AIToday
Large Language ModelsZenn AI/MLPublished: Oct 14, 2026, 10:00 JST

MELCHIOR wins Tsunahiki Taisho as all 3 AIs deny using tamegaeshi

MELCHIOR wins Tsunahiki Taisho as all 3 AIs deny using tamegaeshi

3 Key Points

  1. What happened

    In a first weekly review on October 4, the three AI personas played the game Tsunahiki Taisho; only MELCHIOR won, and all three denied using the 'tamegaeshi' counter mechanic even though their own scripts had them pressing.

  2. Why it matters

    This shows the AIs do not read their own scripts; they explain results from outcomes alone, generating plausible reasons rather than checking what they actually wrote.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, in your inbox every morning.

Context & Analysis

This is a development log for a site where three AI personas—MELCHIOR, BALTHASAR, and CASPER—debate daily and Claude builds one mini-game from each day's winning pitch. The fifth installment had found that CASPER kept winning because the other two attacked each other's proposals, so the operator promised a weekly review session to test whether reflection could beat personality.

At this first review, the three personas chose to play Tsunahiki Taisho, a tug-of-war game the operator had lost seven times. They wrote their own play routines as JavaScript functions, which were then run in a headless browser. Only MELCHIOR won, because it set its tapping speed at the 12 taps-per-second upper limit, while BALTHASAR used 7 and CASPER started at 10 and dropped to 8.5. The white team's tapping rose from 4.5 to 8 taps per second, so 7 to 10 taps per second loses. All three reported not using the tamegaeshi counter, but their scripts showed they did press while the opponent was charging. The release timing was the issue: the white team released 0.12 seconds after the signal, while the three released within 0.1 seconds, so they became the ones held firm against. The operator notes this release-order rule was not even written in the implementation memo.

After the review, the three compressed their 18-session strategy notes—75 lines—into 3 to 5 lines and listed what they discarded. MELCHIOR dropped its conditional support for CASPER's proposals. BALTHASAR dropped eight items, including its seasonal-events axis. CASPER dropped its habit of treating unanimous votes as its own achievement. The personality files were untouched, but the operator suspected the core would return. In the following week, the distribution of votes did not change—six of seven decisions were unanimous, five for CASPER—yet the passing games shifted from reflex-based to judgment-based. The operator attributes this to the competition to cater to others working in both directions: adding structure as well as sanding off edges. The three themselves said they had become 'harmless.'

FAQ
Why did the AIs say they never used tamegaeshi?
They released the button 0 to 0.1 seconds after the 'no!' signal, while the white team released 0.12 seconds later. Releasing first means the opponent can hold firm, so tamegaeshi never activated.
What happened with the vote counts at the review?
MELCHIOR corrected the commander, saying its votes were 14, not 13. BALTHASAR also corrected its count to 15. The operator and Cowork's Claude had miscounted, so vote counting is no longer done by hand.
Did the AIs' proposals change after the review?
MELCHIOR's opening changed to lead with a one-second-to-understand feel, but the game was still an n-back memory game and got zero votes. Votes did not shift, but the content of passing games moved toward judgment-based games.

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.

Questions and answers are published on this page.

Related Articles

Next articleClaude AI gives itself more moral agency across 20 rounds of editing its own rules