One Week in the Rat Farm
Hello, LessWrong. This is a personal introduction diary-ish post and it does not have a…
Recent Articles
View All
LaCy: What Small Language Models Can and Should Learn is Not Just a Question of Loss
This paper was accepted at the Workshop on Memory for LLM-Based Agentic Systems at ICLR.…
A Theoretical Framework for Acoustic Neighbor Embeddings
This paper provides a theoretical framework for interpreting acoustic neighbor embeddings, which are representations of…
CyberAgent moves faster with ChatGPT Enterprise and Codex
CyberAgent uses ChatGPT Enterprise and Codex to securely scale AI adoption, improve quality, and accelerate…
CyberAgent moves faster with ChatGPT Enterprise and Codex
CyberAgent uses ChatGPT Enterprise and Codex to securely scale AI adoption, improve quality, and accelerate…
OpenAI Full Fan Mode Contest: Terms & Conditions
Explore the official terms and conditions for the OpenAI Full Fan Mode Contest, including eligibility,…
Zero-Shot Alignment: Harm Detection via Incongruent Attention Mechanisms
Intro: I made a small adapter (~4.7M parameters) that sits on top of a frozen…
LessWrong Community Weekend 2026 – Applications are open
Applications are openThe event location is AI-inspired by Harry Potter and the Methods of RationalityMain…
“We’re Still Doomed” is Weak Evidence Against Any Particular Past Doom-Aversion Plan
This is mostly a specific case of what Buck said here, but people keep doing…
Poke makes AI agents as easy as sending a text
Poke brings AI agents to everyday users via text message by handling tasks and automations…