







Building with AI & LLMs | Insights, recipes, tools & honest experiments
Supersonic Labs (@supersonicai) on X
We're an AI research lab building fast, local, and accessible AI. Our mission is to make capable AI run on the hardware people already own.

The AI Chemist: To be trustworthy, LLMs need to show their work
Good scientists reveal how they do their experiments and report their results; so should any machine-driven research
I am often wrong
[I shared this note with my team earlier this week, and am posting it here as well. I hope it is interesting or helpful for others working on building product in the age of AI.]
Maggie Appleton - How to design for the future of AI products and LLMs (Dive Club Ep. 57)
AI Innovation Workspace | Miro
Speed up product development from ideation to launch. Align teams, break tool silos and ship what customers need in one AI-powered visual platform.

Introducing LM Studio Bionic: the AI agent for open models
The AI agent made for open models, built to get things done.

(Re)building Roomy in 6 months - meri's missives
A recap on my engineering and design process

Digital Science on Twitter / X
An AI-native workspace that already knows your project?The new Papers AI from Digital Science keeps your drafts, data & references together, so the AI assistant has full context of your work - instead of starting fresh each time. 👉 Available now: https://t.co/DNcG173GDk… pic.twitter.com/FQWxdfKfS4— Digital Science (@digitalsci) August 4, 2026

LLMs as Parts of Systems - Marc's Blog
Over on the Kiro blog, I wrote a post about Kiro and the future of AI spec-driven software development, looking at where I think the space of AI-agent-powered development tools is going. In that post, I made a bit of cheeky oblique reference to a topic I think is super important. I asked Kiro to build a Towers of Hanoi game.

They all use it
Last week, at a conference, I had a random hallway conversation with another engineer. About AI.

Infer Vancouver: AI Engineering Meetup
Vancouver's meetup for tactics, techniques, and lessons learned in LLM and AI engineering.

Using X-Labs to Unleash AI-Driven Scientific Breakthroughs | IFP
How to adapt our science funding mechanisms to the unique infrastructure needs of large-scale AI projects

Notes from inside China's AI labs
Lessons from my trip to talk to most of the leading AI labs in China.

Our newest project is taking flight: meet codename goose! 🪶 Today, we launched an open source on-machine AI Agent. It’s modular, works with your preferred LLM, and integrates seamlessly with developer tools and other software via MCP. Developers, check it out! block.github.io/goose/blog/2025/01/28/introdu…
Introducing codename goose
block.github.io