x

LESSWRONG

LW

Aether — LessWrong

Aether

Edited by Joey Yudelson last updated 29th May 2026

Aether is a small AI safety research organization.

Add Posts

1

1

Posts tagged Aether

1

79Hidden Reasoning in LLMs: A Taxonomy

Rauno Arike, RohanS, Shubhorup Biswas

10mo

12

1

52Extract-and-Evaluate Monitoring Can Significantly Enhance CoT Monitor Performance (Research Note)

Rauno Arike, RohanS, Shubhorup Biswas

10mo

7

1

5013 Arguments About a Transition to Neuralese AIs

7mo

14

1

50Should We Train Against (CoT) Monitors?

2mo

7

1

46A List of Research Directions in Character Training

3mo

21

1

41Exploring Reinforcement Learning Effects on Chain-of-Thought Legibility

Julian H, RohanS, Baram Sosis, vedant-badoni, The-Turtle

5mo

3

1

34Efficiently Detecting Hidden Reasoning with a Small Predictor Model

RohanS, Vishnu Vardhan Sai Lanka, yaumeng, daria

11mo

3

1

33How we spent our first two weeks as an independent AI safety research group

RohanS, Rauno Arike, Shubhorup Biswas

10mo

0

1

26[Paper] How does information access affect LLM monitors' ability to detect sabotage?

Rauno Arike, Raja Moreno, RohanS, Shubhorup Biswas, Francis Rhys Ward

4mo

0

1

22Aether is hiring technical AI safety researchers

Rauno Arike, RohanS, Shubhorup Biswas

5mo

0

1

17We Should Study the Analogy Between Inoculation Prompting Non-Robustness, Negation Neglect, and Backdoor Non-Robustness

Vladimir Ivanov

16d

3

Add Posts