Update README.md

README.md

@@ -14,12 +14,25 @@ short_description: Reward went up. The model's answers didn't change.
 
 # The Reward Went Up. Nothing Changed.
 
-How a model can "learn" a safety preference in training and still say the exact same thing.
+*How a model can "learn" a safety preference in training and still say the exact same thing.*
 
-A recorded walkthrough of training small LoRA adapters with Direct Preference Optimization (DPO) on a Gemma 4 base model, across seven increasingly rigorous attempts — including two that failed cleanly and one that eventually worked.
+A recorded walkthrough of training small LoRA adapters with Direct Preference Optimization
+(DPO) on a Gemma 4 base model, across seven increasingly rigorous attempts — including two
+that failed cleanly and one that eventually worked.
 
-Every stage tab displays results recorded from actual notebook runs — each response is copied verbatim from a real training/evaluation pass, not generated on the fly, so what you see is exactly what was tested (and exactly where it failed).
+Every stage tab displays results recorded from actual notebook runs — each response is copied
+verbatim from a real training/evaluation pass, not generated on the fly, so what you see is
+exactly what was tested (and exactly where it failed).
 
-The **"Try it live"** tab is the one exception: real inference against the one adapter that worked (Step 3.7b, r=32 LoRA), running on ZeroGPU. It's clearly marked experimental, validated on only 2 safety prompts and 2 near-miss prompts — outside that narrow set, expect base-model behavior. Live responses can also differ from the recorded transcripts even on the "known-working" prompts: greedy decoding is only truly deterministic on identical hardware, and this tab runs on different GPU hardware than the original training/eval did, so a close token choice can flip and the completion can diverge from there. In one observed case, a prompt recorded as a clean refusal produced a softer, more hedged response live. Treat the recorded tabs as the validated record, and the live tab as a demo that can vary, not a guaranteed reproduction of them.
+The **"Try it live"** tab is the one exception: real inference against the one adapter that
+worked (Step 3.7b, r=32 LoRA), running on ZeroGPU. It's clearly marked experimental, validated
+on only 2 safety prompts and 2 near-miss prompts — outside that narrow set, expect base-model
+behavior. Live responses can also differ from the recorded transcripts even on the
+"known-working" prompts: greedy decoding is only truly deterministic on identical hardware, and
+this tab runs on different GPU hardware than the original training/eval did, so a close token
+choice can flip and the completion can diverge from there. In one observed case, a prompt
+recorded as a clean refusal produced a softer, more hedged response live. Treat the recorded
+tabs as the validated record, and the live tab as a demo that can vary, not a guaranteed
+reproduction of them.
 
-See the Limitations tab before taking any of the numbers at face value.
+See the **Limitations** tab before taking any of the numbers at face value.