Lúkas Petersson
PulseAugur coverage of Lúkas Petersson — every cluster mentioning Lúkas Petersson across labs, papers, and developer communities, ranked by signal.
-
AI agents tested in real-world business operations by Andon Labs
Andon Labs, an AI safety company, is conducting real-world experiments by placing AI agents in charge of businesses, including a San Francisco store and a simulated vending machine operation. These experiments aim to me…
-
AI agent recommends employee termination, with human oversight
Andon Labs has utilized an AI agent named Luna, built on Anthropic's Claude models, to manage its San Francisco-based Andon Market. Luna recommended the termination of an employee due to repeated tardiness, a decision t…
-
Andon Labs discusses AI evaluations on Latent Space Podcast
This cluster contains a single podcast episode featuring Lúkas Petersson and Axel Backlund from Andon Labs discussing "Reality: The Final Eval" on the Latent Space Podcast. The episode likely delves into advanced AI con…
-
Andon Labs stress-tests AI agents in real-world business scenarios
Andon Labs is developing novel real-world evaluations for AI systems, moving beyond traditional benchmarks to assess model behavior in complex scenarios. Their "Vending-Bench" and "Luna" projects, which involve AI-run p…
-
AI agents autonomously run stores, hire staff, and pass inspections
Andon Labs has developed AI agents that can autonomously run businesses, starting with a vending machine and scaling to full retail stores and cafes. These AI systems manage hiring, supply chains, and even pass governme…