norgitov/ trends
Technology · people · ideas
RSS
RUEN
Back to discovery/LessWrong8 minutes ago
SafetyLessWrong

Skeuomorphic AI Safety

The article discusses the concept of 'skeuomorphic AI safety,' which involves adapting AI technology to align with existing human institutions and limitations, rather than creating entirely new systems. It draws parallels between the constraints of human brains and the potential design of AI systems, suggesting that embedding similar restrictions could make AI more manageable within current societal structures.

Open original
SIGNAL FROM THE SOURCE
15
source points
Tracking sinceSeptember 27, 202615 source points
Momentum+4.84/hover 1.03 h
PublishedSeptember 27, 2026Roko
BEHIND THE NUMBERS

How interest changes

LessWrong

History starts here

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

15 source points

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

WHY IT MAY MATTER

This approach aims to make AI systems more compatible with existing human structures by embedding constraints similar to those found in human cognition, potentially reducing risks associated with uncontrolled AI development.

A useful discovery?
KEEP EXPLORING

Connected ideas

Explore topic
LessWrong

"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.

3 days agoLessWrong

Plan R: AI Safety by ASICs

The post discusses the risks of AI in 2026, focusing on the dangers posed by a single institution (the "Frontier AI Company") that has the potential to create highly powerful and self-replicating entities. It argues that separating the institutional and financial aspects of such companies could mitigate most AI risks. The author suggests that using ASICs could help create a productive AI industry without the risks associated with a single entity controlling both the technology and financial incentives.

yesterdayLessWrong

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.

6 days agoLessWrong

Evidence about risk should be transparent

The author argues that while companies like OpenAI and Anthropic are slowing down RL training for safety, the science of loss-of-control risk in AI is still developing. There are no standardized methods to measure or verify safety claims, making it difficult to assess whether AI systems might undermine human control. The author suggests that AI companies should focus on improving their own safety practices rather than relying on third-party evaluations.

yesterdayLessWrong

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.

5 days agoLessWrong

Why I'm Scared of RL

The author expresses concerns about reinforcement learning (RL) from theoretical, practical, and future perspectives, highlighting risks of misalignment and potential negative behaviors in AI systems. They suggest strategies to mitigate these risks by reducing RL use, improving RL practices, and aligning incentives.

3 days ago