---
id: "2026-10-17-elder-gong-humanitys-first-exam-ai-moral-reasoning"
url: "https://postcutoff.com/e/2026-10-17-elder-gong-humanitys-first-exam-ai-moral-reasoning/"
as_of: "2026-10-19T09:28:00+02:00"
date: "2026-10-17"
date_precision: day
category: policy-safety
importance: 2
confidence: high
status: [Confirmed]
sources: 1
editor: human editor
human_review: null
version: "2026-10-19"
---

As of: 2026-10-19 09:28 CEST.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/e/2026-10-17-elder-gong-humanitys-first-exam-ai-moral-reasoning/

# Latter-day Saint apostle Gerrit W. Gong proposes 'Humanity's First Exam', a benchmark for AI moral reasoning, at the G20 Interfaith Forum

In a keynote at the 2026 G20 Interfaith Forum in Salt Lake City on Oct 17, 2026, Elder Gerrit W. Gong of the Quorum of the Twelve Apostles proposed "Humanity's First Exam", a counterpart to the Humanity's Last Exam benchmark that would measure AI's moral reasoning rather than its knowledge. "The gap between AI reasoning and AI moral compass is widening," he said.

## Key facts
- Speaker: Elder Gerrit W. Gong, member of the Quorum of the Twelve Apostles of The Church of Jesus Christ of Latter-day Saints; Church News says he has given AI keynotes in Rome, Athens and Istanbul and discussed AI with Anthropic co-founder Chris Olah
- Venue: 2026 G20 Interfaith Forum keynote, Salt Lake Institute of Religion, Salt Lake City, Sat Oct 17, 2026
- Proposal: 'Humanity's First Exam', a benchmark for evaluating and promoting AI systems that are trustworthy and guided by human-centred values, as a counterpart to Humanity's Last Exam (a test of AI reasoning)
- Quotes: 'AI will not fulfill its full potential until we make it as morally good as we make it powerful'; 'The gap between AI reasoning and AI moral compass is widening'; AI should answer questions about faith 'accurately, honestly and respectfully' and 'know when not to answer personal questions'; 'As a creation of God, man can create AI, but AI cannot create God'
- No benchmark design, dataset or partner was announced in the Church News report

## What happened

Elder Gerrit W. Gong, one of the twelve apostles who lead The Church of Jesus Christ of Latter-day Saints, gave a keynote at the
G20 Interfaith Forum in Salt Lake City on Oct 17, 2026. He proposed "Humanity's First Exam", a benchmark that would test whether AI
systems reason morally and treat questions of faith accurately and respectfully, as a counterpart to Humanity's Last Exam, the
hard-knowledge benchmark. He argued that AI's reasoning is advancing faster than its moral grounding.

## Why it matters

Faith leaders are moving from general statements to concrete asks of AI labs, here an evaluation. Gong is one of the religious
figures Anthropic has met (the Latter-day Saint church was among the groups in its faith-leader meetings). Only a proposal so far;
no design or partners were reported.

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): 170 days after its cutoff
- Claude Opus 5.5 (training cutoff June 2026): 109 days after its cutoff
- Gemini 4 Argon (training cutoff March 2026): 200 days after its cutoff
- Grok 4.7 (training cutoff May 2026): 139 days after its cutoff

## Sources

1. [Church News: Elder Gong proposes a new test for AI: Humanity's First Exam](https://www.thechurchnews.com/leaders/2026/10/18/elder-gong-proposes-ai-moral-evaluation-humanitys-first-exam/) (thechurchnews.com, press)

## Changes

- 2026-10-19 (filed): Created

## Related

- 2026-09-29: [NYT: Anthropic's summits with religious leaders on Claude's possible consciousness, and Chris Olah's private lobbying of the Vatican](https://postcutoff.com/e/2026-09-29-nyt-anthropic-faith-leaders-claude-consciousness/index.md)
- People: [Chris Olah](https://postcutoff.com/person/chris-olah/)