Drawing from OpenAI’s established safety frameworks, this document highlights our multi-layered approach, including model and product mitigations we’ve implemented to protect against prompt engineering and jailbreaks, protect privacy and security, as well...
This report outlines the safety work carried out prior to releasing OpenAI o1 and o1-mini, including external red teaming and frontier risk evaluations according to our Preparedness Framework.
A factuality benchmark called SimpleQA that measures the ability for language models to answer short, fact-seeking questions.
We’ve simplified, stabilized, and scaled continuous-time consistency models, achieving comparable sample quality to leading diffusion models, while using only two sampling steps.
We introduce MLE-bench, a benchmark for measuring how well AI agents perform at machine learning engineering.
OpenAI and Los Alamos National Laboratory are working to develop safety evaluations to assess and measure biological capabilities and risks associated with frontier models.
Consistency models are a nascent family of generative models that can sample high quality data in one step without the need for adversarial training.
We’re developing a blueprint for evaluating the risk that a large language model (LLM) could aid someone in creating a biological threat. In an evaluation involving both biology experts and students, we found that GPT-4 provides at most a mild uplift in...
To support the safety of highly-capable AI systems, we are developing our approach to catastrophic risk preparedness, including building a Preparedness team and launching a challenge.
We’ve created GPT-4, the latest milestone in OpenAI’s effort in scaling up deep learning. GPT-4 is a large multimodal model (accepting image and text inputs, emitting text outputs) that, while less capable than humans in many real-world scenarios, exhibits...
Our latest research finds we can improve language model behavior with respect to specific behavioral values by fine-tuning on a small, curated dataset.
We’re introducing a neural network called CLIP which efficiently learns visual concepts from natural language supervision. CLIP can be applied to any visual classification benchmark by simply providing the names of the visual categories to be recognized,...