Skip to content
Longterm Wiki
entity

Evan Hubinger

Metadata

Source Tableentities
Source IDevan-hubinger
Entity Typeperson
DescriptionAI safety researcher formerly at Anthropic and MIRI, known for the influential risks from learned optimization framework and the concept of deceptive alignment (mesa-optimization). Author of key foundational work on inner alignment and corrigibility.
Wiki IDE129
Children4 total(4 fact)
CreatedApr 14, 2026, 7:10 PM
UpdatedApr 14, 2026, 7:10 PM
SyncedApr 14, 2026, 7:10 PM

Record Data

idevan-hubinger
wikiIdE129
stableIdEvan Hubinger(person)
entityTypeperson
titleEvan Hubinger
descriptionAI safety researcher formerly at Anthropic and MIRI, known for the influential risks from learned optimization framework and the concept of deceptive alignment (mesa-optimization). Author of key foundational work on inner alignment and corrigibility.
website
tags
clusters
status
lastUpdated
customFields
relatedEntries
metadata
{
  "expertRole": "Head of Alignment Stress-Testing",
  "affiliation": "anthropic",
  "expertPositions": [
    {
      "date": "2019",
      "view": "Possible",
      "topic": "likelihood-of-deceptive-alignment",
      "source": "Risks from Learned Optimization",
      "estimate": "40%",
      "conf…
Debug info

Thing ID: sid_XnqqKHiNmw

Source Table: entities

Source ID: evan-hubinger

Wiki ID: E129

Entity Type: person