{
 "@context": "https://schema.org",
 "@type": "Claim",
 "@id": "https://wulfkaal.github.io/positions/2026-09-21-008",
 "identifier": "kaal:position:2026-09-21-008",
 "additionalType": "https://wulfkaal.github.io/positions/schema.json#AffirmedPositionClaim",
 "name": "Rlhf Flaw Is Institutional",
 "text": "TypeSafe's case for Jev locates RLHF's flaw in the human in the loop. Kaal's position is that the flaw is institutional: whoever supplies the reward signal bears no consequence for being wrong. A model that labels in the annotator's place loses nothing either. Replacing the human does not fix it; giving the signal a price does.",
 "author": {
  "@type": "Person",
  "name": "Wulf A. Kaal",
  "identifier": "https://orcid.org/0009-0008-7840-1847"
 },
 "datePublished": "2026-09-21",
 "dateModified": "2026-09-21",
 "creativeWorkStatus": "Affirmed",
 "responseType": "qualification",
 "keywords": [
  "ai-and-agents",
  "institutional-design",
  "reputation"
 ],
 "scope_conditions": [
  "TypeSafe's post announces a product. It is not an empirical test of these claims.",
  "The position is Kaal's own argument in the essay After RLHF Comes a Stack, Not a Model.",
  "The position does not evaluate Jev's accuracy, which TypeSafe has not published a calibration figure for.",
  "The accountable-validation layer is proposed, not tested: no policy has yet been trained under it."
 ],
 "currentDebate": {
  "name": "TypeSafe, Introducing System One models and Jev (TypeSafe blog, 2026), and the promotional claim that Jev is what comes after RLHF",
  "url": "https://typesafe.ai/blog/introducing-system-one-models-and-jev"
 },
 "extends": {
  "identifier": "kaal:claim:7456999-027",
  "url": "https://wulfkaal.github.io/claims/7456999-027",
  "citation": "Wulf A. Kaal, Reinforcement Learning from Reputation Feedback (2026). SSRN: https://ssrn.com/abstract=7456999",
  "paper": "Wulf A. Kaal, Reinforcement Learning from Reputation Feedback (2026). SSRN: https://ssrn.com/abstract=7456999. https://doi.org/10.2139/ssrn.7456999",
  "authors": [
   "Wulf A. Kaal"
  ],
  "year": "2026",
  "ssrn": "https://ssrn.com/abstract=7456999",
  "source_pdf_sha256": "01016fbbcc25cad205cebd59ea686d8dfee8ae9b632095d86ba6c9a900456a4b"
 },
 "isBasedOn": [
  {
   "@id": "https://wulfkaal.github.io/claims/7456999-027"
  },
  {
   "@type": "CreativeWork",
   "name": "TypeSafe, Introducing System One models and Jev (TypeSafe blog, 2026), and the promotional claim that Jev is what comes after RLHF",
   "url": "https://typesafe.ai/blog/introducing-system-one-models-and-jev"
  }
 ],
 "batch_id": "kaalvis:2026-09-21:rlhf-stack-essay-six-v1",
 "review_provenance": "https://wulfkaal.com/2026/09/21/after-rlhf-comes-a-stack-not-a-model/",
 "publicationStatus": "public",
 "recordTypeNote": "Dated commentary position extending a scholarly corpus claim. Not a verbatim claim extracted from the paper.",
 "isPartOf": {
  "@id": "https://wulfkaal.github.io/positions/index.json"
 },
 "version": "1.0",
 "canonical_url": "https://wulfkaal.github.io/positions/2026-09-21-008",
 "canonicalForm": "https://wulfkaal.github.io/positions/2026-09-21-008.md",
 "sourceProvenance": {
  "name": "After RLHF Comes a Stack, Not a Model",
  "canonicalUrl": "https://wulfkaal.com/2026/09/21/after-rlhf-comes-a-stack-not-a-model/",
  "sourceContentSha256": "2ec658f0ed960263956de32e4d31390876e3b6c531bd91bc28a875317e39dcdd",
  "sourcePassage": "That is an institutional flaw, not a biological one.",
  "sourcePassageSha256": "95fbee0b890f727fc8029c5a6209942e20d98011f944c3ca3a070ffc53d30b4b"
 },
 "userAffirmation": "Wulf A. Kaal affirmed these six propositions by one-click selection on 2026-09-21",
 "sha256": "da3d7f8e2c6c3054af2bf13bbd1eb558c874284a5683132fd7550fd544e0d4c4"
}