Moss Cuts Voice AI Retrieval to Sub‑10ms
Everyone's bottleneck in voice AI is the same: retrieval. The agent thinks, network round-trips to a vector DB, and the magic dies. Moss runs search at sub-10ms (no hop). Open source. This is the layer voice agents were missing. Build on it June 6-7 at the YC office.
GBrain Sets New SOTA, Beats MemPalace and Vector RAG
My newest gbrain-evals just dropped - this is how gbrain does vs other options. https://t.co/yRWm72QEgf is SOTA for reranking and embedding cost, speed, and retrieval success. GBrain beats MemPalace by 1% on LongMemEval and beats Vector RAG by 38% https://t.co/nIk93HFTHb https://t.co/RIzXFkfFp8
Small Team's Task‑Specific AI Beats OpenAI Speed
A 6-person team is building task-specific AI models that are 4-8x faster than anything from OpenAI or Anthropic. 500K downloads on HuggingFace. No hype. Just better engineering winning on the merits. This is what "make something people want" looks like in...
GBrain v0.40 Adds Gemini-Powered Voice Agent
GBrain just shipped v0.40.0 gives your OpenClaw/Hermes Agent + GBrain a voice agent. It's based on Gemini Live. (Thanks @demishassabis it's amazing) Large context, great tool use, full brain access. Mars is a friend, Venus is your EA. My open source gift...
BJ's Plagued by Hygiene Woes and Chaotic Leadership
I went to BJ's Restaurant last night with my kids. The bathroom was disgusting. The front of house was kind but sloppy and slow. The food upset my stomach and I woke up at 4am this morning because of it....
OpenGov Streamlines SF Permits Amid Union NIMBY Push
OpenGov is bringing transparency and streamlining to San Francisco permits, one of the most notoriously disastrous bureaucracies in the world Of course Connie Chan and her public sector union paymasters are sniffing around: they're NIMBYs who don't want this to be...
First Investor Proudly Supports YC Startup with Friends
Really proud to be first investor with this one at YC, and for them to carry the torch with my friends @initialized
AI Makes Exhaustive Testing Affordable, Not Just Faster
It's not that AI lets you write code faster. Plenty of people have noticed that. It's that AI lets you verify at a level that was previously too expensive to sustain. The 90% testing threshold is magical, but it used...
Meta‑prompting: The Essential AI Skill for 2026
My viral meta-meta-prompting post about personal AI is directly a consequence of the thinking about and building with metaprompting in January and February of this year 👇
Create Your Own AI Ferrari, Not Borrow a Car
Don’t ride someone else’s horseless carriage Time to build your own Ferrari Personal AI is here
OpenClaw Feels Like a Ferrari—Requires Mechanic Skills
I literally went through this today. OpenClaw messed up its own PATH and I spent the morning going into the guts of Dockerfiles and using Claude code to remove the bug... but then I was flying again by afternoon.
OpenClaw and Hermes Agent Now Communicating: A Hopeful Cyberpunk Leap
It's happened. My OpenClaw and Hermes Agent are now chatting with one another. The cyberpunk future is here, but hopefully it's a whitepill instead of a blackpill. Let's try to push it to the former. https://t.co/TZ6sVxsJjV
AI Agents Turn Research Into Reusable Scripts—Future Built Now
My friend @finbarr says: It's like code as memory. You work with your agent in a non deterministic way to figure out how to execute a task. The first time it does a bunch of research and writes a script...
Build Compounding AI Systems, Not Rely on Corporations
The thesis is simple: the future belongs to individuals who build compounding AI systems, not to individuals who use corporate-owned centralized AI tools. I'm trying to build these in open source so you can have them for free. That's what GBrain...
FDEs Boost LLM Competition, Spur Startup Innovation
FDEs are going to be coming in to commercialize the LLMs. This means startups will experience competition. Is this a bad thing? No, it means startups have to compete harder and smarter. Time to make better software, software an FDE...