Speakers: Lukas Wesemann (Base Compute)
Track: Research / Deep Tech
Most AI today runs in the cloud, where every token costs money and every input leaves your device. Now AI agents are running around the clock with access to your email, files, and most sensitive data. That burns through tokens fast and sends your private data to someone else’s servers. This talk covers why frontier AI is moving on-device, the technical challenges of running large models on constrained hardware, and the cost and privacy advantages of local inference. It draws on Base Compute’s work building the on-device inference stack.
https://data.webdirections.org/ai-engineer-sydney/sessions.json#295ee9ea-cff3-4b85-9ac5-fc02fdc245d5
Full text on webdirections.org
.