RAW Works

Recursive Language Models (RLMs) have proven a powerful harness architecture for Large Language Models, enabling dynamic agent workflows (Anthropic), extremely long context processing (MIT), SOTA results on “long chain-of-thought” benchmarks (RAW.works),…

As usual, I can’t help but dive right into anything that comes out of Omar Khattab’s lab.

Agent skills are a powerful and portable way to transform generally capable AI agents into specifically useful tools — even teammates.

I personally do not care if my AI programs do their reasoning in latent space or code.

Reasoning models were the first clear proof that language model capability can scale with test-time compute.

A few days ago I showed Sonnet 4.5 + dspy.RLM hitting 45.4% on LongCoT-Mini.

After the LongMemEval experiments in February, I’ve been hungry to find a better benchmark that will actually showcase the power of recursive language models (RLMs) on useful tasks.

Over the last 2 days, we’ve stumbled upon a really powerful coding agent interaction pattern: git notes as an underground information network.

I built ypi — a recursive coding agent.

My morning’s notes from yesterday: As I was waiting for Claude Code to help me with my goal of modifying DSPy to be able to “RLM everything”, I came across this result from Mastra.AI which describes a SOTA result on LongMemEval using an “observational mem…

I’m noticing an inversion of caution between the LLMs themselves and the behavior in their official coding agent harnesses.

Inspired by last week’s research report from Jude Gao - “AGENTS.md outperforms skills in our agent evals” - this weekend my agents worked hard to make dirpack. dirpack creates compressed directory representations that fit within specific token/byte budget…

After years of being frustrated by the inability of AI to read my handwritten notes, I am frankly shocked to report that this morning Claude Opus 4.5 simply one-shotted my crappy handwriting.

I’m often asked how big my company is—how many people I employ full-time.

Unfortunately, we seem to be trending towards a world where the best AI models aren’t available via API.

Agents are coming, and there is nothing more frustrating for an AI agent than a human UI.

When I was in graduate school, I thought 3D printing was dumb.

“Tough times don’t last, tough people do.”

Happy Solstice!

Today I needed to do something in Adobe Illustrator, which I have no idea how to use.

This post and video are dedicated to Prof.

Well, after six days of a ketogenic diet and four with COVID symptoms, I can definitely say that my energy is depleted.

Hey there, it’s Raymond.

I want to treat my social media accounts as “repeaters”.

I have COVID, for the second time.

Remember the story about the McDonald’s at the top of the volcano?

I struggle to create clear instructions for AI.

In this video, I delve into the world of AI transcription, specifically focusing on MacWhisper, a leading tool for AI-driven voice-to-text transcription on Mac.

Today I attended Builder’s Roundtable: Generative AI for eCommerce.

A brief enumeration (or perhaps perturbation) around the concept of the “Zone of Genius”: Zone of Genius Competitive Advantage The One Thing 80/20 Principle Specialization Deep Work Unique Value Proposition Leverage Strategic Focus

“Show me the incentive, and I will show you the outcome.” - Charlie Munger This weekend I’ve been thinking a lot about incentive structures.

The pace of AI development over the last few months has been simply exhausting.

For those that follow, you’ll know I’m currently obsessed with AI, voice to text transcription, and the intersection of AI and voice-to to text transcription.

I’ve been working on my AI “content machine” for polySpectra.

There are three reasons why big companies are so obsessed with big data.

Today is polySpectra’s 7th birthday.

I’m not always the best at making time for play.

Today I started thinking a lot about the fact that the 3D printing industry is “traumatized”.

Today I noticed a new section on Purple Space for AI exploration and discussion.

This week we did our first AI-assisted 6 Hats exercise with 6 Hats Helper.

Today I had an “Oh That’s Why It’s So Hard” moment courtesy of NIST, US taxpayers, and the Constitution.

Sometimes you fall off the horse.

SuperAgent has recently introduced a new feature that’s worth exploring: Custom Tools.

In my ongoing journey with AI, I’ve been experimenting with a new approach: dictating directly to AI.

I’m intrigued by this concept: “Type as fast as you can.

I was revisiting Curable recently.

I recently came across Tavily, an AI-powered platform that aims to revolutionize the way we conduct research.

My friend Keetu said something very deep recently, which I think is appropriate for Thanksgiving: “Family Is Where Things Don’t Need to Make Sense”

Sometimes you get lucky on the first try.

The big companies will never catch up.