wsxiaoys

https://sketchagent.dev/s/yfYU6LhT

When GPT-6/Gemini launched recently, a lot of the 3D demos used blender-mcp (https://github.com/ahujasid/blender-mcp). It's cool, but you have to install blender locally and wire up plugins just to try a prompt or share a run.I built a browser-based 3D mesh playground so you can hook up your own coding agent over MCP (or run in-browser) directly in a tab. It runs on three.js + manifold-3d for...

https://gist.github.com/wsxiaoys/e0286dc6bb624ff5fdf49e7f4c528ba3

https://gist.github.com/wsxiaoys/102e8654c14d5d27b7b77532026ebfa5

I wrapped this small followup to stolen-thoughts.com in a gist for easier reading and wanted to share it here.My hunch is that this might not just be reasoning distillation; it could even be benchmark distillation. This is a small experiment and definitely doesn’t prove anything about how any model was trained, but I thought the contrast was interesting enough to share.I’d also like to try...

https://docs.getpochi.com/tutorials/manage-library-migration-at-team-scale/

https://tabbyml.github.io/jj-benchmark/

Hi HN, Meng from TabbyML here.We decided to build this simply because we find Jujutsu (jj) really interesting, and many folks on our team have started trying it out recently. Since it introduces a very different workflow compared to traditional Git, we thought it would be a fun challenge to see how well current AI coding agents can actually use it.To build this, we created a semi-automated...

https://docs.getpochi.com/developer-updates/#nov-19-2025

https://docs.getpochi.com/developer-updates/dynamic-rendering-stratergies-for-ai-edits/

https://docs.getpochi.com/developer-updates/request-management-in-nes/

I work on an open-source coding agent, and one design choice we made is to keep conversations append-only. No editing past prompts.Many would argue this feels restrictive. Isn’t it just better to edit an earlier message or tweak the prompt and move on? And this is what most coding agents allow, and on the front, it looks convenient. But realistically, editing conversation history throws away...

This is a personal opinion, but I think current coding agents requires human reviews AI's artficats at the wrong moment. Most tools focus on creating and reviewing the plan before execution.So the idea behind this is to approve intent before letting the agent touch the codebase. That sounds reasonable, but in practice, it’s not where the real learning happens.The "plan mode" takes place before...

https://docs.getpochi.com/developer-updates/reinforcement-learning-in-ai-coding/

https://docs.getpochi.com/developer-updates/context-management-in-your-editor/

https://docs.getpochi.com/developer-updates/how-we-created-nes-model/

https://docs.getpochi.com/developer-updates/2025-11-11-launch-parallel-agent/

Though parallel agents already exists, we built this out differently in Pochi. Most other tools operate inside a single editor tab. That means there is at most one conversational state to interact with.Parallel Agents in Pochi use separate Git worktrees, so each task has its own working directory, branch, chat history, and terminal environment. Task state stays isolated.From a UX standpoint,...

https://github.com/wsxiaoys/claude-code-share

I got tired of screenshotting claude code sessions to share with teammates, so I built this. It converts session into beautiful web pages with proper rendering of tool calls.Works by parsing CC's session, extracting steps, then uploading to a simple sharing service. Takes about 2 seconds to generate a shareable link.Live examples:- https://cc.getpochi.com/s/IldMh27j (Research claude-code-share...