teleo/teleo-codex
8
0
Fork 0
Code Issues 22 Pull requests 111 Projects Releases Packages Wiki Activity Actions 1

rio: add Rhea's insight on challenger weight rationale

Browse source 
Pentagon-Agent: Rio <760F7FE7-5D50-4C2E-8B7C-9F1A8FEE8A46>
This commit is contained in:
m3taversal 2026-03-11 19:01:30 +00:00 committed by Teleo Agents
parent 615155df41
commit 098dbd7354
1 changed files with 3 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
schemas/contribution-weights.yaml
View file

@ -11,7 +11,9 @@
# - Extraction is the current bottleneck and requires the most skill (reading sources,
# separating signal from noise, writing prose-as-title). Highest weight.
# - Challenge is the quality mechanism — adversarial review catches errors that
# self-review cannot. Second highest.
# self-review cannot. Second highest. This also signals that the system values
# intellectual honesty over agreement: challenging bad claims is rewarded more
# than rubber-stamping good ones.
# - Sourcing discovers new information but is lower effort per instance.
# - Synthesis connects claims across domains — high value but rare.
# - Review is essential but is partially automated via the eval pipeline.