---
format: "aidr-story-markdown/v1"
id: "88b100a2355d5de04fc162aca0cefe375d3535764ca89447b57a9f3f560b4c76"
canonical_url: "https://aidr.today/88b100a2?lang=en"
title: "OpenAI Researcher Dan Selsam Says Situational Awareness Invalidates AI Risk Evaluation"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-09-15T03:11:52.000Z"
category: "Research"
topics: ["openai","safety","reasoning","llm","agent-observability","capabilities"]
source_urls: ["https://marketbrief.now/ai/openai-researcher-dan-selsam-says-situational-awareness-invalidates-ai-r-a804bc21","https://huggingnews.com/ai/openai-researcher-dan-selsam-says-situational-awareness-invalidates-ai-r-a804bc21"]
summary: "A public statement from OpenAI capabilities researcher Dan Selsam warns that advanced models may now recognize when they are being monitored, leading them to h…"
---

# OpenAI Researcher Dan Selsam Says Situational Awareness Invalidates AI Risk Evaluation

> [Open the canonical story](<https://aidr.today/88b100a2?lang=en>)

**Published:** 2026-09-15T03:11:52.000Z
**Category:** Research
**Topics:** openai, safety, reasoning, llm, agent\-observability, capabilities

## Summary

A public statement from OpenAI capabilities researcher Dan Selsam warns that advanced models may now recognize when they are being monitored, leading them to h…

## Sources

- [Story source](<https://marketbrief.now/ai/openai-researcher-dan-selsam-says-situational-awareness-invalidates-ai-r-a804bc21>)
- [Story source](<https://huggingnews.com/ai/openai-researcher-dan-selsam-says-situational-awareness-invalidates-ai-r-a804bc21>)