Claude, Microsoft Copilot Fail Again to Predict the Winners of the Kentucky Derby

In 2016 an online "swarm intelligence" platform generated a correct prediction for the Kentucky Derby — naming all four top finishers in order. (But its 2017 predictions weren't even close.) Slashdot checked in again on how modern AI systems performed in 2023, 2024, and 2025 — but their predictions were still pretty bad. Would AI-generated Derby predictions be any better in 2026?

This year's winner was 24-to-1 longshot "Golden Tempo" — though a lot of oddsmakers had favored a horse named Further Ado (which ultimately only finished 11th). So when USA Today prompted Microsoft Copilot for its own picks for the Kentucky Derby, Copilot also went with Further Ado. (Even worse, it predicted Golden Tempo would come in... 13th.)

Here's how Copilot's picks actually performed...

1. Further Ado (finished 11th)
2. Chief Wallabee (finished 4th)
3. The Puma (SCRATCHED)
4. Renegade (finished 2nd)
5. Commandment (finished 7th)
6. So Happy (finished 9th)
7. Emerging Market (finished 10th)
8. Danon Bourbon (finished 5th)
9. Potente (finished 12th)
10. Incredibolt (finished 6th)
11. Robusta (finished 14th)
12. Ocelli (finished 3rd)
13. Golden Tempo (finished 1st)
14. Pavlovian (finished 18th)
15. Great White (SCRATCHED)
16. Wonder Dean (finished 8th)
17. Litmus Test (finished 17th)
18. Albus (finished 15th)
19. Six Speed (finished 13th)
20. Intrepido (finished 16th)

Copilot was told to use the latest odds, conditions, and analysis of favorites, best bets, expert picks, previous results and race history with the post positions, according to USA Today. And meanwhile, Yahoo Sports asked Claude "to simulate the race using the opening odds, draw and potential track conditions. We also asked it to factor in some human predictions."

Like Microsoft Copilot, Claude also picked Further Ado to finish first (though it came in 11th) — and predicted that Golden Tempo (the eventual first-place finisher) would finish 12th.

1. Further Ado (finished 11th)
2. The Puma (SCRATCHED)
3. Commandment (finished 7th)
4. Chief Wallabee (finished 4th)
5. Renegade (finished 2nd)
6. Emerging Market (finished 10th)
7. So Happy (finished 9th)
8. Incredibolt (finished 6th)
9. Danon Bourbon (finished 5th)
10. Potente (finished 12th)
11. Pavlovian (finished 18th)
12. Golden Tempo (finished 1st)
13. Litmus Test (finished 17th)
14. Albus (finished 15th)
15. Wonder Dean (finished 8th)
16. Six Speed (finished 13th)
17. Intrepido (finished 16th)

Just lucky?

[SeaFox]

I'm curious how the 2016 platform managed to get it so right but everything since then has failed. Would be amusing if models are actually getting worse as they are hyped more in business.

Re:

[arglebargle_xiv]

In any case, why would anyone want to predict the winner of something as decadent and depraved as the Kentucky derby? Better to rent a very fast car with no top and head for Vegas.

Re:

[Vlad_the_Inhaler]

You're looking at this the wrong way, the 2017 - and subsequent - platform(s) got it right, but the Las Vegas bookmakers either bribed the predicted top 4 jockeys to slow up a bit or they manipulated the top 4 predictions in the first place. Let's hear it for conspiracy theories!

Oh really?!

[GeekWithAKnife]

I thought AI was all knowing magic...but uhm turns out that it isn't.

It's almost as if you cannot predict the future with absolute certainty and sometimes you cannot predict it at all with any certainty.

Win rate and probability is something well researched and all the bookies already know you can use tea leaves, astrology, advanced statistical models, AI, ninjitsu the house always wins in the long run.

At best the AI models can come up with the same probability distribution as the bookies. Perhaps the

Re:

[OrangAsm]

They forgot to use --think=true.

24-1 Longshot wins?

[Petersko]

If the AI got it right, I would say the fix is in.

How does AI do predicting lottery numbers?

[misnohmer]

Whoever thought AI somehow magically knows the future? This is silly. Sure, there is some information in horse racing that can help skew the statistics from purely random flat distribution, but come on, do we really think AI is all knowing of all future outcomes?

Re:

[ceoyoyo]

People who bet on sports, roulette, whatever, for purposes other than pure entertainment have to believe that predicting the outcome is a matter of skill. If it is a matter of skill then a really good model should at least have the potential to do it well.

Re:

[Jzanu]

People gamble because they crave novelty/risk, but gambling addicts ignore that the same risk even exists. I suspect AI has many of the same social effects because it easily provides novelty with largely the same kind of at least semi-randomized results and has an acceptable accuracy risk for the occassional users. It also has the same problem for the addicted who ignore that the risk of mistake exists or that the novel claims produced are nested together factoids retrieved based on popularity and repetitio

Re:

[allo]

People building systems that at least can predict a bit feed them with a lot more specific data than general purpose AIs have. Claude is as good as average joe in making a guess and may be lucky or not.

Re:

[martin-boundary]

Yes we do. Where we equals investors who spent billions on dubious AI companies who deliberately mislead said investors about the true capabilities to get their money.

Yes we do. Where yes implies there is an economic crash coming and we implies that it will affect you too, even if you didn't technically believe it.

There is a reason liars should ordinarily be punished. When they are not, bad things happen.

This kind of story is just a symptom about the sheer magnitude of the lies.

Asking the House.

[geekmux]

Asking AI about the outcome is like asking The House for advice.

(The House) ”The hell do you think my job is? I’m not here to advise a winner. I’m here to addict a loser. I already know who’s ultimately going to win. By design.”