodotbuild man... the js islands are great. unless you are building some huge interface with 200 micro modules you want to mix and match at run time I don't see the point of module federation anymore.

@kenwheeler Bruh

i keep that mf thang on me