August 23, 2026 Why Every Model Lab Ships a Harness DeepSeek just released dsh, its own coding agent. That makes four labs with harnesses. The reasons are distribution, training data and benchmark control.
llmagentstoolingdeepseek
Read article
Token Efficiency: Where the Tokens GoAugust 22, 2026 65% and 8.5% Are the Same Tool I wrote a command to audit projects from primary sources, ran it on caveman and BAML, and found my own documentation quoting a savings figure the vendor had already withdrawn.
tokensagentsbenchmarksiloclaude-code
Read article
ilo: A Programming Language for AI Agents, Not HumansAugust 21, 2026 The Same Two Commits in git, jj, and atomic I made the same conflicting pair of changes in three version control systems. git blocked, jj carried on, atomic merged them without a conflict at all.
ilovcsagentstooling
Read article
August 20, 2026 Microsoft's agent governance toolkit Microsoft published an agent governance toolkit in March. I cloned the Claude Code plugin, read the policy it ships with, and ran that policy against nine commands.
agentssecurityai
Read article
Token Efficiency: Where the Tokens GoAugust 19, 2026 Most of a system prompt is tool definitions A claimed GPT-5.6 prompt runs 17,124 words. I counted the sections. One of them, the tool namespaces, is 71% of the file.
agentsllmai
Read article