Engineering Insights

Learning 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 model uses the native human interface of keypresses and mouse movements, making it quite general, and represents a step towards general computer-using agents.

Getting Started With Embeddings

Convert Transformers to ONNX with Hugging Face Optimum

Consensus algorithms at scale: Part 6 - Completing requests

If you’re still catching up, you can find links to each article in the series at the bottom of this article. The completion of requests is a relatively straightforward topic. However, there are a few concepts to cover before we jump into the more complex part of propagating requests during a leadership change. Recap of parts 1-5 We have redefined the problem of consensus with the primary goal of solving durability in a distributed system, and are approaching the problem top-down. We have shown a

OpenSSL update assessment, and Node.js project plans

Introducing the Edge Runtime

Vercel’s mission is to enable developers to build dynamic, global applications. To enable every framework to build for the edge, we’re releasing edge-runtime: a toolkit for developing, testing, and defining the runtime web APIs for edge infrastructure. Read more

Vue 2.7 is Now in Beta

We are happy to announce that Vue 2.7 is now in beta.

Evolution through large models