x
This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
LW
Login
Aether — LessWrong
Aether
Edited by
Joey Yudelson
last updated
24th Jun 2026
Aether
is an AI safety research organization.
Subscribe
Discussion
1
Subscribe
Discussion
1
Posts tagged
Aether
Most Relevant
2
280
Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models
Anders Cairns Woodruff
,
Francis Rhys Ward
,
Dewi Gould
,
Rauno Arike
,
Jason R Brown
,
Jo Jiao
,
wlanderson
,
ariana_azarbal
,
harrymayne
,
Patrick Leask
,
Twm Stone
,
Josh Hills
,
Ida Caspary
,
Shubhorup Biswas
,
Julian Stastny
3mo
23
2
168
How concerned should we be about Astra's recurrent architecture?
Rauno Arike
10d
28
2
64
How might continual learning affect safety and alignment?
Rauno Arike
,
RohanS
,
Owen Terry
,
Achu Menon
,
Zhijing Jin
,
Francis Rhys Ward
,
Seth Herd
3mo
2
2
49
Implications of Continual Learning for LLM Agents: Introduction
RohanS
,
Rauno Arike
,
Owen Terry
,
Achu Menon
,
Zhijing Jin
,
Francis Rhys Ward
,
Seth Herd
3mo
0
2
32
What's Continual Learning, and Why Might We Expect To See It In Advanced LLM Agents?
RohanS
,
Rauno Arike
,
Owen Terry
,
Achu Menon
,
Zhijing Jin
,
Francis Rhys Ward
,
Seth Herd
3mo
2
1
83
The Most Forbidden Technique is not always forbidden
Rauno Arike
2mo
4
1
80
Hidden Reasoning in LLMs: A Taxonomy
Ω
Rauno Arike
,
RohanS
,
Shubhorup Biswas
1y
Ω
12
1
57
Held-out Monitors Sometimes Degrade, Even When Not Trained Against
Joey Yudelson
1mo
0
1
53
13 Arguments About a Transition to Neuralese AIs
Rauno Arike
10mo
14
1
52
Extract-and-Evaluate Monitoring Can Significantly Enhance CoT Monitor Performance (Research Note)
Ω
Rauno Arike
,
RohanS
,
Shubhorup Biswas
1y
Ω
7
1
52
Should We Train Against (CoT) Monitors?
RohanS
5mo
7
1
49
A List of Research Directions in Character Training
Rauno Arike
6mo
21
1
47
Angles of attack for continual learning safety
Rauno Arike
,
RohanS
,
Owen Terry
,
Achu Menon
,
Zhijing Jin
,
Francis Rhys Ward
,
Seth Herd
3mo
0
1
42
Exploring Reinforcement Learning Effects on Chain-of-Thought Legibility
Julian H
,
RohanS
,
Baram Sosis
,
vedant-badoni
,
The-Turtle
8mo
3
1
34
How we spent our first two weeks as an independent AI safety research group
RohanS
,
Rauno Arike
,
Shubhorup Biswas
1y
0