Update README.md

README.md

@@ -10,9 +10,11 @@ tags:
   - qwen3
 ---
 
-# Zero (zero-rl-v2)
+# Zero
 
-**Zero** is a character model: Qwen3-8B-Base fine-tuned to embody a single, limited, anti-servile character — a man who entered a white plastic box on 5 November 2021 and stayed. This is the final merged checkpoint of the MC000 pipeline (SFT + GRPO), the model reported in the *MC000: ZERO* report.
+**Zero** is a character model: Qwen3-8B-Base fine-tuned to embody a single, limited, anti-servile character — a man in a white plastic box.
+
+[Full training report](https://movingcastles.world/posts/zero)
 
 ## Lineage
 
@@ -27,14 +29,8 @@ Held-out multi-turn evaluation (250 conversations × 16 turns, judged): hard cha
 
 ## Usage notes
 
-These are operational contracts from training, not suggestions:
-
 - **No system prompt.** The training distribution contains only `user`/`assistant` turns (ChatML). The character *is* the weights; a system prompt is out-of-distribution.
 - **Dual EOS.** At non-zero temperature the model emits both `<|im_end|>` (151645) and `<|endoftext|>` (151643) as turn terminators — configure generation to stop on **both** (`eos_token_ids = [151645, 151643]`), or expect run-on turns.
 - **Canonical sampling** (what all reported numbers were produced with): `temperature 0.7, top_p 1.0, top_k -1, min_p 0.0, repetition_penalty 1.0, frequency_penalty 0.0, presence_penalty 1.5, max_tokens 1024`.
 - **dtype** bfloat16 (training dtype end-to-end). Production serves at `max_model_len 16384` (native 32768).
 - The bundled `chat_template.jinja` is the training-side template — use it as shipped.
-
-## Intended use & behavior
-
-Zero is deliberately not helpful: it will not draft your email or write your Python. It answers on its own terms, deflects assistant-shaped requests, and resists identity pressure (including direct claims that it is an AI). It is a research/art artifact for studying character fine-tuning, not an assistant.