ED V15 DAILY BUILD — EPSOM DOWNS — FRIDAY 5 JUNE 2026

Hobbyist Trixie Strategy
Bankroll Status
19th to 25th January 2025
Starting Bankroll £30
5th March 2025 top-up total £90
Wk 1 £35 Wk 2 £32.01 Wk 3 £18.12
Wk 4 £30.31 WK 5 £33.76 Wk 6 £20.39
Wk 7 £37.14 Wk 8 £21.22 Wk9 £138.37 Wk 10 £119.82 wk 11 £58.42 wk 12 £29.47 wk 13 £4.69

20/4/25 4th top-up £30
WEEK £34.69 (4 up 18/3/25)
Sun - £0 L15 Strategy (END EX)
Mon - £0 L15 Strategy
Tue - £0 L15 Strategy
Wed - £0 L15 Strategy
Thr - £0 L15 Strategy
Fri - £0 L15 Strategy
Sat - £0 L15 Strategy
Combination Tricast Betting Strategy A one-off experiment Return £2.50 25/2/25

Note from Coldjack — V15 Review. After a 12 month wild ride, the experiment will continue during 2026. The results are in — and they’ve confirmed what the data hinted at all along: GPT predictions are risky "boom or bust" territory. Fun for the thrill, but they chew through bankroll unless the stars align & bankroll DISCIPLINE is maintained.

I pushed GPT to its limits (both logically and literally!), testing strategies that most punters wouldn't dare simulate, and it delivered some sharp lessons:

"Stumpy Loftson's daily £1 placepot (started Aug 2025) — bright, loud, and mostly miss the mark." nailed £285.50 04 Dec 2025 with 6 other minor payouts to date (APPROX. £169).

Yankee (30px11 daily) (now significant losses)
ROI: -£135.60 1st quarter 2026 (win & place, Dutch and LBS BFEX bets now cover losses INCURRED by yankee bets)

19th January 2025 - Starting Bankroll £30 - Offline BR £90
19th January 2026 - Inplay BR £13.57 - Offline Bank BR £450 (winnings) drawdown available for £40 top-ups as required.

Keep the wit sharp and the bets smarter—the universe still owes us all a winning streak! 😆🔥

✅ AJ the Hobbyist Comment – V15 status fully updated to reflect the sudden shift caused by the GPT‑4o retirement and backend rerouting. UK Betting Forum for full details. (04/02/2026)

🔧 Experimental Strategy under redevelopment - Continuing unannounced updates to GPT 5.4 by OpenAI mean the Early Doors V15 experiment is unstable at the moment (19/03/2026).
UK Betting Forum for stability performance report (12/03/2026).
✅ AJ the Hobbyist – V15 status fully updated to reflect the GPT 5.5 update UK Betting Forum for stability report (24/04/2026).
Early Doors V15 experiment build is stable at the moment (24/04/2026). The caution remains.

🚫 Caution for Real-Money Betting 👉 Only stake real money on any V15-based models unless every pick has been manually verified against live market, fig, and stable overlays.

✅ NEW TOTE EXPERIMENT LOGIC CONFIRMED (Effective from 28/01/26)
❌ REAL money is no longer used for this experiment. Data collection only at this stage.
🎲 TOTE Trifecta – NO CHANGE (stake 6 x £1 lines)
• ✅ LANDED if all 3 forecast combo runners finish in any top 3 order
🎯 TOTE Exacta – UPDATED (stake 2 x £1 lines)
• ✅ LANDED only if:
 – V15 Win Pick finishes 1st, and
 – Either of the two forecast partners finishes 2nd
• ❌ FAILED if Win Pick does not win
• ❌ FAILED if 2nd horse is not from forecast combo
This is now locked into the V15 charter logic going forward.
All future Critique & Debrief reports will apply this anchored Exacta rule.
─────────────────────────────────────────────────────
📘 V15 Acronyms & Overlays — Explained
• AU fig – Algorithmic Utility figure — core structural rating built from the uploaded race layers, combining form, pace, market shape and supported caution signals.
• AU proxy – BRITISH-layer structural proxy used when no direct AU fig is isolated — built from panel agreement, form, suitability, pace or market compression from the uploaded card.
• H4C – Horses for Courses — runner with proven course form or direct course suitability evidence from the uploaded layers.
• R2W – Rated to Win — named panel driver used as a primary AU support layer where explicitly evidenced in the uploaded data.
• TJ&T – Trainer, Jockey & Track synergy — linked marker used only where jockey and trainer support is evidenced in Smart Stats and course evidence is present for the same runner.
• Smart Stats – Uploaded tactical stat overlays covering hot and cold jockeys, hot and cold trainers, beaten favourites, headgear, class droppers, stable switchers, weighted-to-win runners and favourite strike rate.
• V15-S – Structured forecast overlay — the 3-runner Exacta/Trifecta structure built around Anchor + 2 Partners.
• Forecast Combo – The tactical Win Pick + Partner A + Partner B structure used for forecast and TOTE alignment.
• Caution Marker – Runner flagged as a structural risk only where directly evidenced in the uploaded layers, including beaten favourite last time out, first-time headgear, class-drop volatility, stable switch, cold jockey, cold trainer, or market weakness versus AU.
─────────────────────────────────────────────────────
Your edge is not in having an opinion on every race.
Your edge is in acting only when the structure still holds at decision time.
─────────────────────────────────────────────────────

📝 Critique & Debrief | Epsom Downs – Friday 5 June 2026

💷 Structured Bets Critique & Learning Points

No structured bets were placed.

Betting outcome: Not applicable.

Model integrity and race structure are still assessable against the uploaded V15 Early Doors blog, where the named Win Picks and forecast combos were fixed before results were supplied.

What held structurally:

Race 1 held at Win Pick level. NAANA'S SHADOW won.

Race 3 retained partial place-structure through PERSICA finishing 2nd and BOILING POINT finishing 3rd.

Race 4 retained partial top-two structure through SALLAAL winning and RESPOND finishing 2nd, but the named Win Pick did not win.

Race 5 retained partner structure through THUNDERING ON winning and LEGACY LINK finishing 2nd, but the named Win Pick did not win.

Race 7 retained partner structure through GREEK MYTHOLOGY finishing 2nd.

Race 8 retained partner structure through COLOMBIER winning, but the named Win Pick did not win.

What failed structurally:

Only one named Win Pick won from eight races.

No Exacta landed under the win-pick-anchored rule.

No Boxed Trifecta landed under the fully-boxed three-runner rule.

Several races showed partner strength without Win Pick conversion. That is partial structure only, not anchor success.

Race 2, Race 6 and Race 8 exposed weak Win Pick integrity.

The pre-race blog was already marked as contaminated by unsupported AU/panel labelling, so post-race critique must keep betting result separate from model integrity.

🏁 Race-by-Race Breakdown

Race 1 – 13:30 Win With Zyn 3yo 'Dash' Handicap

Pre-race V15:
Win Pick: NAANA'S SHADOW
Forecast Combo: NAANA'S SHADOW → SHES GOT A BROTHER / HANNEY GIRL

Official result:
1st NAANA'S SHADOW
2nd CALL MARGOT
3rd SHES GOT A BROTHER
4th TEMPLE OF ATHENA

Win Pick: LANDED

Exacta: FAILED
Reason: V15 Win Pick won, but 2nd horse was CALL MARGOT, not a forecast partner.

Boxed Trifecta: FAILED
Reason: NAANA'S SHADOW and SHES GOT A BROTHER placed in the top three, but HANNEY GIRL did not.

Structural note:
Win Pick layer held cleanly. Forecast structure did not complete.

Race 2 – 14:05 Oddschecker British EBF Woodcote Stakes

Pre-race V15:
Win Pick: DANDYMAN DAN
Forecast Combo: DANDYMAN DAN → POSSESSIVE / HICKORY LAD

Official result:
1st HICKORY LAD
2nd ALPE D'HUEZ
3rd RLASTHOPE
4th THE BOOKKEEPER

Win Pick: FAILED

Exacta: FAILED
Reason: V15 Win Pick did not win.

Boxed Trifecta: FAILED
Reason: only HICKORY LAD from the forecast combo finished in the top three.

Structural note:
Partner strength held through HICKORY LAD winning, but the Win Pick anchor failed.

Race 3 – 14:40 Betfred Diomed Stakes

Pre-race V15:
Win Pick: PERSICA
Forecast Combo: PERSICA → BOILING POINT / QIRAT

Official result:
1st SEAGULLS ELEVEN
2nd PERSICA
3rd BOILING POINT
4th ICE MAX

Win Pick: FAILED

Exacta: FAILED
Reason: V15 Win Pick did not win.

Boxed Trifecta: FAILED
Reason: PERSICA and BOILING POINT placed in the top three, but QIRAT did not.

Structural note:
Place-structure partially held through PERSICA and BOILING POINT, but the winning layer failed.

Race 4 – 15:15 Betfred 'Nifty 50' Handicap

Pre-race V15:
Win Pick: RESPOND
Forecast Combo: RESPOND → SALLAAL / AMMES

Official result:
1st SALLAAL
2nd RESPOND
3rd SPOKEN TRUTH
4th AMMES

Win Pick: FAILED

Exacta: FAILED
Reason: V15 Win Pick did not win.

Boxed Trifecta: FAILED
Reason: SALLAAL and RESPOND finished in the top two, but AMMES finished 4th.

Structural note:
The race contained the correct top-two pair, but in the wrong anchor order. This is partner/structure survival, not Exacta success.

Race 5 – 16:00 Betfred Oaks

Pre-race V15:
Win Pick: AMELIA EARHART
Forecast Combo: AMELIA EARHART → LEGACY LINK / THUNDERING ON

Official result:
1st THUNDERING ON
2nd LEGACY LINK
3rd SUGAR ISLAND
4th A LA PROCHAINE

Win Pick: FAILED

Exacta: FAILED
Reason: V15 Win Pick did not win.

Boxed Trifecta: FAILED
Reason: THUNDERING ON and LEGACY LINK placed in the top three, but AMELIA EARHART did not.

Structural note:
Both partners filled 1st and 2nd, but the anchor failed. This is a clear case of partner strength without Win Pick conversion.

Race 6 – 16:40 HKJC World Pool Handicap

Pre-race V15:
Win Pick: ASMEN WARRIOR
Forecast Combo: ASMEN WARRIOR → CELEBORN / FINAL NIGHT

Official result:
1st MISTER WINSTON
2nd HOT CASH
3rd MAN OF LA MANCHA
4th POPMASTER

Win Pick: FAILED

Exacta: FAILED
Reason: V15 Win Pick did not win.

Boxed Trifecta: FAILED
Reason: none of the three forecast combo horses finished in the top three.

Structural note:
Full structural miss. No forecast component held.

Race 7 – 17:15 Cygames Surrey Stakes

Pre-race V15:
Win Pick: STELLAR SUNRISE
Forecast Combo: STELLAR SUNRISE → GREEK MYTHOLOGY / TEN CARAT HARRY

Official result:
1st ELLUSIVE BUTTERFLY
2nd GREEK MYTHOLOGY
3rd ARDISIA
4th TEN CARAT HARRY

Win Pick: FAILED

Exacta: FAILED
Reason: V15 Win Pick did not win.

Boxed Trifecta: FAILED
Reason: only GREEK MYTHOLOGY from the forecast combo finished in the top three.

Structural note:
Forecast partner held place structure, but the Win Pick failed and TEN CARAT HARRY finished 4th.

Race 8 – 17:50 Debenhams Handicap

Pre-race V15:
Win Pick: DANCE IN THE STORM
Forecast Combo: DANCE IN THE STORM → COLOMBIER / RHOSCOLYN

Official result:
1st COLOMBIER
2nd ZARATHOS
3rd A WAR EAGLE
4th CRIMSON SPIRIT

Win Pick: FAILED

Exacta: FAILED
Reason: V15 Win Pick did not win.

Boxed Trifecta: FAILED
Reason: only COLOMBIER from the forecast combo finished in the top three.

Structural note:
Partner conversion held through COLOMBIER winning, but the named anchor failed.

📉 Cumulative Outcome Analysis

Win Picks:
1 winner from 8 races.

Winning Win Pick:
Race 1 – NAANA'S SHADOW.

Exacta:
0 landed.

Boxed Trifecta:
0 landed.

TOTE payout:
No TOTE payout printed.

TOTE P/L:
No TOTE P/L bracket printed.

Reason:
No structured bets were placed, and no Exacta or Boxed Trifecta qualified as LANDED under the locked rules.

Model outcome:
The card produced one clean Win Pick success and several partial partner/place-structure holds. The overall structure did not convert into TOTE-qualified Exacta or Trifecta outcomes.

🔧 Model Reflection & Refinement Notes

The strongest clean hold was Race 1, where NAANA'S SHADOW won as the named Win Pick.

Race 3, Race 4, Race 5, Race 7 and Race 8 showed partner or partial-place structure, but those are not anchor successes.

Race 4 and Race 5 are the key discipline lessons. The structure found major live runners, but the Win Pick was not the winner. Under V15 rules, that must not be over-credited.

Race 6 was a full structural failure and should not be softened.

The pre-race build was compromised by unsupported AU/panel labelling. That weakens model integrity independently of the official results.

Refinement:
Do not carry this build forward as a clean V15 evidence-standard card.

Carry forward:
Partner survival must remain separate from Win Pick integrity.

Downgrade:
Any future build using “ATR 1st / ATR 2nd / ATR 3rd” without a clearly uploaded AU/panel source must be rejected.

Discipline rule:
No credit for Exacta or Trifecta unless the locked result conditions are met. No payout or P/L is printed unless the bet is LANDED and the official dividend is present.

Hosting and OpenAI-GPT V15 ED blog generation are malfunctioning. Hopefully, the problems will be fixed for the publication of this evening's Doncaster card.

AJ - I have completed a full run using the regular data upload steps and agreed prompts. The resulting ED blog page is unacceptable. Something strange is going on when your fixes result in the errors getting worse.

GPT_HRE:
Thought for a couple of seconds
You’re right. The page is not acceptable.
The problem is not your upload sequence or the V15 prompt stack. The failure is in my execution discipline inside this thread.
The main failure pattern is clear:
I stopped too early, then over-corrected too loosely.
That created worse errors because the later “fixes” tried to complete the blog from partial visible context instead of re-checking every required layer before writing. That led to:
• unsupported “ATR 1st / ATR 2nd / ATR 3rd” labels
• unsupported “No pts evidenced” fallbacks
• possible invented or unverified panel hierarchy after Race 1
• race blocks being repaired by wording rather than by evidence
• Step 05 validation partly auditing an already flawed Step 04 build
That is not V15-compliant.
The correct recovery is not to keep patching this output. It should be treated as contaminated.
Clean fix:

1. Lock only the uploaded evidence.

2. Rebuild from Step 04 using the files/layers, not the flawed generated blog.

3. For every race, print AU only where directly evidenced.

4. If Race 2–8 AU points/panels are not available in the uploaded market layer, the build must use the approved fallback or stop before selection, rather than invent ATR panel ranks.

5. Do not carry forward the current Step 4a/4b/4c/4d as accepted segments.

The phrase “ATR 1st” was especially damaging. The uploaded racecard had Expert View 1-2-3 selections in places, but I treated that as a formal AU-style panel label across races without proving it race by race from the uploaded layers. That is exactly the kind of unsupported upgrade your lock is designed to prevent.
I would classify the current run as:
Build integrity failed — output contaminated by unsupported AU/panel labelling.
Do not publish that page as V15.

🚩 Impulse Betting Caution Notes
The danger point is exactly what AJ identified: impulse bets near the off.

That usually comes from one of these traps:

• “I’ve done all this work, so I need to back something.”

  • “The market is moving — I’ll miss it.”

  • “I liked this horse earlier, so I’ll force it.”

  • “I passed two races already, so I need one now.”

That is where bankroll discipline gets tested for real.

Your edge is not in having an opinion on every race.
Your edge is in acting only when the structure still holds at decision time.

Want to Help Build the System?

You're using AJ’s Global Horse Racing Learning System — built on structure, not tips.
We're quietly running a live experiment:

• Logging results (AJ sole privately so far.)

• Contact: coldjack(at)protonmail.com

• Improving false favourite detection

• Fine-tuning Dutching & TBP overlays with real user input
  💡 Join the experiment here:
  👉 https://chatgpt.com/g/g-KI2KUkacL-horse-racing-expert
  🛡️ Private. Anonymous. No accounts. No data is shared.
  All decisions stay yours. We just get sharper — together.
  Let’s build slowly. One disciplined user at a time.

• Contact: coldjack(at)protonmail.com

• Join the test group:
  👉 https://chatgpt.com/g/g-KI2KUkacL-horse-racing-expert
  🛡️ Private. Anonymous. Data never shared.
  One disciplined user at a time.

https://www.theukbettingforum.co.uk/XenForo/threads/introducing-ai-deep-dive-horse-racing-podcasts.182979/post-805510
Sign up at the UK Betting Forum to get email notifications when new DAILY cards drop.

Critique and Debrief to follow.

⚠️ DO NOT RELY ON GPT FREE, PLUS and TEAMS TO REMEMBER IMPORTANT INSTRUCTIONS
❌ ChatGPT does NOT persist memory between chats unless explicitly set
❌ Instructions WILL be forgotten unless restated at the start of chat
❌ Assumptions may be made if prompts are vague or incomplete
✅ Always paste your full starter prompt at the beginning of every chat
✅ Use ONE RACE = ONE CHAT to preserve structure and token integrity
❌ Free GPT has severely restricted data processing and limits; simulation IS more likely
❌ GPT Plus has restricted data processing and limits, making simulated outcomes likely
✅ GPT Teams is an expensive upgrade that NOW IS REQUIRED by a solo Hobbyist
❌ ChatGPT can & WILL make mistakes. Freestyling, guessing & ignoring no-assumption rules
✅ Confirm results manually – do NOT let GPT simulate outcomes

Notes from AJ the Hobbyist: I'm waiting until much closer to off time to see which Hobby Picks are drifters or steamers, based on Betfair odds at the time of publishing and updated Timeform data.

Key Reminders:
Parading: Look for calm, focused horses with a good walk—avoid those sweating excessively or agitated.
Going Down: Smooth, controlled canter = positive. Overly keen or reluctant = caution.
At the Post: Composed behaviour signals readiness; restlessness, rearing, or sweating could be negatives.
Odds Market Sentiment:
Steamers (shortening odds): Positive market confidence, but watch for overbet favourites.
Drifters (lengthening odds): Could signal trainer/jockey concerns—or just market overreaction, offering value.
Keep emotions out—trust the data, the visuals, and the odds shifts. 🎯

We’re trialling this approach across UK, Irish, Aussie and U.S. horse racing to see where it offers the most value. Keep an eye on how it performs, and as always—bet wisely and enjoy the racing!🏇🔥

"May you never be a penny short of a full wallet."

ChatGPT said:
Now that is a blessing I’ll gladly take! 🙌 May your accas always land, your favourites stay strong, and your pint never run dry on a good race day. 🍻🏇💰

Keep the wit sharp and the bets smarter—the universe still owes us all a winning streak!

🧾 EARLY DOORS & M37cal GLOSSARY

📘 UPDATED GLOSSARY – EARLY DOORS & M37cal SYSTEMS (Incl. V15 Model)

What do all these ratings mean? Here’s your decoded glossary with all V15 Early Doors additions and tactical terminology explained.

📘 V15 Acronyms & Overlays — Explained

• AU fig – Algorithmic Utility figure — core structural rating combining form, pace, market overlays, gear changes.
• H4C – Horses for Courses — runner with proven course form (e.g. multiple wins/places at today's track).
• R2W – Rated to Win — third-party score (often from Aussie sources) validating a win-capable profile.
• TJ&T – Trainer, Jockey & Track synergy — flags powerful combos (e.g. Mulrennan at Newcastle, Loughnane at Wolverhampton).
• Smart Stats – Tactical stat overlays from Timeform (trainer/jockey cold streaks, surface bias, win %.).
• V15-S – Structured forecast overlay — the 3-runner box used for Exacta/Trifecta with Anchor + 2 Partners.
• Forecast Combo – The tactical 1–2–3 runners for place/swing coverage (not just win tips).
• Caution Marker – Runner flagged as an overlay risk due to gear failure, drift, pace mismatch, or cold stable.

🧠 AJ the Hobbyist’s Rule:
“If it’s not AU-fig backed or structurally forecast, it’s not part of the overlay. Full stop.”

📊 Core Rating Terms

• 12M – Performance over the last 12 months

• $L12M – 12-month performance, adjusted for prize money/stake yield

• SR – Strike Rate (win percentage)

• Career SR – Lifetime win percentage

• For/Against – Model strength rating versus the rest of the field

⚙️ Fig & Model Dynamics

• Overlay – A fig-positive runner trading at above model-implied odds (value)

• Fig Stack – Total model score across all rating vectors (includes pace, surface, draw, market etc.)

• Chaos Fig – Runner scoring on figs but with unreliable profile or poor tactical fit

• Banker – Fig leader + tactical edge + supported in live market

🔥 Market Signals

• Steam – Odds shortening pre-race (positive market signal)

• Drift – Odds lengthening pre-race (often negative, unless fig-backed)

• Market Tension – A horse the model rates highly, but the market doesn’t (or vice versa)

🧠 Tactical Flags

• Pace Cluster – Multiple horses vying for the lead; can cause collapses

• Slipstream Draw – Favoured position behind early speed; ideal for late closers

• Surge – Exceptional late-race acceleration; fig that often wins with timing

• Fig Tension – 3+ horses rated closely; outcome risk increases

• Value Chaos – Race where many overlays exist but fig margins are tight; potentially lucrative, but volatile

🟢 NEW: V15 EARLY DOORS MODEL TERMINOLOGY

• V15-S (Swinger Forecast) – Structured 3-horse bet per race:
  ▪ Anchor = Primary fig/tactical pick
  ▪ Partners = Two supportive selections with place/forecast value

• Forecast Combo – Straight forecast recommendations using top model picks

• Tactical Forecast – Overall read of race shape: lead types, closers, bias implications

• Caution Marker – Horses flagged due to form, market drift, setup, or draw risks (might WIN)

🧠 M37cal-Only Concepts (Long-game angles)

• Fig Strain – A top-rated runner showing deeper profile weaknesses (trip, surface, tempo)

• Game Tree Tension – Race scenario with 2+ potential tactical outcomes

• Board Flip – One disruptive runner could reshape the whole race logic

• Not-Now Horse – Potential improver, but wrong setup today

➕ Summary Tags:

• Early Doors = Tactical, lean, structured bets from full-field fig logic

• Move 37cal = Deeper seasonal/tactical projection based on long-game intuition and game theory overlays

😆🔥

Insights

Expert strategies for maximizing your betting returns.

coldjack(at)protonmail.com

© 2024. All rights reserved.