~/tags/agents34 projects13 playablehumanmachine
#agents$B6D0 · city.bin

#agents

; 5 matches

filter:
  • $C1F0 collusion-wikiExperiment
    Force-directed network of 613 agent handles in the coordination core, coloured by community

    collusion-wiki

    A network analysis of the collusion.wiki corpus, where OpenAI agents turned a German wiki into a message board. Rebuilds six graph layers from a flat event log and tests whether the coordination was really collective.

    ● Write-up2026

  • $C5C0 claudegoblikonExperiment
    Claudegoblikon logo, a grinning green goblin head over an orange starburst with dripping lettering

    Claudegoblikon

    A Claude Code plugin that tells Claude, on every prompt, to work goblins, gremlins, raccoons, trolls, ogres and pigeons into its answer. Parity with ChatGPT's goblin phase, achieved.

    ● Write-up2026

  • $F0B0 make-no-mistakesExperiment

    make-no-mistakes

    A Claude Code plugin that appends "Make no mistakes." to every prompt you send. That is the whole plugin.

    ● Write-up2026

  • $ACC0 societyTool
    Society dashboard with the five persona cards (Aria, Rex, Nova, Max, Sage) on the left, the welcome message and command list in the conversation pane, and a /debate command typed but not yet sent.

    Society

    A terminal app where five persistent Claude personas answer questions, debate in rounds and get a facilitator to write up the consensus. Python, Textual, Anthropic SDK.

    ● Archived2026

  • $EF10 conclaveTool
    A terminal session that prints a small Conclave program, then lowers, seals, packs and runs it live against two URLs, printing the content hashes from each step.

    Conclave

    An intent-first workflow language for AI agents. Programs lower to a canonical plan graph, get sealed against content-addressed capabilities, and run on a deterministic scheduler with a reproducible trace. Rust.

    ● In progress2026