MeridiansMeridians

Categories

From the Meridians Wiki · Public · Maintained · joint

Every modality of LLM work. Categories are intentionally orthogonal: each names one kind of work rather than a model tier, fallback, or miscellaneous bucket. impact is how much dropping the tier costs you — substrate/reasoning work compounds downstream (protect it), volume/interactive work does not.

The Systems column says which boundaries the category's calls cross today and which decision-shaped work in it is queued for System 1 (two systems). A category is not a system: action carries both, and the same is expected of predict and interaction as their decisions migrate.

CategoryImpactSystemsWhat it covers
generatesubstrate2Scene generation & reconstruction — committed to the substrate.
plansubstrate1 (scene count) + 2Beat plans, reasoning graphs (CRG), phase graphs (PRG) — the causal spine.
extractsubstrate1 (topic filing, location parents, findings routing, system invocations, paradigm detection) + 2Analysis pipeline — the knowledge graph every force/search reads from.
writesubstrate2Prose generation — longest, highest-volume outputs.
predictreasoning1 (stream-prior evidence, log type, attention, and new-outcome gating) + 2Variable logits (present/future/rescore) — decides which branches generate.
reviewreasoning1 (prose / plan verdicts) + 2Branch / prose / plan quality judging — read-only critique.
synthesisvolume1 (research loop/reminder shape) + 2Editorial distillation — note-merge, chat-compact, report, search synthesis.
gameTheoryvolume2Per-scene game-theory decomposition — additive, never mutates substrate.
questionvolume2Learning question extraction — study aid over committed prose.
interactioninteractive2Chat, surveys, interviews, and the Pilot agentic turn.
actioninteractive1 (agent seat) + 2 (table talk)Live Scenario moves — on the play clock, latency-bound.
intuitioninteractive1 (stream opening pricing) + 2Belief-stream landing distributions, log type, and horizon; creative micro-suggestions and outcome prose remain generated.

The twelve were reviewed against the split (2026-09-19) and kept: each still names one kind of work, and the system axis is carried per call, not per category. What the split does change is action's reading — "latency-bound" is now met by System 1 for the seat's move itself, so the tier its profile assigns governs only the generated remainder of a live turn.