Introducing Stream & Stream Ring. Let thoughts & ideas flow ∽ Preorder now at sandbar.com

We just acquired @weavy_ai, soon to be known as Figma Weave. With Weavy, you’ll get more models, more tools, more ways to create within the canvas. More to come

i made a chrome extension that hides all website content except ads

I just released Beads, a drop-in cognitive upgrade for your coding agent of choice. github.com/steveyegge/beads In a nutshell, it is a magical 4-dimensional graph-based git-backed fairy-dusted issue-tracker database, designed to let coding agents track all your work and never get lost again. Beads replaces that disgusting pile of half-eaten markdown files in your plans/ directory. You know you have one. Install the Beads binary, tell your agent in AGENTS.md to stop using Markdown and run `bd quickstart`, and your agents will spontaneously get better at everything, particularly long-horizon planning and keeping track of newly discovered work. If you are looking for a long-ass but occasionally funny article about how I discovered it while burning a 350k line code base to the ground: steve-yegge.medium.com/intro… Or you can, you know, just start using it. It's MIT-licensed, written in Go, and super lightweight and portable. Let me know how you like it. Enjoy!

My brain broke when I read this paper. A tiny 7 Million parameter model just beat DeepSeek-R1, Gemini 2.5 pro, and o3-mini at reasoning on both ARG-AGI 1 and ARC-AGI 2. It's called Tiny Recursive Model (TRM) from Samsung. How can a model 10,000x smaller be smarter? Here's how it works: 1. Draft an Initial Answer: Unlike an LLM that writes word-by-word, TRM first generates a quick, complete "draft" of the solution. Think of this as its first rough guess. 2. Create a "Scratchpad": It then creates a separate space for its internal thoughts, a latent reasoning "scratchpad." This is where the real magic happens. 3. Intensely Self-Critique: The model enters an intense inner loop. It compares its draft answer to the original problem and refines its reasoning on the scratchpad over and over (6 times in a row), asking itself, "Does my logic hold up? Where are the errors?" 4. Revise the Answer: After this focused "thinking," it uses the improved logic from its scratchpad to create a brand new, much better draft of the final answer. 5. Repeat until Confident: The entire process, draft, think, revise, is repeated up to 16 times. Each cycle pushes the model closer to a correct, logically sound solution. Why this matters: Business Leaders: This is what algorithmic advantage looks like. While competitors are paying massive inference costs for brute-force scale, a smarter, more efficient model can deliver superior performance for a tiny fraction of the cost. Researchers: This is a major validation for neuro-symbolic ideas. The model's ability to recursively "think" before "acting" demonstrates that architecture, not just scale, can be a primary driver of reasoning ability. Practitioners: SOTA reasoning is no longer gated behind billion-dollar GPU clusters. This paper provides a highly efficient, parameter-light blueprint for building specialized reasoners that can run anywhere. This isn't just scaling down; it's a completely different, more deliberate way of solving problems.