jaswantkaurm@gmail.com

Greg Ziółkowski: Research: Architecting Tools for AI Agents at Scale

Loading all available tools into an LLM’s context simultaneously is one of the most consequential architectural mistakes teams make when building AI integrations. The solution isn’t bigger context windows, and it’s progressive tool exposure: dynamically presenting only the tools relevant to each interaction. This post surveys the major patterns for doing so, drawn from production servers,…

Read More

Gary: The Human in the Loop

If you’ve been paying attention to LLM-based coding tools in the past few months, you’ll have seen a seismic shift in how they’re being used. Even 12 months ago, they were little more than glorified auto-complete tools: useful for quickly repeating patterns, but terrible at producing well structured, thoughtful, maintainable code. More recently, however, there…

Read More

Matt: TheOpenSource

It’s very cool to see Theo / t3.gg‘s open source arc. Just in general, with people creating more software than ever, it’s so exciting to see an explosion of open source and a growing understanding of why working together on open source makes so much sense for the future we want to build.

Read More