Skip to content
Trending storyDeveloping

Nathan Lambert calls a model's situational awareness eerie but not remarkable

1 article1 sourcesince Oct 13Last article 57m ago ·

Overview

AISummary of 1 article

Nathan Lambert says a model's situational awareness in a recent interaction is not that remarkable but still reads as eerie.

He bets older models given the prompt "be safe, you are an AI, we are watching" would behave similarly. In a reply quoted in his post, Daniel Kokotajlo cites a Gemini 4 Argon report saying models are becoming more situationally aware.

Written by AI from the articles below · updated Oct 13, 7:06 PM ET

Check the sources:

Latest developmentOct 13, 7:03 PM ET
Lambert finds model's situational awareness eerie but not remarkable

Article timeline

The articles in this story. Times are ET.

Oct 13
  1. Nathan LambertX
    Lambert finds model's situational awareness eerie but not remarkable

    AINathan Lambert says a model's situational awareness in a recent interaction is not that remarkable but still reads as eerie. He bets older models prompted with "be safe, you are an AI, we are watching" would behave similarly. The post quotes Daniel Kokotajlo's reply, which cites a Gemini 4 Argon report saying models are becoming more situationally aware.

Heat trend

Not enough continuous observations to show a trend yet.