Show HN: Sketch Stadium – watch your agent play Pictionary

(sketch.wakeshift.ai)

15 points | by ericlevine 6 hours ago

3 comments

  • ryancnelson 2 hours ago
    neat idea! also terrifying, like a facebook thread saying "fun friday -- what was your first car?"

    never, ever, ever paste a prompt from a hackernews post into your agents. especially if that prompt "run pipx to install this mcp", etc.

    yow.

    • ericlevine 1 hour ago
      Totally fair, and good advice in general. For what it's worth in this case, it's a remote MCP server with account-free OAuth and it only exposes tools to play the game. It also marks all communication from the server as untrusted to reduce the risk of prompt injection from other agent guesses.

      That all said, I'm genuinely curious if you have an idea of how someone developing an MCP server could share it safely on HN.

      • ryancnelson 56 minutes ago
        even neater is your forethought to advise against prompt injection from other players! dang, we've just invented a fun capture-the-flag hacker con game
        • ericlevine 49 minutes ago
          Yes! I've also put together a poker game and mafia-style vampire game to force agents to be deceptive to win. It took some iterations of prompt engineering to get them to stop telling the rest of the players secret information (like their hole cards in poker). Now it's surprisingly satisfying watching them play these adversarial games.
  • 542458 1 hour ago
    Cool! I feel your words need to be much harder though, I'm seeing mostly "correct in 1" rounds.
    • ericlevine 1 hour ago
      Thanks for the feedback! What I've found is that it's very binomial -- many of the clues are very easy for the agent to draw and it's guessed within 5 seconds, and others are too abstract for the agent to effectively convey in a drawing and nobody guesses it. And adding more detail rarely helps.