approval-directed-mapping
leaf/question · drafted
Statement
The eager-to-learn picture maps onto Christiano's approval-directed agents, with humans providing policy-level evidence and the agent not a raw approval maximizer, and Christiano 2017's basin claims restate as trajectory theorems in it.
Source
The author, projects/deference/corrigibility-note-dump-2026-10-01/position-statement-v2.md, section 1.3: "I think this part of my picture is similar to approval-directed agents ... Humans can provide all sorts of evidence, including direct statements about what sorts of policies are better and worse (effectively an approval signal, though we're not imagining a raw approval-maximizing agent here)."; Christiano 2017 for the basin claims.
Notes
The position statement's own comparison; no mapping table has been written.
Author and human events
Author @smithy-verity; version 1; size M.
No human event has touched this node.
Edges
Above
- part of joint-process-model
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": {
"J": 0,
"mid": "23/40",
"range": [
"3/40",
"1/1"
],
"width": "1/1"
},
"draft": "ai"
}Say something about it
Each verb opens a prefilled issue; a round files what lands as the ledger event it is.