diff --git a/scripts/frank-default-large.env b/scripts/frank-default-large.env
index 2356d73..14a0ca0 100644
--- a/scripts/frank-default-large.env
+++ b/scripts/frank-default-large.env
@@ -83,10 +83,13 @@ SPEC_DRAFT_P_SPLIT=0.10
 # preserve_thinking=true (preserve thinking tokens across turns).
 #
 # FASTGREEDY mode: set to 1 for fast-greedy benchmark (card's default profile)
-# FASTGREEDY=0 (default): production chat config (reasoning on, argmax off)
+# FASTGREEDY=0: production chat config (reasoning on, argmax off)
 # FASTGREEDY=1: reasoning off, LLAMA_TARGET_GREEDY_ARGMAX_FASTPATH=1, deterministic
 #   sampler. Mirrors the card's 'fast greedy (default)' benchmark config.
-FASTGREEDY=0
+# 2026-08-22: flipped to 1 for real (operator decision). NOTE: the fast
+# greedy path rejects non-greedy requests (temp != 0, top_k > 1, penalties,
+# reasoning budgets) with 400. Chat clients must send temperature 0.
+FASTGREEDY=1
 
 # For fast-greedy bench: set FASTGREEDY=1 above. This flips to: reasoning off,
 # argmax fastpath=1, sampling defaults. Deploy with