Conference Schedule

AI coding agents often write outdated Go, generating patterns like manual loops to search slices instead of using slices.Contains. This talk explains why it happens, what "modern Go" means today, and how guidelines and benchmarks can teach agents to generate idiomatic Go code.

For our small backend team managing over 60 Go microservices, AI has become a core part of our development workflow. Recently, I’ve been reflecting on my own journey with these tools and how my colleagues have approached theirs. While everyone uses AI in their own way, many of our experiences overlap in interesting ways. In this talk, we’ll discuss the common themes that have emerged and how individual experiences shape the way we use AI.

Can you build a USB keyboard in 5 minutes with Go? Yes — and I'll do it live.

In this talk, I'll show how TinyGo lets you run Go on microcontrollers and turn your code into a real USB HID keyboard. It's the same approach we use in our TinyGo Keeb workshops in Japan, where soldering meets Go.

Your Go tests pass, until production deadlocks. In this talk, we show how GCT, our in-house concurrency testing tool for Go systematically controls scheduling of goroutines to expose concurrency bugs hidden from the Go scheduler and replay them deterministically for debugging.

Running AI models locally means no API costs, no data leaving your machine, and no vendor lock-in — but integrating local inference into Go applications has traditionally been painful. In this talk, Bill will introduce Kronk, a Go SDK that lets you embed local model inference directly into your applications with full GPU acceleration — no CGO required. Whether it's chat, vision, audio, embeddings, or tool calling, Kronk gives you the same power as a model server without needing one. To prove it, Bill built a Model Server entirely on top of the SDK, complete with caching, batch processing, and agent support. You'll see live demos from writing your first chat app to driving a coding agent with a local model.

With the advent of AI agents, chat bots, and LLMs in general, we assume that they will perform as instructed.

But how do you defend against malicious actors?

If your application makes use of the RAG techniques, or you expose an LLM to your users, let me show you how one could break it.

I'll show a few attacks against LLMs that you should be aware of and how to protect against them.