Latest posts

• Golden Datasets: The Essential First Step for AI-Powered Apps

  One of the biggest process shifts for teams building AI-powered apps is baking in time to create a golden dataset before building the system.

• The Power of Moving LLM Reasoning into Latent Space

  There are plenty of tasks that the large LLMs we use every day are still terrible at. One category: simple puzzles that require generalizing from limited examples, interpreting symbolic meaning, and flexibly applying rules, like those in the ARC-AGI benchmarks. These problems are dead-simple for humans to solve.