✳flâneur — a map of the web's best reading

pdoom.org/crowd_cast

pdoom.org · 732 words · saved by 1 readers

We introduce crowd-cast, a privacy-preserving desktop application that allows anyone to participate in crowd-sourcing an action-annotated long-horizon behaviour-cloning dataset of computer work. Install once, and forget about it. Franz Srambical* p(doom), TUM Mihir Mahajan* p(doom), TUM Alfred Nguyen* p(doom), TUM Stefan Bauer TUM Feb. 2, 2026 Install crowd-cast on macOS (Windows and Linux support are coming soon) While pretraining data acquisition has saturated and post-training overwhelmingly piggybacks on manual data labeling or handcrafted RL environments, the trillion-dollar question remains how we will get to the next set of model capabilities. A billion people are predominantly working on computers, generating hundreds of billions of hours of behaviour-cloning data every week, yet that data remains uncaptured and ultimately lost. Models can make sense of the predominantly garbage-filled internet, they can learn to produce long chains of thought from thousands of cold-start examp

We pay $300/month to record your screen for AI research. Apply → × --> We introduce crowd-cast , a privacy-preserving desktop application for crowd-sourcing an action-annotated long-horizon behaviour-cloning dataset of computer work. * Equal contribution We now pay participants $300/month to use crowd-cast. Apply . Figure 1: Action-annotated recording captured via crowd-cast. 1 You really think we're going to scale data labelers to AGI? While pretraining data acquisition has saturated and post-training overwhelmingly piggybacks on manual data labeling or handcrafted RL environments, the trilli

Explore this link on the map →

related reading