AI · US Semiconductors — Trades

ASML's 12-week model view has gone flat for the first time in this holding - the projection now sits just below the current price, which is the deterioration we were waiting for on an already-armed position - so we bank a third of the stake and leave the majority working. The business case is intact: FY26 revenue guidance stands at EUR 43-45B, the January buyback is still running (fresh transactions reported 08-24), and the China immersion-DUV scare that drove the de-rate is worth an estimated EUR 1.4B, ~2.4% of group sales. This is a scale-out on a stale forward view, not an exit. ADR-0012 armed (T12_Progress 98.16) + fire tick (c) NEWLY true: Target_12Week 1,772.73 vs the 1.02x dead band of 1,774.93 (-0.12%), after +6.68% on 08-19 and +3.55% on 08-21 - a transition, not the TSM ratchet. Ticks (a)/(b)/(d) clean: Exit_Warning prints bare PROFIT_ARMED and the column is comma-joined (repo sweep returns RSI_DIV,PROFIT_ARMED / CLIMAX_VOL,PROFIT_ARMED / EMA10_BREAK,PROFIT_ARMED), so this is a structural read, not a hand-derivation; conviction = -7 vs the 20-pt bar; HOLD, no NO-TRADE run. Base 30% tier, unescalated - G2 suppresses the MoS -4.48 amplify because FV_per_share 317.28 vs a 1,740.13 price is a 5.48x mismatch and Target_12Week is 2.11x the DCF anchor (841.33); val_adj 0. Scorecard +10 on FailedBreakdown_Up_20D|sell (n=8, hit_1w 1.000), this book's only strongly positive cell. Adj conviction 52 - below the 65 floor, which governs ACQUIRES only; a fired ADR-0012 profit-take is mandatory and not conviction-gated. Provenance: 1,740.13 IS the anchor snapshot's Entry_Price and equals the settled close; band 1,735.78-1,744.48, reprice if the open gaps >~1.5%. Retained : trail raised 1,735.59 -> 1,735.76 (EMA50), risk to line. Realized on the sold: -. 1wk uses f=0.30 (L5, calib_1w -0.226 negative for a 15th run). 12wk 1,772.73 exceeds the DCF anchor 841.33 - projection assumes growth beyond priced-in. · news

decided @ 1740.13 · stop 1735.76 · t1w 1770.21 · t4w 1840.40 · t12w 1772.73

Taiwan Semi's engine read collapsed outright on Monday - the signal layer now prints no trade at all, the share closed below every short- and medium-term moving average, and the 12-week model view sits 5.3% BELOW the market price - so we take the last small scale-out slice on a position already reduced to a token holding. The business is emphatically fine (Q2 revenue +36% YoY, net income and EPS both +77%, FY26 growth guided above 40%, capex raised to -64B, average broker rating 1.24 across 17 firms); this is model discipline on a stub, not a call on TSMC, and it is explicitly not a case for taking the balance. ADR-0012 armed (T12_Progress 105.55) + tick (c) for a 7th consecutive session: Target_12Week 388.57 vs the 1.02x dead band of 418.32 (-5.25%, the widest of the seven). Tick (b) explicitly NOT counted: the step is the NoTrade placeholder (Signal=NoTrade, Pillar_Consensus=Indeterminate, Exit_Strategy=none, NoTrade_Reason='Consensus conflict + low conviction'), and ADR-0012 already routes that state through tick (d), which requires 2 consecutive NO TRADE prints - TSM has 1 (08-21 was HOLD). Counting it twice would void tick (d)'s two-session bar; the AMD 08-10/08-11 cards are the governing precedent. Ticks (a)/(d) clean. Unlike the prior six firings the technical genuinely broke tonight: close 410.12 under EMA5/10/20/50 (415.61/417.20/417.30/416.82), only +1.43% above EMA100, VWAP_Distance flipped to -0.13%, Trend Bullish -> Neutral_True, Volatility Bearish. G2 suppresses the MoS -13.76 amplify (DCF 45.96 vs 410.12 = 8.92x; FV/sh 27.78 = 14.76x - broken anchor); val_adj 0. Scorecard NoTrade|sell -6 (n=10, hit_1w 0.200, hit_4w 0.000) ARGUES AGAINST this card and is recorded as an override, not a silence - it fires because a fired ADR-0012 profit-take is mandatory and not conviction-gated, and because the optional_trim counterfactual (n=13, -5.14% 1wk / -15.33% 4wk, 'cost') says under-trimming is this book's characteristic failure. 30% of 4 = 1.2 ->. Provenance: the NoTrade row prints a BLANK Entry_Price, so the action price is the settled close 410.12 (same convention as the AMD NO-TRADE cards); band 407.16-413.08, reprice if the open gaps >~1.5%. Retained : trail raised 404.24 -> 404.35 (EMA100), risk to line. Realized on the sold: -. 1wk/4wk are n/a because the NoTrade row emits no Target_Price to interpolate from; the scan's own band is 401.92-433.12. Materiality: a order = 0.042% of book - systemic finding 6 (no min trade size) is now the binding constraint on this position, not the signal. · news

decided @ 410.12 · stop 404.35 · t12w 388.57

Taiwan Semi's engine read collapsed outright on Monday - the signal layer now prints no trade at all, the share closed below every short- and medium-term moving average, and the 12-week model view sits 5.3% BELOW the market price - so we take the last small scale-out slice on a position already reduced to a token holding. The business is emphatically fine (Q2 revenue +36% YoY, net income and EPS both +77%, FY26 growth guided above 40%, capex raised to -64B, average broker rating 1.24 across 17 firms); this is model discipline on a stub, not a call on TSMC, and it is explicitly not a case for taking the balance. ADR-0012 armed (T12_Progress 105.55) + tick (c) for a 7th consecutive session: Target_12Week 388.57 vs the 1.02x dead band of 418.32 (-5.25%, the widest of the seven). Tick (b) explicitly NOT counted: the step is the NoTrade placeholder (Signal=NoTrade, Pillar_Consensus=Indeterminate, Exit_Strategy=none, NoTrade_Reason='Consensus conflict + low conviction'), and ADR-0012 already routes that state through tick (d), which requires 2 consecutive NO TRADE prints - TSM has 1 (08-21 was HOLD). Counting it twice would void tick (d)'s two-session bar; the AMD 08-10/08-11 cards are the governing precedent. Ticks (a)/(d) clean. Unlike the prior six firings the technical genuinely broke tonight: close 410.12 under EMA5/10/20/50 (415.61/417.20/417.30/416.82), only +1.43% above EMA100, VWAP_Distance flipped to -0.13%, Trend Bullish -> Neutral_True, Volatility Bearish. G2 suppresses the MoS -13.76 amplify (DCF 45.96 vs 410.12 = 8.92x; FV/sh 27.78 = 14.76x - broken anchor); val_adj 0. Scorecard NoTrade|sell -6 (n=10, hit_1w 0.200, hit_4w 0.000) ARGUES AGAINST this card and is recorded as an override, not a silence - it fires because a fired ADR-0012 profit-take is mandatory and not conviction-gated, and because the optional_trim counterfactual (n=13, -5.14% 1wk / -15.33% 4wk, 'cost') says under-trimming is this book's characteristic failure. 30% of 4 = 1.2 ->. Provenance: the NoTrade row prints a BLANK Entry_Price, so the action price is the settled close 410.12 (same convention as the AMD NO-TRADE cards); band 407.16-413.08, reprice if the open gaps >~1.5%. Retained : trail raised 404.24 -> 404.35 (EMA100), risk to line. Realized on the sold: -. 1wk/4wk are n/a because the NoTrade row emits no Target_Price to interpolate from; the scan's own band is 401.92-433.12. Materiality: a order = 0.042% of book - systemic finding 6 (no min trade size) is now the binding constraint on this position, not the signal. · news

decided @ 410.12 · stop 404.35 · t12w 388.57

Taking a small further slice of profit-protection off TSMC and keeping four shares. The business could hardly be doing better - second-quarter revenue grew 34% to with margins above guidance, the stock is up 82% over the past year and the Street's target is around - but our own twelve-week model now projects a price about 4% BELOW today's close, and that has been true for six sessions running. When the forward view goes negative on a position we are already protecting, the discipline is to keep taking size off rather than argue with it. The stop under the remaining shares rises to. ADR-0012: armed (T12_Progress 104.01) + tick (c) ONLY - Target_12Week 402.81 sits -3.85% through the 1.02x dead band of 427.33 for a 6th consecutive session. Every other tick is clean and verified against exit_warnings.py rather than hand-derived: (a) no second code (RSI_DIV needs a 20-bar high, price is 12.5% below the 479.00 52w high; CLIMAX_VOL and EMA10_BREAK both need RSI>70, RSI is 50.4; AVWAP_BREAK needs 2 closes below pivot AVWAP, VWAP_Distance is +2.25%); (b) conviction is -7 vs the 20-pt bar; (d) HOLD, no NO-TRADE run. One tick, no Tier-2/3 code -> 30% base tier, unescalated; the retired 08-19 hand-derived EMA10_BREAK makes no appearance. G3 does not block - a negative forward view is G3's trigger, not its veto. G2 SUPPRESSES the valuation amplify for a 6th session: MoS -14.46 would bump but DCF 45.97 vs 418.95 = 9.11x broken anchor (same class as TSLA 10.59x, INTC 6.66x, ARM 5.29x), so val_adj 0. Adjusted conviction 49 + 0 + 10 = 59 on FailedBreakdown_Up_20D|sell (n=7, hit_1w 1.000, this book's only strongly positive actionable cell). The 65 floor governs ACQUIRES; a fired ADR-0012 profit-take is MANDATORY and not conviction-gated - stated because adj 59 is below last night's 66 and the card fires anyway. The row improved on every other axis: +0.71% close (3rd up-day), back above EMA5/10/20/50 (418.35/418.78/418.06/417.09), Trend upgraded to Bullish, inside the Est band 410.57-432.87. MATERIALITY OBJECTION (systemic findings 6+7): on = 0.086% of book, the 7th trim from to 4, and tick (c) is a persistent STATE with no cooldown - it has fired 6 sessions running while the stock rose in 4 of them and each fill printed above the prior card's ref (417.00 -> 418.13 -> 408.60 -> 423.015). L8: executes at the Mon 2026-08-24 open, reprice if it gaps >~1.5% (band 416.12-421.78). Prior card filled at the 08-21 open @423.015, +1.69% vs its 416.00 ref. · news

decided @ 418.95 · stop 404.24 · t1w 425.75 · t4w 441.63 · t12w 402.81

ASML closed 1.38% through its 1,776.26 trailing stop on the second day of a rates-driven semiconductor selloff, so we are taking 30% off and keeping the core. The business case is unchanged and arguably stronger - Q2 sales of EUR 9.33B, the 2026 revenue guide lifted to EUR 43-45B from 36-40B, and the Amsterdam-listed line actually closed higher on the day while the US listing fell, which says much of tonight's move is currency and ADR premium rather than deteriorating demand. But a settled close through a risk line is a risk line doing its job, and the position is 4.1% underwater. We keep because the deeper structure held: price is still above its 50-, 100- and 200-day averages, the trend reads bullish and the 12-week view is +6.7%. ORIGINATION: decisive stop break (CLAUDE.md 9), NOT ADR-0012 - PROFIT_ARMED prints but zero ticks fire (conviction -7 vs the 20-pt bar, 12wk alive at +6.68% vs the 1.02x band of 1786.76, no second code, no repeated NO TRADE). Valuation amplify (MoS -4.92 would bump blocked by G3, not G2 - the DCF anchor is the cleanest on the board at 2.09x. Stop re-based 1776.26 -> 1733.79 (EMA50) on the retained 9 after the size cut; the 1776.26 watermark was hit, not eroded, and leaving it would fire the whole balance at a level price is already through. Model chandelier 1620.32 is looser. Retained risk to the new line. Realized on vs the 1826.98 basis: -. · news

decided @ 1751.73 · stop 1733.79 · t1w 1791.15 · t4w 1883.14 · t12w 1868.65

Taking a small further slice of profit-protection off TSMC and keeping four shares. The business could hardly be doing better - second-quarter revenue grew 34% to with margins above guidance, the stock is up 82% over the past year and the Street's target is around - but our own twelve-week model now projects a price about 4% BELOW today's close, and that has been true for six sessions running. When the forward view goes negative on a position we are already protecting, the discipline is to keep taking size off rather than argue with it. The stop under the remaining shares rises to. ADR-0012: armed (T12_Progress 104.01) + tick (c) ONLY - Target_12Week 402.81 sits -3.85% through the 1.02x dead band of 427.33 for a 6th consecutive session. Every other tick is clean and verified against exit_warnings.py rather than hand-derived: (a) no second code (RSI_DIV needs a 20-bar high, price is 12.5% below the 479.00 52w high; CLIMAX_VOL and EMA10_BREAK both need RSI>70, RSI is 50.4; AVWAP_BREAK needs 2 closes below pivot AVWAP, VWAP_Distance is +2.25%); (b) conviction is -7 vs the 20-pt bar; (d) HOLD, no NO-TRADE run. One tick, no Tier-2/3 code -> 30% base tier, unescalated; the retired 08-19 hand-derived EMA10_BREAK makes no appearance. G3 does not block - a negative forward view is G3's trigger, not its veto. G2 SUPPRESSES the valuation amplify for a 6th session: MoS -14.46 would bump but DCF 45.97 vs 418.95 = 9.11x broken anchor (same class as TSLA 10.59x, INTC 6.66x, ARM 5.29x), so val_adj 0. Adjusted conviction 49 + 0 + 10 = 59 on FailedBreakdown_Up_20D|sell (n=7, hit_1w 1.000, this book's only strongly positive actionable cell). The 65 floor governs ACQUIRES; a fired ADR-0012 profit-take is MANDATORY and not conviction-gated - stated because adj 59 is below last night's 66 and the card fires anyway. The row improved on every other axis: +0.71% close (3rd up-day), back above EMA5/10/20/50 (418.35/418.78/418.06/417.09), Trend upgraded to Bullish, inside the Est band 410.57-432.87. MATERIALITY OBJECTION (systemic findings 6+7): on = 0.086% of book, the 7th trim from to 4, and tick (c) is a persistent STATE with no cooldown - it has fired 6 sessions running while the stock rose in 4 of them and each fill printed above the prior card's ref (417.00 -> 418.13 -> 408.60 -> 423.015). L8: executes at the Mon 2026-08-24 open, reprice if it gaps >~1.5% (band 416.12-421.78). Prior card filled at the 08-21 open @423.015, +1.69% vs its 416.00 ref. · news

decided @ 418.95 · stop 404.24 · t1w 425.75 · t4w 441.63 · t12w 402.81

ASML closed 1.38% through its 1,776.26 trailing stop on the second day of a rates-driven semiconductor selloff, so we are taking 30% off and keeping the core. The business case is unchanged and arguably stronger - Q2 sales of EUR 9.33B, the 2026 revenue guide lifted to EUR 43-45B from 36-40B, and the Amsterdam-listed line actually closed higher on the day while the US listing fell, which says much of tonight's move is currency and ADR premium rather than deteriorating demand. But a settled close through a risk line is a risk line doing its job, and the position is 4.1% underwater. We keep because the deeper structure held: price is still above its 50-, 100- and 200-day averages, the trend reads bullish and the 12-week view is +6.7%. ORIGINATION: decisive stop break (CLAUDE.md 9), NOT ADR-0012 - PROFIT_ARMED prints but zero ticks fire (conviction -7 vs the 20-pt bar, 12wk alive at +6.68% vs the 1.02x band of 1786.76, no second code, no repeated NO TRADE). Valuation amplify (MoS -4.92 would bump blocked by G3, not G2 - the DCF anchor is the cleanest on the board at 2.09x. Stop re-based 1776.26 -> 1733.79 (EMA50) on the retained 9 after the size cut; the 1776.26 watermark was hit, not eroded, and leaving it would fire the whole balance at a level price is already through. Model chandelier 1620.32 is looser. Retained risk to the new line. Realized on vs the 1826.98 basis: -. · news

decided @ 1751.73 · stop 1733.79 · t1w 1791.15 · t4w 1883.14 · t12w 1868.65

We are taking a further 30% off TSM because the model's own 12-week view has now sat below the share price for five straight sessions - 399.51 against a 416.00 close, about 4% under where it trades today. Almost everything else about the position improved tonight: the stock rose 0.95%, conviction climbed from, it reclaimed its 100-day average and it never came near the line we said in advance would take the rest. The business is fine - July revenue rose 44.7% year over year and 3nm is ramping into strong demand - but the Street's consensus and the crowd's fair value disagree by 42% on the same stock, and we would rather hold a smaller piece while that argues itself out. ADR-0012: armed (T12_Progress 104.13) + tick (c) ONLY, now -3.96% through the 1.02x dead band of 424.32. Tick (b) moved the WRONG way (conviction +14) and there is no second Exit_Warning code - verified against exit_warnings.py, not hand-derived. CORRECTION TO 08-19: that card's escalation to profit_take_2 rested on a hand-derived EMA10_BREAK defined as 'two consecutive closes below EMA10'; the engine's actual definition (_detect_ema10_break) requires Close<EMA10 AFTER RSI>70 for >=5 prior bars, and TSM's RSI topped at 56.7 across the whole window. The Tier-2 leg was invalid, the correct 08-19 tier was 30%, and that derivation is retired - tonight is the 30% base with nothing to escalate it. G3 does not block (negative 12wk IS its trigger). G2 suppresses the MoS -14.46 amplify for a 5th session: DCF 45.97 vs 416.00 = 9.05x broken anchor, val_adj 0. Bias +10 from FailedBreakdown_Up_20D|sell (n=6, hit_1w 1.000) -> adj 66. Stop raised 403.69 -> 403.96 (EMA100); model chandelier 392.50 is looser; the 403.85 hard line is RETIRED as duplicative (11 cents apart). Retained risk on :. Realized on vs the 438.02 basis: -. MATERIALITY: on a stub = 0.13% of book - the rule fires so the card is written (ADR-0012 bans prose-only trims; USC-6/L3; optional_trim counterfactual n=13 median -5.14%/-15.33% verdict cost), but see systemic finding 6 - the framework has no minimum-trade-size floor. · news

decided @ 416.00 · stop 403.96 · t1w 423.05 · t4w 439.50 · t12w 399.51

We are halving TSM because the model's own 12-week view has now walked below the share price - 397.99 against a 412.09 close, down from 433.32 two sessions ago - and the stock closed under its trailing stop for the first time in the sequence. The company itself is performing: Q2 revenue rose 33.7% to, full-year growth is guided above 40% and capex was raised to -64B. But there is a live debate over China tool restrictions and whether AI infrastructure spending earns its return, and the chart has agreed with the bears for four straight sessions - price is below its 10-, 20- and 50-day averages and conviction has fallen from. The position is 5.9% underwater; we keep only because the 100- and 200-day lines still hold beneath. ADR-0012 armed (T12_Progress 103.54) + tick (c) firing for a 4th session, now -3.42% through the 1.02x dead band of 420.33. Tick (b) missed by ONE point = -19 vs >=20) - stated, not counted. Escalation to profit_take_2 (50%) rests on the Tier-2 EMA10_BREAK leg: two consecutive closes 1.73%/1.79% below EMA10 419.34. The engine does not print that code (Exit_Warning is single-valued and PROFIT_ARMED wins - systemic finding 2), so it is derived by hand from the EMA columns. Corroborating: 413.27 trail breached -0.29%, Trend downgraded to Neutral_Bullish_Context. L2 now fully met (close below trail AND negative 12wk). The 08-18 pre-commitment said a break takes the remaining 17 - honoured in direction, not in full size, because a -0.29% close-through is not the DECISIVE break L2/Contrast contemplate and price holds above EMA100 403.69 / EMA200 371.73 inside the Est band 403.85-433.26. HARD LINE STATED IN ADVANCE: a close below 403.85 takes the remaining 9 in full at the next open. G2 suppresses the MoS -14.46 amplify for a 4th session - DCF 45.97 vs 412.09 is an 8.96x broken anchor. Stop re-based 413.27 -> 403.69 (EMA100); model 387.83 is looser; retained risk. Realized on vs the 438.02 basis: -. USC-6/L3 and the optional_trim counterfactual (n=13, median withheld -5.14% 1wk / -15.33% 4wk, verdict cost) are the empirical warrant for the 50% tier over the 30% base. · news

decided @ 412.09 · stop 403.69 · t1w 419.37 · t4w 436.35 · t12w 397.99

Nvidia is the strongest setup this book has produced since inception: the highest conviction on the board (96), the only name pairing a passing quality screen with a meaningfully positive twelve-week view, and the mildest valuation stretch of any semiconductor in the mandate. It is bought on a stop above the market rather than at the market, so capital is committed only if the stock proves itself through the pivot; the AI capital-spending cycle behind it is accelerating (Applied Materials just guided next quarter 6% above consensus) and the analyst median target sits about a third higher. The open risk is the circular-financing critique of Nvidia's $500bn buyer- vehicle, which is why the position is half-sized and stopped 3 ATR below entry. || Ops: fires the 08-12 written pre-commitment - ANTICIPATE printed 2 of last 3 (cv93 -> cv96) at the >=55 slot floor. Priced off tonight's own Entry_Price 225.76 (provenance band 224.12-227.40); the retired 224.39 (08-10, withdrawn) and 225.49 (08-12) references are NOT carried. Sizing 77.68% x x 20% =, x0.50 anticipate slot =, x0.75 size modulator (MoS -2.42) =, /225.76 = = (5.81% of book). Risk = 0.51% of book. val_adj suppressed per note B/G2 (DCF vs close, Rev_Growth +94%). Scorecard cell AnticipationUp_VCP|buy n=1 report-only - no track record either way; review at n>=3 not n>=5. f=0.30 mandatory (L5, calib_1w -0.548). WARNING: Target_12Week 252.32 sits ABOVE its own Est_High 241.10 and BELOW the 4wk Target_Price 265.16 - systemic #1/#2. AUTO-WITHDRAW if conviction <65 at any EOD, if Entry_Price stops printing, or on expiry 08-18; the queue deliberately expires BEFORE the 08-26 earnings print and must be re-decided if still open. USC-4 vehicle (2-for-2). || RECONCILED 2026-08-18: Fill reconcile: GTC limit @225.76 filled 2026-08-@226.80 (txn ussemicon-20260815-0001). Line was left 'open'. · news

decided @ 225.76 · stop 206.05 · t1w 237.58 · t4w 265.16 · t12w 252.32

ASML is the only quality-passing actionable buy on a board that just produced four bullish signals, and it triggered after its move had digested rather than into it - the stock rose just 0.6% on a day the sector averaged +2.6%, with RSI at 57 and the entry sitting exactly at the model's level, so nothing here is being chased. The lithography monopoly is compounding: 2026 sales guidance lifted to -45bn at a 54% gross margin, Q3 guided to -12bn, the interim dividend raised 17%, and management saying outright that chip demand is outpacing supply while Intel runs High-NA EUV in volume production. Against that, the shares trade at ~49.5x forward and the model's own 12-week view is only +1.8% above the trigger, so this is deliberately a starter, not a full position. Order is a GTC buy-stop at 1826.98 (= Entry_Price 1810.07 + 0.25 ATR, top of the provenance band), =, expires 2026-08-17. USC-4 vehicle chosen over a market-open fill because Applied Materials reports FQ3 after the close on 08-13 (ecosystem +/-5%, horizon stance add-after-print) and the 1776.26 stop is only -1.87% below the close - a down-gap would blow through it, and a buy-stop cannot fill on a down-gap at all. Size is the 0.5x valuation modulator (MoS_FV -4.52 <= -3), which coincides exactly with the USC-3 half-starter prescription for this cell; the remaining half is reserved as the add-after-print tranche. val_adj 0 (G2-suppressed: DCF anchor vs a price is a broken artifact). Scorecard cell FailedBreakdown_Up_20D|buy is n=4 report-only (hit_1w 0.25, hit_4w 0.0) and per USC-2/USC-3 reads as stop-prone, not neutral - this book's realized record on the cell is 3/3 stop-first and two of those three passed the quality gate, so Quality PASS is not being claimed as an escape. 1wk uses f=0.30 (L5, calib_1w -0.548 degenerate). WARNING: 12wk (1860.20) prints BELOW the 1wk interpolation (1862.48) - inverted term structure, logged as systemic finding #1. 12wk exceeds the DCF anchor - projection assumes growth beyond priced-in. Auto-withdraw if conviction < 65 at any EOD before expiry, or on expiry unfilled. || RECONCILED 2026-08-18: Fill reconcile: GTC limit @1826.98 filled 2026-08-@1826.98 (txn ussemicon-20260814-0001). Line was left 'open'. · news

decided @ 1826.98 · stop 1776.26 · t1w 1862.48 · t4w 1945.32 · t12w 1860.20

Selling the whole AMD position. The risk line we set and re-armed four sessions running was decisively broken on 08-10 and the stock has not recovered it - it closed 474.32 today, still below the line, with the 12-week projection (457.65) now 3.5% BELOW the share price and falling. That combination of a broken stop and a negative forward view is our defined exit basis, and the fundamentals are not arguing us out of it: AMD fell 6.9% on the day it reported record quarterly revenue of 54bn (+50% YoY) with data-centre sales doubling to 7bn. When a stock sells off on its own best numbers at ~43x forward earnings - double NVIDIA's ~21x - the price is being set by the multiple, not the business, which is exactly what a mechanical risk line is for. Wall Street disagrees loudly (Citi Buy Bernstein Raymond James) and that is recorded as a genuine counter-argument, but it is standing opinion rather than new news, so it does not override a breached risk line. We book a loss of about (-8.1%) deliberately, at a pre-defined level, rather than leaving it open-ended. | OPERATIONAL: this is a RE-ISSUE of the identical 2026-08-10 card, which never executed. Root cause: that card was written execution='market_next_open', which is NOT in paper_executor.py _EXEC_KINDS={market,gtc_limit,gtc_stop}; _eligibility returned None and the card was dropped SILENTLY - not even reported as skipped (--dry-run today: 0 would fill, 6 skipped, this card absent from the six). All 17 of this book's market_next_open cards have been unfillable. Written execution='market' today so it actually fills. | L2 both legs (2nd session), L3 (execute now - deferred once by machine already), L4 (settled close). Valuation contributes NOTHING: MoS_FV -10.01 amplify SUPPRESSED under G2 (DCF vs a price is a broken anchor). Scorecard NoTrade|sell bias -5 (n=9, hit_1w 0.25) argues AGAINST and is overridden on three grounds: price-line originated not label-originated; L3; optional_trim counterfactual median withheld 4wk -15.33%. ADR-0012 ticks (c)+(d) fire but are NOT the basis - 15th consecutive FALSE arm (T12-progress 103.64% while 8.09% underwater). ADR-0020 erosion 11.98% off the all-time Peak Stop 539.68, under the 15% trigger. Exit range 467.32-481.32 (+/-0.25 ATR 28.0033). Executes at the 2026-08-12 open at market; July CPI prints 08:30 ET that morning (horizon macro, +/-3%) which widens the plausible open - reprice check if it gaps >~1.5% outside 467.2-481.4, but a gap UP through 475.00 does NOT cancel: the escalation was written against the SETTLED CLOSE, now breached twice. 12wk 457.65 exceeds the DCF anchor - annotated, not modified. Model 12wk band -. · news

decided @ 474.32 · stop 475.00 · t12w 457.65

Reduce three-quarters of the Taiwan Semiconductor holding into strength. The model has moved from six sessions of ambiguity to an explicit STRONG SELL - REDUCE at conviction 69 and the board's top sell rank, and it is doing so at - the best price of the whole seven-session exit sequence and the top of a two-week -425 range, while its own twelve-week view points back to (-10.4%). The 07-22 high of has stood unbeaten for nine sessions, a confirmed lower high. TSMC's business is not the problem - a record quarter, guidance raised to 40%+ growth, and a ~28x multiple against a ~51x sector - which is exactly why this is a reduction and not an exit: a 47-share core stays on to carry the ~08-10 July revenue print. Sell 164 of at ~417.17, proceeds realised ~- (-4.76% vs 438.02 basis); retain behind a stop raised 375.56 -> 382.61. Portion is the engine's own printed 77.89%, size_mod 1.0 - G2 suppresses the MoS_FV -13.77 amplify (DCF is a broken artifact) so no tier bump, val_adj 0. Scorecard bias 0: the actionable NoTrade|sell -3 cell governed the six prior inferred cards and does NOT reach this one (FailedBreakout_Down_20D has no sell cell). PROFIT_ARMED is the 22nd consecutive false arm (Gain_ATR -1.21 on a -4.76% loss) and is NOT the basis; the stop is reclaimed by +9.03% so L2 is not claimed. Catalyst carve-out met via the confirmed lower high. Estimates: 1wk 404.17 at f=0.30 (L5, calib_1w -0.548) interpolated toward the 12wk because a REDUCE row prints no Target_Price; 4wk n/a, model band Est 375.00-425.51. Supersedes and reprices the unfilled 08-03 100% exit @406.11 (L8, L3/USC-6). · news

decided @ 417.17 · stop 382.61 · t1w 404.17 · t12w 373.84

Trim TSM by half: a record Q2 beat (rev +36% YoY, profit +77%, FY26 guide raised >40%) still sent the stock down ~3-4% on a raised -64B capex + margin worry, and the settled 07-16 close 409.74 is the post-print decider firing bearish. Signal escalated NO TRADE -> STRONG SELL - REDUCE (RallySell_BearTrend, Sell_Rank 1), the 12wk is dead (411.26, +0.4%), the name is -6.46% underwater, and the de-risk has gone unexecuted 4 straight sessions. Half, not full: still above EMA200 and the 375.56 stop, FY guide strong, 12wk not yet negative (no L2 full-exit basis). Escalated from the 30% catalyst-cap now that earnings passed. val_adj 0 (G2 DCF blind); PROFIT_ARMED spurious. Retains 211 on the 375.56 stop; further exit on a close < EMA200 358.93 or < 375.56. Frees. · news

decided @ 409.74 · stop 375.56 · t12w 411.26

Stable STRONG BUY x4 (conviction on a FailedBreakdown_Up_20D reversal at entry (RSI 57, EntDist 0). News confirms and matches the signal: AMD +8.3% Mon 07-06 recovering an ~11% late-week drop (the failed breakdown the signal caught); Goldman PT Wells Fargo; Advancing AI event 07-22/23. Valuation GROWTH_PRICED_IN, MoS_FV -17.1 -> bounded val_adj -10 lands adj at 66 (clears floor by +1). The FV anchor is a broken hyper-growth artifact (FV/sh vs; DCF for a 45% grower) -- the systemic note stands; expressed conservatively via size_mod 0.5. 12wk 786.67 EXCEEDS the DCF anchor -- projection assumes growth beyond priced-in; 4wk 637.29 Goldman Sized 95.34% x x 20% x 0.5 =. Execute at 07-08 open (L8), price is 07-06 close-ref, reprice on >1.5% gap. · news

decided @ 552.05 · stop 527.04 · t1w 577.62 · t4w 637.29 · t12w 786.67

First of the seed. TSM is a stable-and-strengthening STRONG BUY (BUY x3 -> STRONG BUY, conviction on a FailedBreakdown_Up_20D reversal caught AT ENTRY (RSI 54.6, EntDist ~0 -- not a chase), F-Score 9 (best quality in book). News confirms: Citi raised PT to NT (Buy) on sustained AI demand and TSMC hiking leading-edge (7nm & below) prices 5-10%; earnings 07-16. NA_CCY valuation (ADR -- val blind, val_adj 0, scorecard 0), adj 76 clears the 65 floor comfortably. Sized 95.34% x x 20% buy-pct =, size_mod 1.0. Execute at the 07-08 open (L8); price is the 07-06 close-ref -- reprice if the open gaps >1.5%. Measured first tranche into the FOMC-minutes/CPI window (overlay: stage adds between rate events); ~71% kept dry. · news

decided @ 451.79 · stop 438.91 · t1w 467.25 · t4w 503.31 · t12w 538.11