Development

Hallucinated claims fall 52.5% on high-stakes prompts

development2026-05-06

Claim

OpenAI's GPT-5.5 Instant produces 52.5% fewer hallucinated claims than its predecessor on high-stakes prompts in medicine, law and finance, and the same lineage took the top spot on the hardest ultra-long-horizon coding benchmark.

Reported metric: -52.5%

Reporting date: 2026-05-06 (not necessarily the event date)

Sources

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

Welcome to May 6, 2026 (theinnermostloop.substack.com)

Knowledge graphopen in browser →

Reported in

Welcome to May 6, 2026

Actor

OpenAI

Evidence for

Supersedes

Tuning for warmth raises error rates by up to thirty points

Referenced by

Welcome to May 6, 2026

Cite or correct this record

Citation formatCitation text

Hallucinated claims fall 52.5% on high-stakes prompts
Innermost Loop KB — secondary record
Reporting date: 2026-05-06
KB permalink: https://nicholsn.github.io/innermost-loop-kb/developments/2026-05-06-hallucinations-fall-by-half
Claim: OpenAI's GPT-5.5 Instant produces 52.5% fewer hallucinated claims than its predecessor on high-stakes prompts in medicine, law and finance, and the same lineage took the top spot on the hardest ultra-long-horizon coding benchmark.
Attributed sources:
- Welcome to May 6, 2026 — https://theinnermostloop.substack.com/p/welcome-to-may-6-2026
This citation does not imply independent verification of linked-source claims.

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