Safety & Alignment
0
A hazard analysis framework for code synthesis large language models
0

Codex, a large language model (LLM) trained on a variety of codebases, exceeds the previous state of the art in its capacity to synthesize and generate ...

0
Forecasting potential misuses of language models for disinformation campaigns and how to reduce risk
0

As generative language models improve, they open up new possibilities in fields as diverse as healthcare, law, education and science. But, as with any new ...

0
Forecasting potential misuses of language models for disinformation campaigns and how to reduce risk
0

As generative language models improve, they open up new possibilities in fields as diverse as healthcare, law, education and science. But, as with any new ...

0
Language models can explain neurons in language models
0

Although the vast majority of our explanations score poorly, we believe we can now use ML techniques to further improve our ability to produce explanations. ...

0
Frontier AI regulation: Managing emerging risks to public safety
0

Frontier AI regulation: Managing emerging risks to public safety

0
Confidence-Building Measures for Artificial Intelligence: Workshop proceedings
0

Sarah Barrington (University of California, Berkeley)Ruby Booth (Berkeley Risk and Security Lab)Miles Brundage (OpenAI)Husanjot Chahal (OpenAI)Michael Depp ...

0
DALL·E 3 system card
0

DALL·E 3 is an artificial intelligence system that takes a text prompt as an input and generates a new image as an output. DALL·E 3 builds on DALL·E 2 by ...

0
GPT-4V(ision) system card
0

GPT-4 with vision (GPT-4V) enables users to instruct GPT-4 to analyze image inputs provided by the user, and is the latest capability we are making broadly ...

0
Weak-to-strong generalization
0

There are still important disanalogies between our current empirical setup and the ultimate problem of aligning superhuman models. For example, it may be ...

0
Practices for Governing Agentic AI Systems
0

Agentic AI systems—AI systems that can pursue complex goals with limited direct supervision—are likely to be broadly useful if we can integrate them ...

0
Practices for Governing Agentic AI Systems
0

Agentic AI systems—AI systems that can pursue complex goals with limited direct supervision—are likely to be broadly useful if we can integrate them ...

0
Building an early warning system for LLM-aided biological threat creation
0

Note: As part of our Preparedness Framework, we are investing in the development of improved evaluation methods for AI-enabled safety risks. We believe that ...

0
Your Cart is empty!

It looks like you haven't added any items to your cart yet.

Browse Products
Powered by Caddy
Shopping cart