software engineer, contributing @amontlabs, prev. @primodiumgame.
Paris, France
Joined December 2021
- Tweets1.7K
- Following1K
- Followers1.2K
- Likes3.9K
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
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.
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
polarzero retweeted
Only Smithers supports this feature: Time Travel
No other orchestration framework is built from ground up to be this observable debuggable and durable while supporting multiple providers
1. Smithers saves "frames" to sqlite everytime updates happen
2. JJ snapshots the state of the file system every frame
3. The frame provides perfect visibility into what smithers is doing and why
4. You as the user can time travel back to any frame at any time reverting botht he file system and the state of smithers to that frame
polarzero retweeted
Has been a while since I wrote about agentic engineering, so this time around some learnings of maintaining Pi as a junior maintainer to @badlogicgames :) lucumr.pocoo.org/2026/5/24/p…
polarzero retweeted
The bun rewrite is some of the most impressive harness engineering I've seen. @jarredsumner basically first invented his own minimal version of Smithers and then thoughtfully created what is a high quality zig to rust compiler utilizing llms
Since it's one of the best examples of building a long running workflow I have seen I am busy porting it to using Smithers directly as a demo
polarzero retweeted
Best uses of smithers so far
- Burns — Workspace-first local control plane for authoring, running, and supervising Smithers workflows (web/desktop/CLI)
github.com/l3wi/burns
- Ralphinho — Multi-agent dev workflows that turn RFCs into landed code and automate code review
github.com/enitrat/ralphinho
- Cairo Coder — AI-powered Cairo smart contract generator using a RAG pipeline with Smithers orchestration
github.com/KasarLabs/cairo-c…
- Agentix — Opinionated RFC-to-production workflow orchestrator with DDD/BDD/TDD and merge queues
github.com/AbdelStark/agenti…
- Era — Generic reusable multi-phase dev workflow engine (research → plan → implement → test → review)
github.com/ClementWalter/era
- Local Isolated Ralph — Kubernetes-native runner for Smithers workflows as isolated K8s Jobs/CronJobs
github.com/SamuelLHuber/loca…
polarzero retweeted
It sounds so gimmicky
AI Orchestration framework via React
But hear me out, Smithers is secretly the best-in-class agentic orchestration framework
In this 🧵 I answer two questions
1. Why you even need an orchestration framework?
2. Why that orchestration framework should be smithers
🧵 1/18
polarzero retweeted
You should use Voltaire over alternatives because I love zig and learned what good zig looks like
This alternative zig library screenshotted below lists "comptime-first" as a reason to use their library over alternatives like Voltaire.
comptimeSelector("transfer(address,uint256)");
This is a bad practice in zig. Libraries should not declare library functions as comptime. Why? Because any function can be used in comptime or runtime using comptime keyword
comptime selector("transfer(address,uint256)");
Also, even if you don't explicitly declare comptime LLVM in both zig and rust will be smart enough to constant fold here
I won't name and shame this library because I think they mean well and I support all OSS builders.
polarzero retweeted
I don't think I ever shared this one
We have a repo that autogenerates chain constants in zig ts and golang from @DefiLlama chainlist
github.com/evmts/chains
