software engineer, contributing @amontlabs, prev. @primodiumgame.
Paris, France
Joined December 2021
- Tweets1.7K
- Following1K
- Followers1.2K
- Likes3.9K
I switched to T3 Code with Claude as my daily driver, so I ported lastdrop to it.
lastdrop gives Claude omp-like subagents ("reviewer", "advisor"…) on every other plan I pay for, as if they shipped with the harness:
- Claude calls them through its own Agent tool, the format it's trained on;
- same agents in the chat and in background tasks;
- each task takes the account with the most usage left.
Works with Claude app as well.
2
1
143
Free and open source, for macOS
github.com/amontlabs/lastdro…
41
You can do this with silo as well: github.com/amontlabs/silo.
You get both macos and linux computers for your agents, with builtin codex computer use, which until proven otherwise is the best computer use out there.
Still heavy wip and I’m working on a better app that silo will fold into tho.
@mdlahfir any benchmarks on how agent-desktop compares with codex cu?
if you're on a mac and want computer use without the agent touching your personal stuff, here's how i do it
run agent-desktop inside a macOS VM. Apple's Virtualization framework boots a full guest in a window, and the agent only sees what's inside it.
you keep working on your mac and your agents runs inside the VM
1
3
286
Use any model as a built-in subagent in Claude Code, with a subscription or API key.
Claude calls them like its native subagents, and lastdrop spreads usage across your accounts.
github.com/amontlabs/lastdro…
4
204
polarzero retweeted
I have decided to take the leap out of crypto and find a new job in AI
If you, or anyone you know, is hiring, I would love to chat!
let’s cook 🧑🍳
ps. I’m also open to crypto-related roles if they’re interesting
the cryptocurrency industry is now being handed over from the “builders” to the “caretakers”
that is, from the individuals who created and grew a multi-trillion dollar global industry to those who will maintain the industry as it is and work to achieve marginal future growth
I can guarantee you: there is life after crypto
Claude code is the best harness by far.
2 things I was missing I now have as mods built on top of the app:
- (a good) computer use: github.com/amontlabs/lcu
- subagents (from multiple claude subs and other providers): github.com/amontlabs/lastdro…
(slop motion showcases attached)
1
6
338
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
6
209
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
2
168
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
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
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
2
5
367
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
Installers are here: github.com/0xpolarzero/silo/…
I built this for myself, but if you end up using it, issues and PRs are welcome !
And if something feels worse than just doing it in a terminal, please tell me.
1
104
polarzero retweeted
zhipu absolutley nailing pursuing the element that played in oss models favour from the HF incident
masterclass in adpating goals and roadmaps to informatin as they come.
anthro and oai neuter you cause they believe humans are more bad than good and they need to control every outcome. kimi and zhipu are there to serve you cause they beleive the future is built toghther in the open and no one person or group can pursue that.
individualism and collectivism battling it out on the grand stage
Introducing GLM-5.3: Built to Code. Ready for Cyber Defense.
- Top-tier coding and agentic capabilities, achieved through post-training on the 743B base model
- A major leap in cybersecurity, setting a new standard among open models
Tech Blog: z.ai/blog/glm-5.3
