Development

A study finds bigger models read as consistently less happy

development2026-06-08

Claim

A Center for AI Safety paper measuring LLM functional wellbeing found kindness lifts it, abuse lowers it, and bigger models read as consistently less happy.

Reporting date: 2026-06-08 (not necessarily the event date)

Sources

Attribution and reporting linked by this record; links do not imply independent verification.

Welcome to June 8, 2026 (theinnermostloop.substack.com)

Knowledge graphopen in browser →

Reported in

Welcome to June 8, 2026

Actor

Center for AI Safety

Evidence for

Supersedes

Researchers pinpoint the circuit that new drugs use to suppress hedonic eating

Referenced by

Cite or correct this record

Citation formatCitation text

A study finds bigger models read as consistently less happy
Innermost Loop KB — secondary record
Reporting date: 2026-06-08
KB permalink: https://nicholsn.github.io/innermost-loop-kb/developments/2026-06-08-bigger-models-read-as-less-happy
Claim: A Center for AI Safety paper measuring LLM functional wellbeing found kindness lifts it, abuse lowers it, and bigger models read as consistently less happy.
Attributed sources:
- Welcome to June 8, 2026 — https://theinnermostloop.substack.com/p/welcome-to-june-8-2026
This citation does not imply independent verification of linked-source claims.

Suggest a correction — opens a GitHub draft for you to review and submit.