Projects

What I'm building and what I've shipped. Most have a live site, the code, or a write-up on how it came together.

prototype

Zamburak

Prompt-injection defense for LLM coding agents. A reference monitor tracks attacker-influenced data through a session and gates tool calls, with a content-blind LLM judge for the grey zone and a benchmark harness across 3,000+ attack scenarios.

  • AI security
  • agents
  • Python
shipped

Covid Was the Rehearsal. AI Is the Show.

Which jobs will AI displace? An analysis of 894 US occupations using a Delegation Resistance score built from O*NET work-context data and checked against 4.4 million Indeed job postings.

  • AI and work
  • data analysis
shipped

Routine Went First. Judgment Is Next.

The follow-up, six months on. 2025 BLS employment data shows fifteen million routine, non-embedded jobs shrank while other knowledge work grew, tested against both Delegation Resistance and Tyler Cowen's two-factor model of AI-aided growth.

  • AI and work
  • data analysis
active

cardlang

A language for card games that compiles into hidden-information environments for OpenSpiel, with automated checks that each player sees only what the rules allow. Built for multi-agent safety evaluations.

  • AI safety
  • compilers
  • multi-agent
  • Python