In Part 1 of our series, we introduced the eager intern model: a strategy for harnessing the power of AI while firmly anchoring it in a loop of human verification. In Part 2, we described how we’ve formalized hard-won institutional knowledge into a living checklist, letting us encode what senior engineers know into prompts that AI can execute and defend.
Author: Steve Hackbarth
-
Part 2: The Living Checklist: When Gawande Meets Karpathy’s Software 3.0
Atul Gawande made a deceptively simple argument in The Checklist Manifesto: avoidable failures are common not because we lack knowledge, but because we fail to apply what we already know — consistently, correctly, and at the right time. The humble checklist, he argued, offers a lightweight way to encode and enforce best practices, even among experts.
-
Part 1: The Eager Intern Model and Karpathy’s Verification Loop
A key part of Andrej Karpathy’s recent talk at Y Combinator’s AI Startup School involved the challenges and opportunities of building software in the context of powerful but inherently flawed large language models. Karpathy’s advice — that AI works best when its output is limited in scope and rapidly reviewed by humans — tracks with our experience so far in integrating AI tooling into our workflow.
-
Report: 2021 Database Benchmark for Healthcare Analytics
New cloud-based database management systems (DBMSs) are powerful and scalable, but it’s hard to know which technology will best serve your organization’s needs under realistic data processing scenarios. This uncertainty is compounded in healthcare, where the characteristics of a typical data analytic exercise don’t usually conform to the “big data,” aggregation-oriented use cases around which the latest generation of columnar DBMSs were developed.
-
The specter of failure and the specter of success
The disastrous launch
It’s been a warm winter, but the palm trees are nonetheless shrink-wrapped up and down Atlantic Avenue. Virginia is not their native environment, and their winter discomfort is the price we have to pay to maintain the fiction that Virginia Beach is a summer paradise.
-
Working with dates and timezones in JavaScript: a survival guide
Many JavaScript developers approach dealing with dates and timezone issues with apprehension. And indeed, it’s easy to get turned in a knot as you’re trying to get times working sensibly for all your users. Nor are date and timezone problems the sort of issue that a great library can make easy. But with a solid understanding of the fundamentals, you’ll find that thinking through how to work with dates in JavaScript becomes a tractable problem.