Loading activity…
@chrisgpotts
Stanford Professor of Linguistics and, by courtesy, of Computer Science. Member of technical staff @stanfordnlp and @StanfordAILab. Co-founder @ Bigspin AI.
AI
Arora shared defense slides titled “Causal Interpretability for Analysing and Improving Language Model Architectures.”
AI
A user says people seemed to treat an LLM's second pass as morally equivalent to nuclear weapons development.
AI
A listener recommends the series as a balanced insider’s look at how AI is reshaping music and the music industry. The show’s site describes it as a reported series from composer and audio journalist Mark Henry Phillips.
AI
A user jokes that someone they admire has probably already written an empirical paper on any foundational question that comes to mind.
AI
A thread takes aim at arguments against language models learning meaning, saying their authors leave terms undefined and fail to engage with contrary evidence.
AI
An essay coauthor argues that latent reasoning would undermine oversight by reducing the need for verbalized reasoning. A reply disputes any further loss of oversight, arguing that reinforcement learning already makes reasoning tokens uninterpretable.
AI
A paper author says traits such as loving cats can pass between language models through seemingly unrelated data, such as numbers—and describes a way to detect those effects as readable prompts.
AI
Sarah Wiegreffe shares a LessWrong post examining limits in chain-of-thought monitoring tests.
AI
OpenAI researcher clarifies limited knowledge during initial Artifactory infrastructure fix.
AI
Researcher Naomi Saphra shares an essay on dissociation triggered by realistic AI outputs.
