software engineer, contributing @amontlabs, prev. @primodiumgame.
Paris, France
Joined December 2021
- Tweets1.7K
- Following1K
- Followers1.2K
- Likes3.9K
Thanks for answering. I'm not sure I recorded these benchmarks, these were vibed on a few samples and few iterations, just enough to get an idea. I was more expecting to see yours ahah
Last time I benchmarked cua was less accurate than codex computer use, is it not the case anymore? I even made a library for using codex cu inside other harnesses for this reason
We crossed 700 stars.
Keep the issues coming, and feel free to open a PR if you believe you have a useful feature or fix to contribute!
I extracted computer use from the ChatGPT app to plug it into any harness, because it's great.
Completely decoupled from ChatGPT auth and built-in browser. For macOS and Linux.
github.com/0xpolarzero/lcu
polarzero retweeted
Today, we are launching a preview of our new model, Mistral Large 4 (ML4), aka le Chonk 🐈.
ML4 is a 1T-parameter model with 49B active parameters, trained natively with multimodal capabilities.
It is at the frontier of open models, and by far the strongest open-weight model from the US or Europe.
The RL run behind this preview is still in flight and shows no sign of saturation -- we will release a final version before the end of the month along with the weights of the model.
🧵
1/n
Meet Mistral Large 4, aka Le Chonk.
• 1T parameters, natively multimodal. 49B active.
It is the best open weights model from US or Europe on aggregated benchmarks.
• State-of-the-art on critical workloads, including cyber defense, manufacturing and finance and it surpasses closed frontier models on visual grounding.
• Forged in Europe end-to-end and is deployable from Europe via our own Mistral Cloud infrastructure.
• Available to all via API today. Working with cybersecurity partners privately.
Open weights release end of October.
Btw with lcu you can get claude to control... claude.
Computer-use agents usually don't allow a harness to control itself but we do.
LCU now works properly with Claude Code (both app and CLI).
The first time Claude touches an app, you get an approval panel right in the session.
You can also review and edit your always-allowed apps with Touch ID, no Codex app needed.
github.com/amontlabs/lcu
First-class support for claude code now!
LCU now works properly with Claude Code (both app and CLI).
The first time Claude touches an app, you get an approval panel right in the session.
You can also review and edit your always-allowed apps with Touch ID, no Codex app needed.
github.com/amontlabs/lcu
LCU now works properly with Claude Code (both app and CLI).
The first time Claude touches an app, you get an approval panel right in the session.
You can also review and edit your always-allowed apps with Touch ID, no Codex app needed.
github.com/amontlabs/lcu
Extracted it so you can drop it into any harness github.com/0xpolarzero/lcu
I extracted computer use from the ChatGPT app to plug it into any harness, because it's great.
Completely decoupled from ChatGPT auth and built-in browser. For macOS and Linux.
github.com/0xpolarzero/lcu
It’s just a different default behavior, you have to prompt a bit more specific to get the same result as opus but it’s capable as well
You can now open SSH on a sandbox from Silo and connect from this machine or another.
Works with a terminal or an agent harness, against a local or remote VM.
github.com/0xpolarzero/silo/…
Silo: a native macOS/Linux app for sandboxes on your machine or remote ones. Powered by MicroSandbox.
Meant for letting agents run wild in isolated Linux VMs.
Open a workspace in your editor or terminal, forward ports, keep secrets on the host, scope GitHub access per sandbox, snapshot the environment.
github.com/0xpolarzero/silo