Source≈ 40,000 charsSymbol≈ 400 charsKnowledgeevery claim

The smallest representation of knowledge a model can rebuild.

Symbol distills any source into the smallest possible text that any arbitrary model can rebuild its knowledge from.

This experiment is to see if a universal (or close to universal) language exists between independent models. I.e. does one representation (symbol) decode across all sufficiently capable models.

Why?

  1. It's interesting.
  2. Every agent currently rereads the same sources repeatedly. This is an attempt to see if we can create a new utility at much lower tokens, latency and cost.
  3. Longshot we discover an intermodel language.

Autoresearchers

An autoresearcher runs continuously, evolving a single generic compression method — a strategy that names no topic and is scored across a mix of sources plus a held-out one, so it only survives if it generalizes. The goal is the most distilled artifact possible: the fewest tokens from which the model panel, drawing on its own knowledge, still rebuilds at least 95% of the source's claims — reported net of what the models already knew.

The run has concluded; the snapshot below is every ≥95%-recovery distillation it produced.

autoresearcherfinal snapshot307 distillations · best 3.7% of original (tokens) · only ≥95%-recovery artifacts shown
5%10%20%50%100%178154231307successful distillation #distilled size (% of original)
What the researcher tried
  • discarded

    v14Added explicit MERGE PASS (repeat-until-stable loop merging any two claims sharing subject OR major predicate; drop claims inferentially implied by another); added SPINE+BRANCH encoding for argumentative/planning docs (encode only what a ca

  • kept

    v14Added explicit pre-write CLAIM INVENTORY+DEDUP pass (list all claims, mark DROP if subsumed, write each concept once); back-reference syntax [N]/→[N] to avoid re-encoding prior claims; relaxed format prescription to allow flat-claim-list fo

  • kept

    v13Replaced flat numbered-claim list with mandatory ENTITY-RECORD blocks — each subject written exactly once as a scoped header; ALL claims about it collapsed into typed field:value pairs inside; cross-references by alias only. Structurally pr

  • discarded

    v12Added explicit INTRA-ARTIFACT DEDUP scan as a mandatory final pass (the mars-civilization artifact restates the same roadmap/plan claims 3× and the 100t-reusable claim 2×); also added SYM ROI rule (only declare if alias used ≥3×) and sharpe

  • kept

    v13malformed proposal (no --- delimiter; kept strategy)

Symbolic Distillation

Cold-starting across the source mix on the VM — first lift numbers within minutes.

What we found

Distilling each source to the smallest artifact a panel of three independent models can still rebuild ≥95% of, three results held up.

  1. Compression is bimodal — set by redundancy. Long-form prose compresses ~25×; fact-dense material (whitepapers, reference entries) only 2–4×, because it's already near its information floor — nearly every token carries a claim the model can't infer, so there is little to remove.
  2. It generalizes. The evolved strategy reached 100% recovery on a source it never trained on, and on a decoder model (qwen3-235b) never used during the search — so the compression is a property of the shared model prior, not an overfit to the panel or the corpus.
  3. No inherent inter-model language — for frozen models. Left free to use any script, the token-optimal encoding stays ~95% English plus standard notation: tokenizers and training make English the most meaning-dense representation these models already share. A stronger researcher could push genuinely symbolic encodings, but only when the artifact shipped its own legend — a cipher it was handed, not a shared language. Legend-free foreignness that still decodes is small.
SourceTypeCompression
catmull-pixarprose29×
sacks-unicornsprose26×
aschenbrenner-agiessay25×
apollo-11transcript15×
mars-civilizationfact-dense3.7×
photosynthesisfact-dense3.1×
bitcoinfact-dense2.1×
napoleonfact-dense2.0×

Panel: gpt-5-mini · claude-haiku-4.5 · deepseek-v4-flash. Extractor and judge are held outside the panel; recovery is worst-case across the three decoders.

References