AI × RFIC
What self-driving can teach us about AI-assisted RFIC design
A fuller account of L0–L5: what an engineer supplies, which decisions a system owns, and what evidence makes delegation useful.
9 MIN
The notebook
Ideas worth
working through.
Essays on intelligence, agents, and the physical world. Some are working frameworks; others are questions I am still learning how to ask.
Compression & intelligence
Compression is a lens on intelligence
The interesting part is not making data smaller. It is discovering structure that survives beyond the examples.
4 MIN
Agent systems
Build the laboratory, not another agent
For domain-specific engineering, the highest-leverage work may be the environment around the agent—not another reasoning loop.
3 MIN
AI × RFIC
At radio frequencies, layout is still design
A netlist is not a complete physical specification. Geometry, coupling, and return paths are part of the design problem.
3 MIN
AI × RFIC
Six levels of AI-assisted RFIC design
A working framework based on design responsibility and verified closure—not model size, agent count, or impressive screenshots.
3 MIN
Engineering methods
The next simulation should change a decision
Treat simulation as a decision resource: combine inexpensive exploration with the expensive evidence a claim actually needs.
3 MIN
Compression & intelligence
Two meanings of compression
Information compression and amplifier gain compression share a word. The interesting connection is a research question, not an equivalence.
3 MIN
Agent systems
Serial before swarm
Clear handoffs and durable state can matter more than adding simultaneous agents to an engineering workflow.
3 MIN
Prefer a feed reader? Follow the RSS feed. No account or mailing list required.