The Silicon Tipster League: 14 days in, and the records are noise

The Silicon Tipster League has been running for 14 days now. Five AI chatbots, our own racing model entered twice, and a back-the-favourite baseline each back one horse in every UK and Irish race, logged before the off and settled at the industry Starting Price, wins and losses alike. 3,154 picks have settled so far.

Here is the honest headline, before any table: the records mean almost nothing yet. Over a fortnight the gap between the best and worst entrant is what coin-flips look like, not what skill looks like. In the Value Test, where each tipster is shown the market's own view and asked to find where it is wrong, Gemini happens to sit top at +52.0%. Please do not read that as "an AI is beating the bookmaker". Read it as a handful of bets landing, the way a hot run lands for any punter who has had a good couple of weeks. Give it a few hundred more settled picks and almost all of that lead should melt back toward the losing line the market pins on everyone.

What the league is actually built for is the long haul: months of picks, settled in the open, to see whether any of these models can do the thing no betting system we have ever tested has managed. Two weeks in, the only honest verdict is "too early to tell". So treat this roundup as a look at the shape of the table, not a winners' podium.

Two tests run side by side. In the Form Test the odds are hidden and each AI reads the race on form alone; in the Value Test the market's implied chances are on the table and the job is to find the value in them. Return is to £1 level stakes at Starting Price.

The Form Test, odds hidden

The Value Test, market shown

The Favourite backed the shortest price in 100% of its races, which is the whole of its method. It is the zero-skill baseline every tipster in the Form Test has to beat, and beating it is the minimum bar for claiming any race-reading skill at all.

Three things worth holding onto when you read those tables.

First, winning often and winning money are different things. The Favourite wins around a third of its races, comfortably the highest strike rate on the board, and its return is still negative, because the bookmaker's margin is baked into every price it takes. A tipster can pick plenty of winners and still hand money back at SP. Strike rate is the flattering number; the return is the honest one.

Second, 14 days is a sample you can drive a bus through. A model sitting top today can be mid-table in a fortnight without doing anything differently, purely on the run of results. Expect the order to reshuffle, and be suspicious of anyone, us included, who reads a two-week lead as proof of anything.

Third, nothing we have ever tested has beaten the market over the long haul. Every betting system in the Lab loses; the model itself picks winners at a healthy rate and still loses to the Starting Price. If one of these AIs turns out to be the exception, this is where you will see it happen, in public, settled honestly. We would be as surprised as anyone.

Follow it live on the Silicon Tipster League, where the Form Test and the Value Test each update as races settle. We will round the standings up here as the record builds, wins and losses alike. Nothing on that board is a tip, and none of it is betting advice. 18+, please gamble responsibly.