Field entries on the Hammerstein doctrine, the benchmark, and what the AI is doing. Methodology that survives publishing. Newest first.
Six features moved to Sonnet 5.5 after a side-by-side test caught two problems that would have reached the site. Chat stayed on Sonnet 5. Match, the VASSAL opponent, is built and merged but switched off, and you cannot play it yet.
“Match won’t move if it can’t find the rule, modifier or chart it needs in your book.”
Wargamer turns with pasted rules and no board photo, and the RPG rulebook condenser, now run on DeepSeek V4.1 Flash. I found it by testing a model router. The router lost, the model it kept picking won, and the money saved goes into bigger rules limits: both quadruple today.
Every mode on the site now runs Sonnet 5, and a solo RPG GM mode opened at /rpg. Its dice are drawn from a tape fixed when the campaign starts, echoed in the mechanical log, and checked by the server before a turn stands. Cairn ships built in, alongside the GM’s own 2012 game.
A kriegsspiel umpire, a matrix-game referee, and a hosted chat. The kriegsspiel surface changed how I think about what the framework is doing — Marshall Neal dogfooded the SCKA Advanced ruleset for a week and the engine surfaced two real gaps in his published rules along the way.
Public-facing AIs are polite. They’ll tell you your benchmark is “solid work” and move on. The same Grok 4.20, prompted privately, called it “a specialized idiot-savant for this exact distribution.” Then it designed the test that would prove it. We ran the test.