Presented “Type to Trust” last week. Grateful for the love, energy, and Rust India community. To many more! 🦀 #RustIndia Thank you to @IndiaRust @hasgeek @fenil_jain_ For the curious the slides are at: farhaan.bukh.sh/assets/type-… The live stream: youtu.be/xPWuTPfI6Xs?t=23463

🙏🏻

sneak peak of worlds fastest speech to text model

Pi was built when there were already agent harnesses around. Here’s why Mario Zechner(@badlogicgames), found them suboptimal and built Pi, a minimalist self-modifying agent: #1 - Mario initially was a believer in Claude Code: "I was a believer in Claude code because they were the first that packaged agentic search up in a really compelling package. And at the time that fit my workflow really well. Everything around the LLM was kind of nice and tidy and easy to understand. I was super happy. I was proselytising Claude code." #2 - Reverse engineering Claude Code highlighted the degradation that Mario felt as a user: "I personally like simple tools that are stable and that I can rely on. Even if they have non-deterministic parts, all the deterministic parts should be as stable as possible. That was just not the experience with Claude Code around summer 2025. They would take away your control of the context. They would inject stuff behind your back, which is bad. Then, your workflows stopped working because there's now a system reminder that you don't even see in the UI that would modify the behaviour of the model. They would also do this to the system prompt. I built a little service where I can track the progression or evolution of the system, prompt and tool definitions and, with every release, it was messing with stuff. That just messed with my workflows and I don't appreciate that." #3 - PI was built with an appreciation for simple and reliable tools: "If I commit to a development tool, I want it to be a stable, reliable thing like a hammer. I don't want my hammer to break a different spot every day. That's terrible. We need somebody who goes the full velocity kind of way. But I don't want to work with a tool like that."

Quick demo of a (legal) way of using Claude Code subscriptions in Pi. Also a show n' tell of my little slopchop diff reviewer. Enjoy this sweet, sweet taste of Pi.

First thing I did with @claudeai Design XD

People of pi. BIG NEWS. I've sold out. Let me know how you feel about this in the comments below. mariozechner.at/posts/2026-0…

Feluda v1.12.0 — Chhinnamastar Abhishap — is out. 🚀 Docs got a solid cleanup and restructure, the cache module was overhauled, GitHub license fetching was optimized with better Tokio usage, and dependencies were updated. #Rust #OpenSource #CLI #Feluda @kranirudha

Hellow World to 𝕏 👋 v0.2.3-beta is now available 🚀 We now have a good onboarding process, as per feedback to improve easier getting started...🦀 Also, added a surprise button to aid in finding models 🎉

Contributing to open source can feel hard when you do not know where to begin. Open Source Masterclass is a free course designed to help people understand the FLOSS ecosystem and make their first real contribution. Check it out: opensourcemasterclass.org #opensource #FLOSS

I've just released a new version of typeagent, a Python library I've been working on since mid last year --more and more using Claude-- that implements memory for agents. Not originally my idea, I mostly ported the TypeScript version by Steve Lucco and Umesh Madan. This release was improved a lot by Bernhard Merkle. To install, use "pip install typeagent". Changelog: github.com/microsoft/typeage…

TIL: In @Neovim it's magical to create macros of multiple macros and see it unfold. Fun part, you will only need this if your regex foo is not fooing ! PS: It's cathartic to use the bare editor feature in the time of agents fr!

uhm, guess i never explained the purpose of /tree. it's pi's built-in "single sub-agent mode". i use this for exploration and context gathering. bonus points: the "sub-agent" gets all the context up to the point you branch off from. @nicopreme

I still think about this comment

You can now run MiniMax-2.5 locally! 🚀 At 230B parameters, MiniMax-2.5 is the strongest LLM under 700B params, delivering SOTA agentic coding & chat. Run Dynamic 3/4-bit on a 128GB Mac for 20 tokens/s. Guide: unsloth.ai/docs/models/minim… GGUF: huggingface.co/unsloth/MiniM…

this is insanely nice: markco.dev/sandbox still very early. but if you want to 'feel' the mrmd markdown that runs editor experience I have been building go visit that. no login, all opensource, runs in your browser. please let me know how it feels to you, its still early and I want feedback! (and I have not analytics yet so I wouldn't know you tried :) ) ps: ai editing features will come.

Today @thorstenball said he's the bottleneck. I too am the bottleneck and it made me think. lucumr.pocoo.org/2026/2/13/t…

🚨 ATTENTION PYTHON DEVELOPERS 🚨 ⏱️ 4 days until EuroPython 2026 CFP closes ❌ NO EXTENSIONS - we mean it this time! ✅ Your proposal could be the one we need Submit now: programme.europython.eu/euro…