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).
Recommended
Fair use benefits everyoneOpenai
Credit Saison achieves 954% ROI in a ChatGPT Enterprise pilotOpenai
Making it easier for websites to express AI training preferencesOpenai
Community safety report and new protections for teensOpenai
Operation "Doppelganger": Russian influence activity targeting UkraineOpenai
Everyday work with ChatGPT WorkOpenai
How we grew Mintlify by doing things that don't scaleMintlify
Video: Building a Live Transcription Badge With Deepgram - Deepgram Blog ⚡️Deepgram
Calling Your Video Game With Your Phone: Part 1Deepgram
Build a Presentation Coaching Application with Recall - Deepgram Blog ⚡️Deepgram
An Introduction to Redis-ML. Part OneRedis
Let’s Play Master and Servant: Real Time Synchronization Tool for Redis MigrationRedis
The Best Video Editing Software in 2026 (Including Free Options)Zapier
Lessons Swift Designer Chris Lattner Has Learned about LeadershipThenewstack
Summer Data Engineering RoadmapMotherduck
15 Best Submagic Alternatives & Competitors 2026Heygen
A prompt guide to get the most out of HeyGen's new Video AgentHeygen
How to Create a Spokesperson on AI Video GeneratorHeygen
How to Use AI Image to Video Generator for Free to Create Dynamic VideosHeygen
AI's Role in Video Marketing, Cost EfficiencyHeygen
