Code · Math · Hardware · Teaching

I write code, do math, build hardware, and teach.

I’m Ari Lerner. I’ve spent a long time working across systems software, AI infrastructure, security, and product—writing code and mathematics, building hardware, and teaching what I learn.

Currently building secure execution infrastructure for AI agents. What I’m doing now
Ari Lerner

Working thesis

Power is useful when its boundaries are legible

The systems I care about make capability explicit, complexity containable, and trust inspectable.

01

Compute should be containable

Powerful workloads need hard machine boundaries, attenuated authority, and a blast radius the operator can understand.

02

Interfaces should hide the right complexity

The best infrastructure does not expose every mechanism. It exposes the guarantees people need to build with confidence.

03

Trust should be verifiable

Policy, identity, provenance, and auditability should travel with the system—not live in an operator’s memory.

The long arc

Builder, teacher, operator.

I’ve spent a long time moving between code, math, hardware, systems, and teaching. The details change, but I keep returning to the same question: how do we make powerful technology useful without making it careless?

The longer story
9
technical books authored or co-authored
Stripe capture-the-flag competitions
curiosity for systems from hardware to semantics

Open channel

Working on something technically ambitious?

I’m always interested in hard systems problems, serious open-source work, and people building new leverage without ignoring trust.

Start a conversation