Why Your Engineers Are Building Different Systems—and How to Align Them

At the GitHub AI Summit, I ran an exercise focused on capacity planning across four teams working on closely related services. Officially, the goal was to ideate how we could better manage our GPU compute capacity. Unofficially, I had a deeper agenda: to reveal just how differently each team saw the system—even though we were all building the same product.

Engineers realizing that they are all building different types of chairs, bar stools, recliners, and more. Realizing they need to understand what chair means first.

It might sound odd to say I had an ulterior motive, but I’ve seen this pattern everywhere I’ve worked. Even on highly aligned, well-intentioned teams, you’ll often find:

[Read More]

Breadth in Ai

Language is infinite, Your product should not be

Over the past few years I have been directly involved in developing GitHub Copilot, working on different parts of the tooling and grappling with the ethics and implications of these amazing AI models and their confounding abilities and limitations which constantly seem to be unveiling themselves to us.

When working on an LLM product there is an interesting consideration that is not present in other technologies, or at least not as prevalent. An LLM works in the domain of language and language can describe anything. This makes fitting the LLM to you product challenging as it will happily answer any query the user may offer regardless of the domain of your product. I have seen many people on social media identify they are chatting with an LLM simply by steering it way off topic and having a conversation having nothing to do with the service being offered. Language is an infinite tool of expression, but your product is definitely not.

[Read More]