AI & ML
Learning to play Minecraft with Video PreTraining
OpenAI Blog0 views
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.
Source：https://openai.com/index/vptRelated posts
Elpis, the mother of your coding agents
0dev.to Rust
Build an LLM Gateway with hikyaku: One Endpoint, AI-Picked Models and Failover Across Providers
0dev.to Go
Less Is Suddenly Enough — Sparse Edits and Synthetic Data Start Beating Full-Scale Post-Training
0dev.to AI
Axelera AI unveils Titania: third-generation chiplet architecture for air-cooled inference
0dev.to AI
OpenAI launches Daybreak Red Team in early access to test web apps for flaws and Daybreak Defense Factory to automate finding, validating, and fixing them (Jessica Lyons/The Register)
0Techmeme
AI server maker xFusion gets approval from the Shenzhen Stock Exchange for a ChiNext IPO; filing: the company aims to raise ~$1.2B by issuing up to 220M shares (Sangmi Cha/Bloomberg)
0Techmeme