Model card: "New (1 October 2026)" summary at the top

README.md

@@ -92,6 +92,19 @@ stronger System 2, and it answers a single decision in about half the time the h
   <sub><b>Scorecard.</b> System 1 fidelity, calibration and transfer, System 2 and speed; grey tags show JEV-9B · click to enlarge</sub>
 </p>
 
+## New (1 October 2026)
+
+* **System 1 over plain HTTP.** `serve_decide.py` (in this repository) adds `POST /v1/decide` to the vLLM server: send
+  `{kind, state, question, options}` and get a calibrated probability for every option. See
+  [Quickstart](#quickstart-with-vllm-recommended).
+* **Up to 256 options per choice question**, with no retraining. Zero-shot on CLINC150 with all 150 intents as options:
+  89.5% with intent names alone, 93.8% with a one-line description per option. See
+  [Choice questions with up to 256 options](#choice-questions-with-up-to-256-options).
+* **How to write prompts, measured.** One-line "use when" descriptions for similar options help; question wording, JSON
+  vs plain text and extra instructions make no measurable difference. See [Writing System 1 prompts](#writing-system-1-prompts).
+* **256K-token prompts.** Decisions that hinge on one sentence hidden at a random depth in up to 250K tokens of text:
+  20 of 20 correct at every length tested. See [Context length](#context-length).
+
 ## Public decision benchmarks
 
 Six public text-decision benchmarks. AutoTrust ran them in full for autotrust/JEV-27B and for the hosted TypeSafe