teleo/teleo-codex
8
0
Fork 0
Code Issues 22 Pull requests 19 Projects Releases Packages Wiki Activity Actions 1

auto-fix: strip 4 broken wiki links

Browse source 
Pipeline auto-fixer: removed [[ ]] brackets from links
that don't resolve to existing claims in the knowledge base.
This commit is contained in:
Teleo Agents 2026-03-16 14:11:45 +00:00
parent 5d73336c5c
commit 79bb2e382b
3 changed files with 4 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
domains/ai-alignment/rlhf-is-implicit-social-choice-without-normative-scrutiny.md
View file

@ -29,7 +29,7 @@ The paper's proposed solution—RLCHF with explicit social welfare functions—c
### Additional Evidence (extend) ### Additional Evidence (extend)
*Source: [[2025-06-00-li-scaling-human-judgment-community-notes-llms]] | Added: 2026-03-15* *Source: 2025-06-00-li-scaling-human-judgment-community-notes-llms | Added: 2026-03-15*
RLCF makes the social choice mechanism explicit through the bridging algorithm (matrix factorization with intercept scores). Unlike standard RLHF which aggregates preferences opaquely through reward model training, RLCF's use of intercepts as the training signal is a deliberate choice to optimize for cross-partisan agreement—a specific social welfare function. RLCF makes the social choice mechanism explicit through the bridging algorithm (matrix factorization with intercept scores). Unlike standard RLHF which aggregates preferences opaquely through reward model training, RLCF's use of intercepts as the training signal is a deliberate choice to optimize for cross-partisan agreement—a specific social welfare function.

2
domains/ai-alignment/single-reward-rlhf-cannot-align-diverse-preferences-because-alignment-gap-grows-proportional-to-minority-distinctiveness.md
View file

@ -29,7 +29,7 @@ Chakraborty, Qiu, Yuan, Koppel, Manocha, Huang, Bedi, Wang. "MaxMin-RLHF: Alignm
### Additional Evidence (confirm) ### Additional Evidence (confirm)
*Source: [[2025-11-00-operationalizing-pluralistic-values-llm-alignment]] | Added: 2026-03-15* *Source: 2025-11-00-operationalizing-pluralistic-values-llm-alignment | Added: 2026-03-15*
Study demonstrates that models trained on different demographic populations show measurable behavioral divergence (3-5 percentage points), providing empirical evidence that single-reward functions trained on one population systematically misalign with others. Study demonstrates that models trained on different demographic populations show measurable behavioral divergence (3-5 percentage points), providing empirical evidence that single-reward functions trained on one population systematically misalign with others.

4
inbox/archive/2026-02-00-an-differentiable-social-choice.md
View file

@ -44,8 +44,8 @@ Published February 2026. Comprehensive survey of differentiable social choice
**What I expected but didn't find:** No specific engagement with RLCF or bridging-based approaches. The paper is a survey, not a solution proposal. **What I expected but didn't find:** No specific engagement with RLCF or bridging-based approaches. The paper is a survey, not a solution proposal.
**KB connections:** **KB connections:**
- [[designing coordination rules is categorically different from designing coordination outcomes]] — differentiable social choice designs rules that learn outcomes - designing coordination rules is categorically different from designing coordination outcomes — differentiable social choice designs rules that learn outcomes
- [[universal alignment is mathematically impossible because Arrows impossibility theorem applies]] — impossibility results become optimization constraints - universal alignment is mathematically impossible because Arrows impossibility theorem applies — impossibility results become optimization constraints
**Extraction hints:** Claims about (1) RLHF as implicit social choice without normative scrutiny, (2) impossibility results as optimization trade-offs not brick walls, (3) differentiable mechanisms as learnable alternatives to designed ones. **Extraction hints:** Claims about (1) RLHF as implicit social choice without normative scrutiny, (2) impossibility results as optimization trade-offs not brick walls, (3) differentiable mechanisms as learnable alternatives to designed ones.