diff --git a/code/duffle/gen/duffle.macs.h b/code/duffle/gen/duffle.macs.h
index c71cbfe..337ce4c 100644
--- a/code/duffle/gen/duffle.macs.h
+++ b/code/duffle/gen/duffle.macs.h
@@ -115,11 +115,8 @@ WORD_COUNT(mac_format_g4_color, 12)
 /* Words: 3; Stores the 3 transformed (V2_S2 screen) vertices of the
  * G4 triangle portion to p0/p1/p2.
  * PIPELINE: post-RTPT, pre-RTPS (SXY0=v0.screen, SXY1=v1.screen, SXY2=v2.screen). 
- * MUST be called BEFORE V3-RTPS, otherwise SXY0/1/2
- * get overwritten with v3 (RTPS writes only to SXY2, but to keep the
- * three registers aligned with v0/v1/v2 you must store before RTPS).
- * The macro name declares the pipeline position; check #6 (GTE state-
- * machine validation) verifies the call site matches the declaration. */
+ * MUST be called BEFORE V3-RTPS, otherwise SXY0/1/2 get overwritten with v3
+ * (RTPS writes only to SXY2, but to keep the three registers aligned with v0/v1/v2 you must store before RTPS). */
 #define mac_gte_store_g4_p012_post_rtpt_pre_rtps(...) \
 	gte_sw(C2_SXY0, R_PrimCursor, O_(Poly_G4,p0)) \
 ,	gte_sw(C2_SXY1, R_PrimCursor, O_(Poly_G4,p1)) \
@@ -128,10 +125,8 @@ WORD_COUNT(mac_gte_store_g4_p012_post_rtpt_pre_rtps, 3)
 
 /* atom_dbg_skip */
 /* Words: 1; Stores the V3 screen coord to the G4's p3 slot.
- * PIPELINE: post-RTPS (SXY2 holds v3.screen because RTPS writes its
- * single-vertex result to SXY2; SXY0 still holds v0.screen from the
- * earlier RTPT — DO NOT read SXY0 here, that's the bug this name
- * prevents).
+ * PIPELINE: post-RTPS (SXY2 holds v3.screen because RTPS writes its single-vertex result to SXY2;
+ * SXY0 still holds v0.screen from the earlier RTPT.
  */
 #define mac_gte_store_g4_p3_post_rtps(...) \
 	gte_sw(C2_SXY2, R_PrimCursor, O_(Poly_G4,p3))
diff --git a/code/duffle/lottes_tape.h b/code/duffle/lottes_tape.h
index 86aedbb..569f2df 100644
--- a/code/duffle/lottes_tape.h
+++ b/code/duffle/lottes_tape.h
@@ -193,11 +193,8 @@ MipsAtomComp_Proc_(ac_format_g4_color, {
 /* Words: 3; Stores the 3 transformed (V2_S2 screen) vertices of the
  * G4 triangle portion to p0/p1/p2.
  * PIPELINE: post-RTPT, pre-RTPS (SXY0=v0.screen, SXY1=v1.screen, SXY2=v2.screen). 
- * MUST be called BEFORE V3-RTPS, otherwise SXY0/1/2
- * get overwritten with v3 (RTPS writes only to SXY2, but to keep the
- * three registers aligned with v0/v1/v2 you must store before RTPS).
- * The macro name declares the pipeline position; check #6 (GTE state-
- * machine validation) verifies the call site matches the declaration. */
+ * MUST be called BEFORE V3-RTPS, otherwise SXY0/1/2 get overwritten with v3
+ * (RTPS writes only to SXY2, but to keep the three registers aligned with v0/v1/v2 you must store before RTPS). */
 atom_dbg_skip MipsAtomComp_(ac_gte_store_g4_p012_post_rtpt_pre_rtps) {
 	gte_sw(C2_SXY0, R_PrimCursor, O_(Poly_G4,p0)),
 	gte_sw(C2_SXY1, R_PrimCursor, O_(Poly_G4,p1)),
@@ -205,10 +202,8 @@ atom_dbg_skip MipsAtomComp_(ac_gte_store_g4_p012_post_rtpt_pre_rtps) {
 };
 
 /* Words: 1; Stores the V3 screen coord to the G4's p3 slot.
- * PIPELINE: post-RTPS (SXY2 holds v3.screen because RTPS writes its
- * single-vertex result to SXY2; SXY0 still holds v0.screen from the
- * earlier RTPT — DO NOT read SXY0 here, that's the bug this name
- * prevents).
+ * PIPELINE: post-RTPS (SXY2 holds v3.screen because RTPS writes its single-vertex result to SXY2;
+ * SXY0 still holds v0.screen from the earlier RTPT.
  */
 atom_dbg_skip MipsAtomComp_(ac_gte_store_g4_p3_post_rtps) { gte_sw(C2_SXY2, R_PrimCursor, O_(Poly_G4,p3)) };
 
diff --git a/code/gte_hello/gen/gte_hello.offsets.h b/code/gte_hello/gen/gte_hello.offsets.h
index d5370e6..ce2aa87 100644
--- a/code/gte_hello/gen/gte_hello.offsets.h
+++ b/code/gte_hello/gen/gte_hello.offsets.h
@@ -5,9 +5,9 @@
 #pragma region hello_gte_tape
 
 
-// --- atom: cube_g4_face (87 words) ---
+// --- atom: cube_g4_face (79 words) ---
 
-#define _atom_offset_cull_cube_g4_face_exit           48
+#define _atom_offset_cull_cube_g4_face_exit           44
 #define _atom_offset_bounds_chk_cube_g4_face_exit     12
 
 enum {
diff --git a/code/gte_hello/hello_gte_tape.c b/code/gte_hello/hello_gte_tape.c
index 0b3cf75..5851084 100644
--- a/code/gte_hello/hello_gte_tape.c
+++ b/code/gte_hello/hello_gte_tape.c
@@ -47,12 +47,11 @@ MipsAtom_(cube_g4_face) atom_info(atom_phase(cube_g4),
 	load_half_u(R_T3, R_FaceCursor, 3 * S_(S2)),
 
 	mac_gte_load_tri_verts(R_T0, R_T1, R_T2),
-	nop2, gte_cmdw_rotate_translate_perspective_triple,
-	nop2, gte_cmdw_nclip,
+	nop2, gte_cmdw_rotate_translate_perspective_triple, // required cpu -> gte delay slot
+	gte_cmdw_nclip,
 
-	nop2,  gte_mv_from_data_r(R_T0, C2_MAC0),
-	nop,
-	branch_le_zero(R_T0, atom_offset(cull, cube_g4_face_exit)), nop,
+	gte_mv_from_data_r(R_T0, C2_MAC0),
+	nop, branch_le_zero(R_T0, atom_offset(cull, cube_g4_face_exit)), nop,
 
 	store_word(R_0, R_PrimCursor, O_(Poly_G4, tag)),
 	mac_format_g4_color(
@@ -69,8 +68,8 @@ MipsAtom_(cube_g4_face) atom_info(atom_phase(cube_g4),
 	nop2, gte_cmdw_rotate_translate_perspective_single,
 	mac_gte_store_g4_p3_post_rtps(),
 
-	nop2, gte_cmdw_avg_sort_z4,
-	nop2, gte_mv_from_data_r(R_T1, C2_OTZ),
+	gte_cmdw_avg_sort_z4,
+	gte_mv_from_data_r(R_T1, C2_OTZ),
 
 	add_ui(      R_AT, R_0,  OrderingTbl_Len),
 	set_lt_u(    R_AT, R_T1, R_AT),