🧬 Memory - harrytouloupas · Scour

Why do I believe preserving structure is enough? 🔗Neuroplasticity

lesswrong.com·6d

My Exobrain Software (forays into cyborgism) 🤖AI Agents

lesswrong.com·2d

[Paper] Stringological sequence prediction I 🤖AI Agents

lesswrong.com·3d

Model organisms researchers should check whether high LRs defeat their model organisms 🔗Neuroplasticity

lesswrong.com·13h

How Does an Agent with Multiple Goals Choose a Target? 🤖AI Agents

lesswrong.com·2d

A Fast and Loose Clustering of LLM Benchmarks 🤖AI Agents

lesswrong.com·12h

Reproducing steering against evaluation awareness in a large open-weight model 🤖AI Agents

lesswrong.com·2h

Linear vs Non-linear Probes for Interpretability 🔗Neuroplasticity

lesswrong.com·8h

Exploring capability gated out-of-context reasoning 🤖AI Agents

lesswrong.com·1d

Writing With Robots 🤖AI Agents

lesswrong.com·21h

AI #163: Mythos Quest 🤖AI Agents

lesswrong.com·2d

Self-Aware Confabulation 🔗Neuroplasticity

lesswrong.com·5d

My personal research agenda, version 1. 🤖AI Agents

lesswrong.com·7h

Chocolate Sloths, Tinder, and Moral Backstops 🧠Rationalism

lesswrong.com·1h

Why Alignment Risk Might Peak Before ASI - a Substrate Controller Framework 🤖AI Agents

lesswrong.com·1d

Claude Mythos: The System Card 🧠Rationalism

lesswrong.com·15h

Cheaper/faster/easier makes for step changes (and that's why even current-level LLMs are transformative) 🤖AI Agents

lesswrong.com·5d

Zero-Shot Alignment: Harm Detection via Incongruent Attention Mechanisms 🔗Neuroplasticity

lesswrong.com·1d

Inkhaven menu, part 2 🧠Rationalism

lesswrong.com·8h

My picture of the present in AI 🤖AI Agents

lesswrong.com·2d·Hacker News

Loading more...