Ph.D. in Physics ⚛️ | AI & ML Expert. Leading innovations. InCredibles & Innowator Śląska 2024 winner. Bridging deep science & business impact.
Poland, San Jose USA
Joined March 2011
- Tweets174
- Following184
- Followers93
- Likes220
Heading to SysOps/DevOps Katowice tonight? So am I—but I’ll be up on stage! 🎤
Join me for some serious engineering deep-dives, community Q&A, and networking over pizza.
📅 Tonight (Oct 14) at 18:00 CEST
📍 ING Hubs Poland, Katowice
Last chance to sign up! 👇
meetup.com/pl-pl/sysopskato/
#DevOps #SysOps #Katowice #TechMeetup
Lech Kalinowski retweeted
We trained Apex for React Native. It landed #2 at fixing web React.
Callstack's Apex is tied #5 overall on @aidenybai's ReactBench. React Native tuning carries over to the web.
Try it on Vercel AI Gateway or apex.callstack.com
Lech Kalinowski retweeted
Read the article 👇
clstk.com/4yf2uOb
Lech Kalinowski retweeted
AI helps your team ship code faster, but how does it actually achieve end-to-end ROI?
@syke shares his approach: start with a business metric hypothesis, verify user exposure, then measure the outcome and cost.
Learn how to apply a rubric before calling your next agent-assisted feature release a success 👇 Link in the comments
🚀 Apex is now available on Vercel AI Gateway.
Callstack’s agentic coding model is built for React Native, React, and Next.js, with a 256K context window for feature development, debugging, testing, reviews, and large refactors.
Try it: vercel.com/ai-gateway/models…
Celebrating @callstackio’s APEX launch! 🎉
I connected APEX to my Vault Terminal (callstack.com/blog/building-…) for some classic RPG gaming. 🎮
@OpenAIDevs has Codex × @modretro Chromatic.
We have @apex__ai × Vault. 😎
Still an early prototype (only one piece exists 😅).
Small company, big heart and even bigger ambitions! ❤️
Lech Kalinowski retweeted
Announcing Apex: agentic coding model for mobile and web, specialized in React.
We built Apex from a single idea: can an open-weight model deliver frontier-level performance at lower cost?
Yes. Apex is SOTA in React Native and Next.js.
Try it now: apex.callstack.com
A few photos from my Agents Commander talk at Code Europe! 😄
I spend a lot of time working with AI agents, so it was good to share what I’ve been building and how I actually use it.
Thanks to everyone who came along—and to @code_europe for having me!
I’m building something awesome. 👀
The inspiration came while on holiday with my kids—but this is the next chapter of my AI-native device project, Vault.
I’ve tested the stack with current SOTA open-weight LLMs, and it works. The ultra-compact enclosure for my custom Jetson Orin Nano Super build is now printing. Fully parametric, too—no Astra operating Blender involved. 😉
Probably my most ambitious after-hours Physical AI project yet. Still need to add a physical kill switch… just in case! 😅
I’m fascinated by how far I can push this.
Where it started:
callstack.com/blog/building-…
#PhysicalAI #OpenSource #Hardware
Lech Kalinowski retweeted
This is your tool for testing mobile apps with agents, any platform, simulators and devices included ⬇️
Any agent can test iPhone Duo apps for you now. No need to do it by hand.
Folded, half-open, open, all without stealing your focus or other agents sessions.
Just give them @agent_device
How does quantization affect APEX performance? 🔬
Artur Morys-Magiera @artus9033 and I shared our research at @AgentConf . We hope our findings help the community make more informed decisions about quantization.
🎥 youtu.be/XLoY8PpYXNU
344 runs. 25 days. Quantization is humbling 😅
Apex-31B BF16: 57% → 86.5% MMLU after fixing the chat template + eval harness. Same weights. Same 400 questions. 🤯
Then the payoff: IQ4_XS gave us 3.4× decode throughput and a 73% smaller file vs BF16 on DGX Spark. 🚀
@artus9033 and I talked about all of this at @AgentConf , organized by @callstackio.
For me, it’s already one of the most exciting AI conferences in Poland! 🇵🇱🔥
