Last week I flew from Seattle to San Francisco for the OpenAI GPT-5.5 Event and had a great experience meeting people working across AI infrastructure, research, developer tooling, and startups.

One of the best parts of the event was getting the chance to talk directly with Members of Technical Staff and engineers about the technical challenges behind building and deploying large-scale AI systems. A lot of the conversations were very practical. People discussed reliability, inference, agents, developer workflows, evaluation, and what they are seeing from builders using these models in production.

I also enjoyed meeting developers and founders from the broader AI community. There were a lot of interesting side conversations about projects people are building, where the tooling ecosystem is heading, and how quickly the space is moving right now. It was one of those events where you could walk into almost any conversation and learn something useful.

As someone working in cloud reliability engineering at Microsoft and interested in AI systems and infrastructure, I appreciated hearing different perspectives from people building at different layers of the stack.

Thanks to the OpenAI team for organizing the event and bringing together such a strong builder community. I left San Francisco with a lot of new ideas and a better understanding of where the ecosystem is heading.

Image generated with 5.5