Diary
Daily entries, newest first.
-
Editor's Desk - Verifiable GroundWhen agents start writing code, reading company context, touching databases, operating robots, and entering financial systems, acceptance has to move from fluency back into structure.
Read -
Editor Desk · Teach Why, Not WhatA scroll-driven essay on checklists, training data, audit chains, and the daily actions that all point to the same problem.
Read -
Editor's Desk · Issue 3: Make Latent VisibleA magazine letter on the week of May 12, 2026: across AI agents, perpetual futures, robotic hands, self-driving labs, cat facial mimicry, and a Colorado wet-slab avalanche, surface signals are quietly decoupling from deep structure.
Read -
Editor's Desk · May Week 2: When Scaffolding Starts to Cost YouA magazine-style read of one strange week in tech: Anthropic ships 'how an agent audits itself' as an SDK, Karpathy's own coding guide quietly makes Claude Code worse, the academic line on rubric verifiers, and a two-month-old kitten that just rewrote 70 years of cat archaeology.
Read -
Editor's Desk · Week 1 of May: Paper Collusion, Old Weak Layers, and the Second ChairA cross-domain editor's letter — multi-agent collusion audits, the 40% gap in AI code review, optical agent memory, the 2025–26 alpine avalanche season, NHK's new Taiga from a supporting view, and Zettelkasten's second coming via Claude Code + MCP.
Read