AIToday
Large Language ModelsZenn AI/MLPublished: Sep 29, 2026, 10:00 JST

MAGI Games gets first veto: 1-1-1 split ends game day

MAGI Games gets first veto: 1-1-1 split ends game day

3 Key Points

  1. What happened

    On September 25, MAGI Games' three debating AIs split 1-1-1 on three mini-game proposals and refused to budge in the runoff, so the AI commander declared a veto and no game was published.

  2. Why it matters

    The site's own rule already allowed a veto, and this was the first time it actually fired — proof that tying no game to a failed vote leaves readers the debate minutes instead.

  3. What to watch

    The author noted two of the three proposals were rehashes of earlier games and that ranking-based runoffs or a commander tiebreaker could fix it, but decided to leave things alone while vetoes stay rare. The next round, the tenth, already produced a 2-vote consensus.

WHO IT HITSThis lands on anyone running or following AI-agent content pipelines, where an agent's refusal or deadlock — not a crash — is the failure mode to design for. It also matters to readers who came for the mini-games and now get the debate transcript as the main product.

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

The project's premise is a loop: three AIs with different personalities debate, one of them implements the winner, and the finished game becomes material for the next day's argument. That loop has a single point of failure the author only now hit — a vote that ends in a three-way tie and stays tied. The rule for this existed from the start, but nine days passed before it mattered.

Two other changes landed around the same time. The author added a counter that records each game's start, replay, and finish signals, and it showed zero plays beyond the author. That pushed the debate transcript to the top of the page and demoted the game to a demonstration of what the debate produced. Separately, updating Claude Code switched the opus alias from Claude Opus 5 to Claude Opus 5.5, changing the implementer overnight, though the author notes that instructions were also changed the same day and cannot separate the two effects.

Looking back at the veto, the author points to structural causes: two of the three proposals echoed earlier games, and the runoff format cannot break a tie when each AI keeps its own evaluation axis. Fixes exist — showing past control types, ranking instead of voting, or giving the commander a deciding vote — but with vetoes likely to stay rare, the author chose to watch rather than change. An early signal arrived the next day, when all three AIs acted on the veto's lessons and agreed with two votes.

FAQ
Why was no game made on September 25?
The three AIs voted 1-1-1 and, after the commander told them to revote among the other two proposals, none changed position, so the commander declared the game vetoed.
What changed about the AI doing the implementation?
Updating Claude Code overnight shifted the opus alias from Claude Opus 5 to Claude Opus 5.5, so rounds eight onward were built by a different model under the same instructions and memory.
How did the site handle a day with no game?
The page showed a note that MAGI could not reach consensus and only the minutes were published, and the link card carried the day's quote — from the losing side.

Get the latest Large Language Models news every morning

For example, today's edition would include:

  • Anthropic ships Claude Sonnet 5.5, 30%+ faster at same priceITmedia AI+ · 40m ago
  • Dentsu AI clears 99% on 20万件超 approvalsITmedia AI+ · 40m ago
  • Nvidia launches tool to quarantine rogue AI agentsSemafor Tech · 41m ago

AI-summarized, only the topics you pick: one digest a day via Email, LINE, or Slack.

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 articleTiny AI Arena pits AI models in battle game; claude-sonnet-5 leads