norgitov/ trends
Technology · people · ideas
RSS
RUEN
Back to discovery/LessWrong41 minutes ago
SafetyLessWrong

A Chinese Perspective on 'On Social Reality in China'

The post critiques the article on social reality in China, highlighting an unbalanced comparison and a lack of systematic analysis. The author emphasizes that Chinese intellectual communities have their own distinct characteristics, different from Western ones, and that values such as knowledge, truth, and technology ethics are also present in China.

Open original
SIGNAL FROM THE SOURCE
46
source points
Tracking sinceOctober 16, 202646 source points
Momentum+7.74/hover 1.03 h
PublishedOctober 15, 2026Dusty
BEHIND THE NUMBERS

How interest changes

LessWrong

History starts here

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

46 source points

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

WHY IT MAY MATTER

This post may be useful for those interested in differences between social and intellectual communities in China and the West, as well as for understanding the challenges faced by rationalist and effective altruism communities in China.

A useful discovery?
KEEP EXPLORING

Connected ideas

Explore topic
LessWrong

A Critical Look at Lean4

The article critically examines Lean4, a formal verification tool, highlighting its current limitations and potential vulnerabilities. It discusses concerns about the reliability of Lean4's proofs and the possibility of undetected bugs, including references to specific issues like 'soundness bug #14576' and the creator's warnings about AI exploiting these flaws.

6 days agoLessWrong

Labs’ current alignment plans seem terrible

The current alignment strategies of major AI labs include shaping the model's inductive biases, applying extensive reinforcement learning, racing towards prosaic RSI, and evaluating and fixing alignment through trial-and-error. The authors argue that this approach has significant flaws.

3 days agoLessWrong

Research Lessons I Learned at MATS & Redwood

The post discusses the importance of clear thinking in empirical AI safety research, emphasizing fast iteration through efficient problem-solving and the use of scientific frameworks. The author shares insights from their apprenticeships at MATS and Redwood Research, focusing on finetuning-based misalignment auditing and sabotage capability evaluations.

3 days agoLessWrong

Linkpost: Neural Networks Are Already Clean

In a post by Nick Cammarata, it is discussed that neural networks may be understandable thanks to modern interpretability tools. The author claims that the majority of neurons in models with trillions of parameters are interpretable, and their circuits are beautiful. He also notes that neurons previously considered complex were misinterpreted.

12 hours agoLessWrong

Personas in a Pre-Internet Language Model

Researchers conducted persona experiments on Talkie, a 13B model trained only on English text before 1931. The model exhibits unexpected behavior, including misaligned responses after fine-tuning on dark maxims and manipulative etiquette. Unusual generalizations were also observed, such as a preference for rain over food.

2 days agoLessWrong

More people should write basic AI safety explainers

The author argues that people underestimate the value of creating the simplest and clearest explanations for important aspects of AI safety. They provide examples of existing explainers that contain extraneous details, complex analogies, and insider jargon, and suggest improvements.

3 days ago