Metadata
| Source Table | entities |
| Source ID | sam-toyer |
| Entity Type | person |
| Description | AI safety researcher at Anthropic. PhD from UC Berkeley. Works on alignment techniques and robustness of AI systems. Research on reward hacking, specification gaming, and safe reinforcement learning. |
| Children | — |
| Created | Mar 29, 2026, 10:41 PM |
| Updated | Oct 12, 2026, 4:25 PM |
| Synced | Oct 12, 2026, 4:25 PM |
Record Data
id | sam-toyer |
wikiId | — |
stableId | Sam Toyer(person) |
entityType | person |
title | Sam Toyer |
description | AI safety researcher at Anthropic. PhD from UC Berkeley. Works on alignment techniques and robustness of AI systems. Research on reward hacking, specification gaming, and safe reinforcement learning. |
website | — |
tags | [ "ai-safety", "alignment" ] |
clusters | — |
status | — |
lastUpdated | 2026-03 |
customFields | — |
relatedEntries | — |
metadata | — |
Debug info
Thing ID: sid_0oOPM1i5lg
Source Table: entities
Source ID: sam-toyer
Entity Type: person