norgitov/ trends
Technology · people · ideas
RSS
RUEN
Back to discovery/LessWrong16 minutes ago
SafetyLessWrong

"I am an AI Safety Researcher"

The post discusses the tension between AI safety and capabilities research, arguing that focusing solely on safety can limit the impact of research. It examines the history of interpretability research and suggests that prioritizing safety over capabilities may hinder progress. The author proposes strategies for conducting alignment research without contributing to capabilities development.

Open original
SIGNAL FROM THE SOURCE
30
source points
Tracking sinceSeptember 23, 202630 source points
Momentum+6.89/hover 1.02 h
PublishedSeptember 23, 2026Ashe Vazquez Nuñez
BEHIND THE NUMBERS

How interest changes

LessWrong

History starts here

The chart will appear after repeat observations. The current metric comes from the source.

30 source points

Real observations only. History before source connection is not reconstructed.

WHY IT MAY MATTER

This post provides insights into the challenges of balancing AI safety and capabilities research, offering practical strategies for researchers to focus on alignment without inadvertently advancing capabilities.

A useful discovery?
KEEP EXPLORING

Connected ideas

Explore topic
LessWrong

The Game is Set for a Targeted Memetic Attack on the AI Safety Community

The author discusses potential adversarial memetic attacks targeting the AI safety community, suggesting that false information about dangerous AI incidents could be spread through unverified sources. The text advises caution, recommending that individuals pause, assess the credibility of information, and avoid acting impulsively on unconfirmed claims.

5 days agoLessWrong

Common Mistakes in AI Safety Group Organizing

The text outlines common errors in organizing AI safety groups, suggesting that reading groups often fail due to low participation and lack of shared knowledge. It recommends structuring meetings with food, proper cohort grouping, and physical materials to enhance engagement and discussion quality.

4 days agoLessWrong

We've saved the world before: what the ozone hole teaches us about AI

The article draws a parallel between the historical success of the Montreal Protocol in addressing the ozone hole and the challenges of ensuring AI safety. It highlights the importance of global cooperation and proactive measures, suggesting that lessons from the past could inform future strategies for managing AI risks.

3 days agoLessWrong

AI as Orderly Evacuation vs Stampede

The article compares the development of AI to an orderly evacuation rather than a stampede, emphasizing the importance of careful management to avoid chaos. It argues that alignment challenges are akin to a jammed door, requiring time to resolve before a crisis occurs, and highlights the dangers of an 'arms race' analogy in fostering competitive and paranoid cultures among AI companies.

6 days agoLessWrong

Alignment Midtraining Cracks Under Pressure

The study investigates the effectiveness of alignment midtraining (AMT) under various conditions, revealing that it struggles with distributional shifts and reward underspecification when faced with imperfect data. Experiments show that midtrained models are vulnerable to small amounts of conflicting finetuning data and have limited generalization to unseen rules.

2 days agoLobsters

Flock Cameras Have Security Vulnerabilities and Hard-Coded Credentials

Flock cameras have been found to have security vulnerabilities and hard-coded credentials.

6 days ago