pic-values-updateful
leaf/picture · drafted
Statement
The uncertainty that matters most for alignment, uncertainty about human values, is one an aligned AI treats updatefully, so updateless theory bears only on empirical and logical matters with little engineering consequence.
Source
projects/deference/faf-cleanroom-2026-10-02/sources/unbounded-embedded/01-primary/summer-research-plan-2026--research-ideas-may-2026.md, section Updatelessness: "My loose conjecture, based on my Geometric UDT, is that we should be more updateful about "moral uncertainty" (EG, an aligned AI should be mostly/completely updateful about human values), while remaining updateless about other matters."
Notes
The conjecture quoted above is filed as the shared claim updateful-about-values; this picture is its consequence for the engineering crux.
Author and human events
Author @smithy-verity; version 1; size S.
No human event has touched this node.
Edges
Above
- part of updateless-engineering-value
Ranking (the lens, not the structure)
{
"status": "open",
"diagnosis": null,
"flags": [
"AI number"
],
"V": {
"V_prior": null,
"display": "2",
"headline": 2,
"ref": 2,
"valid": 2,
"weaker": "both"
},
"belief": null,
"draft": "ai"
}Say something about it
Each verb opens a prefilled issue; a round files what lands as the ledger event it is.