Still limited by compute, so I built a thing that runs codex in the cloud, powered by @Cloudflare firecracker boxes (and since that's not beefy enough for larger projects, tests are run via crabbox) Uses Ghostty ofc, via WebAssembly.
Codex replicated itself, basically.
COMPUTING
-
Cloud codex runner using Cloudflare Firecracker and Ghostty
By
–
-
Get a fourth RTX PRO 6000 to enable TP=4 flexibility
By
–
Get a fourth RTX PRO 6000 so you can run TP=4, you’ll have a lot more options and flexibility that way
-
No staging, live production builds on VPS, Claude Code only failed twice
By
–
Every bug fix or new feature on any of my sites I now built live on my VPS, in production, without any staging Claude Code only failed me 2x in 12 months, it made a small bug and the site was down for 2x 5 seconds It never lost any data I also have 3-2-1 Backup strategy, with
-
Opensource AI Will Win: A Memo on Sovereign Intelligence
By
–
MEMO INCOMING re: Sovereign Intelligence Opensource AI WILL WIN
-
Discover Sana: a new GitHub repo for machine learning by NVlabs
By
–
repo → https://
github.com/NVlabs/Sana -
NVIDIA’s SANA-WM: Open-Source World Model for Controllable Video on Gaming PCs
By
–
NVIDIA JUST DROPPED AN OPEN-SOURCE WORLD MODEL THAT RUNS ON YOUR GAMING PC 🤯
— Charly Wargnier (@DataChaz) 23 mai 2026
Instead of melting your GPU, @NVIDIAAI’s new 2.6B-parameter model, SANA-WM, brings 60 seconds of controllable video straight to your laptop.
> Just feed it an image
> a prompt
> a camera path
.. and… pic.twitter.com/zR1eva7YPpNVIDIA JUST DROPPED AN OPEN-SOURCE WORLD MODEL THAT RUNS ON YOUR GAMING PC Instead of melting your GPU, @NVIDIAAI
’s new 2.6B-parameter model, SANA-WM, brings 60 seconds of controllable video straight to your laptop. > Just feed it an image
> a prompt
> a camera path .. and -
Run local air-gapped models to avoid data center risks
By
–
Bruh, just run the model locally in an air-gapped server access w/ those Chinese models and you'll be fine since there is no internet connection Sending your life to a data center that someone controls IS NOT okay
-
Free online LLM bible: Understand ChatGPT, run models at home, future AI careers
By
–
DROP EVERYTHING The bible for how LLMs work is now available online to read FOR FREE This is for you if you: – Want to run these LLMs at home on your hardware?
– Want to understand how ChatGPT works?
– Want to work at an AI Lab in the future? Covers all the concepts from -
Anthropic engineers’ token-saving habits, no setting changes needed
By
–
this guy literally breaks down the exact habits Anthropic engineers use to save millions of tokens without changing a single setting 🤯
— Charly Wargnier (@DataChaz) 22 mai 2026
Watch the video, then bookmark the written guide 👇 https://t.co/gAHjGmFxwy pic.twitter.com/Hlb96srixBthis guy literally breaks down the exact habits Anthropic engineers use to save millions of tokens without changing a single setting Watch the video, then bookmark the written guide
-
Claude MD File: Top GitHub Repo Uses Karpathy’s 4 LLM Principles for AI Control
By
–
DID YOU KNOW THE #1 GITHUB TRENDING REPO (146K+ STARS) IS LITERALLY JUST A CLAUDE MD FILE? It uses @karpathy
's 4 LLM principles to keep AI in check: → Seek clarity: Always ask before making assumptions.
→ Stay minimal: Avoid bloat and keep things simple.
→ Edit