Elicit

How To Hire AI Engineers (ft. James Brady and Adam Wiggins of Elicit)

Jun 21, 2024 · 1:08:06

James Brady and Adam Wiggins of Elicit define the AI engineer role as a blend of conventional software engineering, deep curiosity about language models, and a defensive fault-first mindset to handle LLMs' chaotic latency and non-determinism. They explain their interview process uses coding exercises that force edge-case thinking and system design probing fault tolerance, not happy-path algorithms. For sourcing, they emphasize side projects, hackathons, and targeted communities like effective altruism. The episode explores the ML-first mindset of relinquishing control to leverage model capabilities, using techniques like retries, fallbacks, and strong typing. Elicit shares their job description template and tiered ML reading list as practical resources for hiring.

Supervise the Process of AI Research — with Jungwon Byun and Andreas Stuhlmüller of Elicit

Apr 11, 2024 · 1:05:28

Andreas Stuhlmüller and Jungwon Byun, co-founders of Elicit (formerly the nonprofit Ought), have built an AI research assistant that automates literature review and reasoning by breaking complex tasks into transparent, step-by-step processes. Their philosophy—"supervise the process, not just the outcome"—led them to start with human simulations before GPT-3 enabled a product pivot. Elicit now uses both open-source and closed models (e.g., GPT-4, Claude Haiku) for summarization, data extraction, and uncertainty flags, and recently launched computational notebooks for scalable, reusable workflows. The company transitioned from nonprofit to a Public Benefit Corporation, reached $1M revenue in four months, and now employs 12 people, focusing on senior software engineers to build reliable orchestration from unreliable components.