Search

10 results

Science
Mar 23, 2026
Vibe physics: The AI grad student
Can AI do theoretical physics? I decided to find out by supervising Claude through a real research calculation, start to finish, without ever touching a file myself.
View article
Interpretability
Aug 1, 2025
Persona vectors: Monitoring and controlling character traits in language models
In a new paper, we identify patterns of activity within an AI model’s neural network that control its character traits, which we call persona vectors.
View article
Interpretability
Mar 27, 2025
Tracing the thoughts of a large language model
Today, we're sharing two new papers that represent progress on the development of an “AI microscope,” and the application of it to see new “AI biology.”
View article
Safeguards
Jun 6, 2024
Testing and mitigating elections-related risks
This blog provides a snapshot of the work we've done since last summer to test our models for elections-related risks.
View article
Models
Mar 4, 2024
Introducing the next generation of Claude
The Claude 3 model family—Haiku, Sonnet, and Opus—sets new industry benchmarks across a wide range of cognitive tasks.
View article
Product
Feb 29, 2024
Prompt engineering for business performance
Prompt engineering techniques that raised a Fortune 500 company's chat assistant accuracy by 20%, from few-shot examples to prompt chaining.
View article
Safeguards
Feb 16, 2024
Preparing for global elections in 2024
In this post, we’ll discuss some of the specific steps we’ve taken to help us detect and mitigate potential misuse of our AI tools in political contexts.
View article
Models
Nov 21, 2023
Introducing Claude 2.1
Claude 2.1 brings a 200K token context window, a 2x reduction in hallucination rates, beta tool use, and system prompts.
View article
Models
Aug 9, 2023
Releasing Claude Instant 1.2
Claude Instant 1.2 is a faster, lower-cost model with improved math, coding, reasoning, and safety inherited from Claude 2.
View article
Alignment
Jul 11, 2022
Language models (mostly) know what they know
Larger models are well calibrated at judging whether their own answers are true, and can predict whether they know an answer before answering.
View article