Your Skill File Now Has a Backward Pass
Researchers at Microsoft published the first systematic text-space optimiser for agent skill files last week.
Author: Martin Treiber
What Free Software Promised, Prompts Deliver — of All Things
Free software is about the right to modify the software you use, given source access. Few users could ever exercise that right.
When Software Updates Arrive as Instructions
When software updates arrive as prompts, the signature authenticates the instruction — not the program the local LLM produces from it.
The Kanban board is the file: lightweight coordination for parallel Claude Code
A Kanban board tells you is what's about to happen, what another agent is doing right now, or which card is yours to pick up.
Building a development diary for Claude Code
Commit messages tell you what changed, but don't tell you what was tried first, what broke, or where the work pivoted. A diary does.
Fork-on-share
How Fork-on-share doesn't give you a URL to update. Why the Fork-on-share model is still working well for many use cases.
The Other Half of the Rediscovery
Thariq, Karpathy, Theo — HTML for LLMs has crossed into the open. But the rediscovery is only the read side. The write side is where the document edits itself.
HTML is being rediscovered in the Context of LLMs
The web was supposed to be writable HTML is being rediscovered. This is happening in how people work with LLMs.
The Center of Gravity Decides Everything
OpenClaw's gateway-first architecture and Hermes Agent's loop-first runtime shape memory, skills, security, and deployment.
reWritable Is Harness Engineering You Can Do in an HTML File
A reWritable is a complete harness..The HTML file ships with its own loop, its own memory, its own persistence and its own model call.