Mechanistic Anomaly Detection Research Update
Interim report on ongoing work on mechanistic anomaly detection
Latest
🔥 Meet Yi-Large Turbo: the powerful, cost-effective upgrade to Yi-Large. Faster and more affordable at only $0.19 per 1M tokens for input and outpu…
🔥 Meet Yi-Large Turbo: the powerful, cost-effective upgrade to Yi-Large. Faster and more affordable at only $0.19 per 1M tokens for input and output. Ideal for…
We Need Positive Visions for AI Grounded in Wellbeing
IntroductionImagine yourself a decade ago, jumping directly into the present shock of conversing naturally with an encyclopedic AI that crafts images, writes code, and debates philosophy.…
Open Source Automated Interpretability for Sparse Autoencoder Features
Building and evaluating an open-source pipeline for auto-interpretability
An Open Course on LLMs, Led by Practitioners
An Open Course on LLMs, Led by Practitioners
AI existential risk probabilities are too unreliable to inform policy
How speculation gets laundered through pseudo-quantification
Building A Generative AI Platform
After studying how companies deploy generative AI applications, I noticed many similarities in their platforms. This post outlines the common components of a generative AI platform,…
Extrinsic Hallucinations in LLMs
Hallucination in large language models usually refers to the model generating unfaithful, fabricated, inconsistent, or nonsensical content. As a term, hallucination has been somewhat generalized to…
New paper: AI agents that matter
Rethinking AI agent benchmarking and evaluation
Experiments in Weak-to-Strong Generalization
Writing up results from a recent project
Free Form Least-Squares Concept Erasure Without Oracle Concept Labels
Achieving even more surgical edits than LEACE without concept labels at inference time.
What We’ve Learned From A Year of Building with LLMs
What We’ve Learned From A Year of Building with LLMs
VINC-S: Closed-form Optionally-supervised Knowledge Elicitation with Paraphrase Invariance
Writing up results from a project from Spring 2023
Financial Market Applications of LLMs
The AI revolution drove frenzied investment in both private and public companies and captured the public’s imagination in 2023. Transformational consumer products like ChatGPT are powered…
Measuring personal growth
My founder friends constantly think about growth. They think about how to measure their business growth and how to get to the next order of magnitude…
Diffusion Models for Video Generation
Diffusion models have demonstrated strong results on image synthesis in past years. Now the research community has started working on a harder task—using it for video…
A Brief Overview of Gender Bias in AI
A brief overview and discussion on gender bias in AI
Coordinated Vulnerability Disclosure Dashboard
A regularly updated record of vulnerabilities found by Anthropic and reported to maintainers with cryptographic commitments to each finding at the time of disclosure.
Mamba Explained
Is Attention all you need? Mamba, a novel AI model based on State Space Models (SSMs), emerges as a formidable alternative to the widely used Transformer…
Yi-34B, Llama 2, and common practices in LLM training: a fact check of the New York Times
Setting the record straight regarding Yi-34B and Llama 2.
What I learned from looking at 900 most popular open source AI tools
[Hacker News discussion, LinkedIn discussion, Twitter thread] Update (Feb 2026): The full list of open source AI repos is hosted at Good AI List, updated daily.…
Car-GPT: Could LLMs finally make self-driving cars happen?
Exploring the utility of large language models in autonomous driving: Can they be trusted for self-driving cars, and what are the key challenges?
Do text embeddings perfectly encode text?
'Vec2text' can serve as a solution for accurately reverting embeddings back into text, thus highlighting the urgent need for revisiting security protocols around embedded data.
Unlocking the 3rd Dimension for Generative AI (Part 1)
It would be an understatement to say that generative AI has been taking the world by storm over the past couple of years. While text (1D)…