In a future filled with agent-driven dependency upgrades, semantic versioning has less value.
(Ironically, agents are probably better at enforcing strict semantic versioning than humans are.)
We built vgpu.sh to ship shaders on vercel.com. Now it's open source.
▪︎ Minimal agent-first WebGPU library
▪︎ Run in the browser or headless Node.js
▪︎ Render in CPU sandboxes and CI tests
▪︎ Create reusable .wgsl modules
I agree more and more. Everything seems to point to doing work in passes -- code generation pass, review pass, etc. "Dreaming" is yet another pass.
I think we'd greatly benefit from more RL on memory extraction and/or discovery.
