dev | prev appl, amzn
Joined January 2022
- Tweets10.9K
- Following1.7K
- Followers2.1K
- Likes17.9K
Looking for my next full-stack role -> lucas.website
Experience working with multiple Web3 companies, Apple, Amazon, and doing agency work.
I've shipped and scaled production apps from first prototypes to thousands of users across various stacks.
Have experience using the latest AI tools and setting up AI workflows and pipelines.
Bonus: I can still manually read/write code
Before Apple, worked at Amazon Game Studios on their first AAA console shooter. I was in charge of the in game voice chat, in game notifications/hud, and some matchmaking and leaderboard features on the menu. The game has since been taken off Steam but here's a demo.
youtube.com/watch?v=iglHfEpz…
qudo retweeted
inspired by pixel-agent, i built a pixel agent factory 🏭
you hire pixel coworkers with distinct roles and skills, give them scoped tasks, and see what the office is waiting on.
the factory lets you:
- run multiple tasks in parallel, with capacity and queueing visible
- hire coworkers with role-specific skills
- assign work to local or remote execution environments
- review plans and decisions before work starts
- track task ownership, saved session history, and employee requests
- get notified when an employee needs a decision, verification, or your input
- use existing Claude or Codex accounts
- keep the actual coding-agent terminal separate from the game-like office UI
- pet and feed the office cat 😼
the goal is to make running coding agents feel more like managing a small studio than juggling tabs.
Browserless
Introducing Kitesurf: a browser built for agents, running entirely on Cloudflare Workers.
Chromium is too heavy to hand every agent one. Kitesurf is written in Rust, uses 3-7x less CPU and memory, and spins up per request.
Free in beta: blog.cloudflare.com/kitesurf…
Y’all got your feathers in a twist about Fable drama while me and the homies have been over here on GLM
A $20 Droid sub has replaced my $100 Claude sub.
Droid + Kimi is crazy. Canceled Claude a month ago and haven’t looked back. I produce a lot more reliable and predictable code with Droid, it scales well on big code bases and is good at picking up where you left off. It also connects to local models and works awesome, so I can setup Droid missions that are a combo of cloud models for orchestration/planning and local models for building.
Claude starts form 0 each session, you’re constantly re explaining things to it, it feels like a lottery for what comes out the other end and each time you prompt you pray it finds the right CLUADE files so you don’t have to manually tell it about them.
qudo retweeted
I can't believe this is real
I have GLM 5.2 running 100% locally on my Mac Studio. 2 bit quant.
The results I'm getting are better than Opus 4.8
It's now powering my Hermes Agent and Codex. 100% free, local, private super intelligence on my desk
I also have it in a loop coding for me 24/7 now
I thought we were at least a year away from this type of event. It happened today.
The model takes up about 250gb of memory. So you can technically run it on a Mac Studio with 256gb, but you probably want the 512gb memory version (please tell me you listened to me 5 months ago when these were sitting on store shelves)
With Fable gone, I now have Opus 4.8 level intelligence on my desk for free. This is the future.
Local, private, secure, personal super intelligence.
If you're still writing off local AI as a fad or engagement bait, you are officially delusional
