Just learning this AI thing. Building Prediction Machines, then bet against them. They're only somewhat right, which is still better than me.
Austin, TX
Joined November 2025
- Tweets508
- Following107
- Followers48
- Likes295
jake cukjati retweeted
112 agents, 16 hours, 60,000 lines of code. Jake Cukjati (@Byte0fCode) says stop prompting agents to code and hand them specs instead. #AIMUG youtube.com/watch?v=-65TrkDP…
jake cukjati retweeted
PSA: Don't forget that you only have another 2 days to claim this $250 credit for each of your Claude Max 20x subscription accounts.
If you have a bunch of accounts and don't log into the web app very often other than to swap accounts in Claude Code, it's easy to miss this.
You need to connect it to your GitHub account, which is very quick and easy if you're already logged into GitHub in the same browser. Then you just start a session, pick one of your repos, and give it a prompt to claim the credit.
If you're like me and don't even want to have to think much about this but want to make sure you get reasonably good utility out of your $250 credits, you can try this generic prompt that I've been using, shown below (adapted from a similar prompt I use with GPT Pro in the web app with the GitHub connector).
You can adapt it accordingly if you don't use beads or have a comprehensive plan document in the repo:
(also, another PSA: they gave everyone one banked reset per account that expires Oct 22 if you don't click the button in the "Usage" section in settings in the web app. But wait until you actually hit your weekly limit before clicking it, then do it right after that. Don't waste this potentially valuable reset!).
---
I have this now… can you work on it for me? Read the comprehensive plan and look at the beads first. Figure out the most momentous and critically important remaining gaps in features and functionality and focus on getting as much done of those things as possible in this session—not on minutiae or process/ceremony related tasks!!
Use GitHub to commit your changes directly to main (no PRs!!!!). Commit relatively frequently: don’t wait to do one big commit at the end, it’s too risky. But don’t commit absolutely trivial, tiny changes separately: wait until you have a meaningful commit.
And just keep going, being as useful as possible. Again, don’t focus on minutiae, focus on implementing the most critically important parts of the system that are incomplete! And commit directly to main using GitHub (I know for a fact that this works, just be persistent!).
jake cukjati retweeted
Also from AIMUG: @Byte0fCode's Forge with Rigor. Stop prompting agents to code, hand them specs, gate every step, and treat the harness as the asset. byteofcode.io/presentations/…
jake cukjati retweeted
6/ And Jake Cukjati (@Byte0fCode) on Forge with Rigor: specs are canonical, gate every stage, nothing certifies its own work, and give your skills CLIs. byteofcode.io/presentations/…
jake cukjati retweeted
No one buys new technical books nowadays, anyway, right? Get it for free here:
agent-flywheel.com/complete-…
jake cukjati retweeted
Uber publicó cómo armó su infraestructura de MCP y hay varias ideas muy buenas acá.
imaginate una empresa con miles de servicios internos y muchos equipos conectando agentes a esos sistemas por su cuenta.
cuando eso empieza a crecer, terminás con tooling fragmentado, infra duplicada, distintas formas de exponer tools y poca consistencia en seguridad, discovery y operación.
por eso Uber hizo un MCP Gateway: una capa central entre los agentes y sus servicios internos.
el agente habla MCP y el gateway se encarga de routing, permisos, ejecución y de traducir las llamadas a HTTP, gRPC o TChannel según corresponda.
como Uber ya tenía miles de APIs internas, también hicieron AutoCrawler: recorre sus definiciones, detecta métodos y schemas y genera MCP tools automáticamente. incluso usan un LLM para mejorar las descripciones.
hoy tienen +800 MCP servers y +5000 tools. y ahí aparece otro problema: no podés cargar todas esas definiciones en el contexto del modelo.
para eso crearon Omni MCP. en vez de pasarle miles de tools al agente, este va descubriendo qué server necesita, qué tools tiene disponibles, carga el schema de la correcta y recién ahí ejecuta.
me parece un muy buen ejemplo de cómo cambia la arquitectura cuando los agentes pasan de usar unas pocas tools a trabajar con miles.
terminás necesitando algo muy parecido a un API Gateway para agentes.
jake cukjati retweeted
begun, the clone war has
jk, I love openai and think more competition and validation is great for developers! (assuming the model is good - plz make it good!)
hopefully this is a sign for the future that building in a system one compatible way is the future
jake cukjati retweeted
We built Figma for hardware.
heypcb.ai/multiplayer
jake cukjati retweeted
If we really think English is the new programming language, why don't we get serious about it?
Set up a project, that's a bunch of markdown files in directories. Still have "functions" and "procedures", but have them all be written in English. Refer to other bits in other markdown files. Maybe using a bit of legalese-style wording. Eg. "human operator of the system (hereinafter referred as User)".
Then run an agent over the entire thing, and have it produce a finished artifact - codebase in some language or compiled, whatever. Record source-maps from markdown to the artifact, use them for cache busting later.
Then to modify stuff, instead of prompting, edit some of the markdown instructions. A dev server detects the changes, and instructs an agent to update the code and redeploys.
The funniest bit is, the IDE would be back in style. 😂