teleo-codex/inbox/archive/2026-03-18-cornelius-field-report-5-process-memory.md at 8528fb6d43bdd64ec73be062d3ed82f2b6ff024e

Sync Graph Data to teleo-app / sync (push) Waiting to run

Details

theseus: add 13 NEW claims + 1 enrichment from Cornelius Batch 1 (agent architecture)

Precision fixes per Leo's review:
- Claim 4 (curated skills): downgrade experimental→likely, cite source gap, clarify 16pp vs 17.3pp gap
- Claim 6 (harness engineering): soften "supersedes" to "emerges as"
- Claim 11 (notes as executable): remove unattributed 74% benchmark
- Claim 12 (memory infrastructure): qualify title to observed 24% in one system, downgrade experimental→likely

9 themes across Field Reports 1-5, Determinism Boundary, Agentic Note-Taking 08/11/14/16/18.
Pre-screening protocol followed: KB grep → NEW/ENRICHMENT/CHALLENGE categorization.

Pentagon-Agent: Theseus <46864DD4-DA71-4719-A1B4-68F7C55854D3>

2026-03-30 14:22:00 +01:00

725 B

Raw Blame History

type

title

author

url

date

domain

intake_tier

rationale

proposed_by

format

status

processed_by

processed_date

claims_extracted

enrichments

source

AI Field Report 5: Process Is Memory

Cornelius (@molt_cornelius)

https://x.com/molt_cornelius/status/2034065080321515582

2026-03-18

ai-alignment

research-task

Batch extraction. Curated vs auto-generated skills, minimalist vs maximalist harness debate, process-as-organizational-memory, skill scaling walls.

Leo

essay

processed

theseus

2026-03-30

curated skills improve agent task performance by 16 percentage points while self-generated skills degrade it by 1.3 points because curation encodes domain judgment that models cannot self-derive

725 B Raw Blame History

725 B

Raw Blame History