Posts by Tags

AI

How I Design Claude Code Skills

13 minute read

Published:

A skill is crystallized consensus from repeated experience, not something designed in the abstract. Eight skills and what I learned about knowing what’s worth putting in them.

How to Build AI Agents: Lessons from Five Projects

18 minute read

Published:

How much should I specify upfront, and how much should I let the agent figure out? Lessons from five agent projects, grounded in Anthropic’s engineering philosophy.

Ascend

DeepSeek

GPU

KV Cache

KernelGen

Memory

OSTEP Memory Virtualization Notes

16 minute read

Published:

Notes on memory virtualization from OSTEP—address spaces, page tables, TLBs, and the mechanisms that make virtual memory work.

MoE

Operating System

OSTEP Memory Virtualization Notes

16 minute read

Published:

Notes on memory virtualization from OSTEP—address spaces, page tables, TLBs, and the mechanisms that make virtual memory work.

Quantization

SwiGLU

Triton

Virtualization

OSTEP Memory Virtualization Notes

16 minute read

Published:

Notes on memory virtualization from OSTEP—address spaces, page tables, TLBs, and the mechanisms that make virtual memory work.

agent

How to Build AI Agents: Lessons from Five Projects

18 minute read

Published:

How much should I specify upfront, and how much should I let the agent figure out? Lessons from five agent projects, grounded in Anthropic’s engineering philosophy.

ai

biophysics

claude-code

How I Design Claude Code Skills

13 minute read

Published:

A skill is crystallized consensus from repeated experience, not something designed in the abstract. Eight skills and what I learned about knowing what’s worth putting in them.

concurrency

cryptochrome

debugging

deepseek

docker

infrastructure

Design Dimensions for Research Infrastructure

15 minute read

Published:

Four research infrastructure projects, and what they taught me about failure recovery, data integrity, observability, system abstraction, and the mistakes I’d avoid starting over.

linux

magnetoreception

methodology

How I Design Claude Code Skills

13 minute read

Published:

A skill is crystallized consensus from repeated experience, not something designed in the abstract. Eight skills and what I learned about knowing what’s worth putting in them.

How to Build AI Agents: Lessons from Five Projects

18 minute read

Published:

How much should I specify upfront, and how much should I let the agent figure out? Lessons from five agent projects, grounded in Anthropic’s engineering philosophy.

opensource

Design Dimensions for Research Infrastructure

15 minute read

Published:

Four research infrastructure projects, and what they taught me about failure recovery, data integrity, observability, system abstraction, and the mistakes I’d avoid starting over.

production

python

quantum-biology

radical-pair

research

research-methodology

Design Dimensions for Research Infrastructure

15 minute read

Published:

Four research infrastructure projects, and what they taught me about failure recovery, data integrity, observability, system abstraction, and the mistakes I’d avoid starting over.

rust

skill

How I Design Claude Code Skills

13 minute read

Published:

A skill is crystallized consensus from repeated experience, not something designed in the abstract. Eight skills and what I learned about knowing what’s worth putting in them.

snap

software-engineering

How I Design Claude Code Skills

13 minute read

Published:

A skill is crystallized consensus from repeated experience, not something designed in the abstract. Eight skills and what I learned about knowing what’s worth putting in them.

How to Build AI Agents: Lessons from Five Projects

18 minute read

Published:

How much should I specify upfront, and how much should I let the agent figure out? Lessons from five agent projects, grounded in Anthropic’s engineering philosophy.

spin-dynamics

systems

How to Build AI Agents: Lessons from Five Projects

18 minute read

Published:

How much should I specify upfront, and how much should I let the agent figure out? Lessons from five agent projects, grounded in Anthropic’s engineering philosophy.

Design Dimensions for Research Infrastructure

15 minute read

Published:

Four research infrastructure projects, and what they taught me about failure recovery, data integrity, observability, system abstraction, and the mistakes I’d avoid starting over.

systems-programming