Engineering AI Reading Group
Theme: Can AI Make Good Judgments?
Thanks to Tanmaye and Abhi, this week EAIRG will be hosted at Primary VC. Primary is an early stage venture fund based in New York, that just raised a $625M Fund V to invest in the earliest stage founders.
Are taste and judgement uniquely human? There are two camps: those who believe judgment under uncertainty is irreducibly human (see the NYT headline on the event page), and those betting that with enough reasoning, context, and architecture, long-running agents can develop good judgment too.
If you're building anything where agents must evaluate rather than just generate, we invite you to share how you're approaching it. Here's some thoughts in more detail.
Who should come: Engineers, researchers, and builders working on evaluation systems, reasoning architectures, decision support tools, or anyone wrestling with how to get AI to make good judgments under uncertainty.
We only have capacity for 30 people and will prioritize admittance by those who have worked on AI Evals and first-come-first-served basis.
Agenda:
Tanmaye presents AI in VC (15 min)
Independent Readings & Discussion (30 min)
Lightning Demos (30min - 1 hour)
Pizza provided.
Engineering AI RG comes together to read and code on tools, libraries and codebases that are used frequently in the modern AI stack.
All are welcome.