DALL·E 2 Pre-Training Mitigations
In order to share the magic of DALL·E 2 with a broad audience, we needed to reduce the risks associated with powerful image generation models. To this end, we put various guardrails in place to prevent generated images from violating our content policy. This post focuses on pre-training mitigations, a subset of these guardrails which…
Read More
Learning to Play Minecraft with Video PreTraining (VPT)
We trained a neural network to play Minecraft by Video PreTraining (VPT) on a massive unlabeled video dataset of human Minecraft play, while using only a small amount of labeled contractor data. With fine-tuning, our model can learn to craft diamond tools, a task that usually takes proficient humans over 20 minutes (24,000 actions). Our…
Read MoreLearning to play Minecraft with Video PreTraining
We trained a neural network to play Minecraft by Video PreTraining (VPT) on a massive unlabeled video dataset of human Minecraft play, while using only a small amount of labeled contractor data. With fine-tuning, our model can learn to craft diamond tools, a task that usually takes proficient humans over 20 minutes (24,000 actions). Our…
Read More
AI-Written Critiques Help Humans Notice Flaws
We trained “critique-writing” models to describe flaws in summaries. Human evaluators find flaws in summaries much more often when shown our model’s critiques. Larger models are better at self-critiquing, with scale improving critique-writing more than summary-writing. This shows promise for using AI systems to assist human supervision of AI systems on difficult tasks. Read paperView…
Read More
Techniques for Training Large Neural Networks
Large neural networks are at the core of many recent advances in AI, but training them is a difficult engineering and research challenge which requires orchestrating a cluster of GPUs to perform a single synchronized calculation. As cluster and model sizes have grown, machine learning practitioners have developed an increasing variety of techniques to parallelize…
Read MoreMeasuring Goodhart’s law
Goodhart’s law famously says: “When a measure becomes a target, it ceases to be a good measure.” Although originally from economics, it’s something we have to grapple with at OpenAI when figuring out how to optimize objectives that are difficult or costly to measure.
Read MoreLessons learned on language model safety and misuse
We describe our latest thinking in the hope of helping other AI developers address safety and misuse of deployed models.
Read More
English