A. Jesse Jiryu Davis
- Review: Automated Design of Agentic Systems
A meta-agent develops agents to solve puzzles. But are the benchmarks and conclusions realistic?
- Review: SysMoBench: Evaluating AI on Formally Modeling Complex Real-World Systems
Some TLA+ experts try to teach LLMs to write TLA+. The LLMs fail.
- Review: Measuring AI Ability to Complete Long Software Tasks
What we talk about when we talk about time horizon.
- Will the Training of Junior Engineers Be a Tragedy of the Commons?
We still need senior engineers, but there's less economic incentive to create them.
- What Does Privacy Mean Now?
Do you care if an LLM sees you naked?
- The Work of Art in the Age of Mechanical Creation
Walter Benjamin misforecast back in 1935: copies only enhance the aura of the original. What about AI?
- This Senior Staff Engineer Vibe-Coded for the First Time, What Happened Next Will Shock You
Spoiler alert: it was both productive and annoying.