Matt Rickard
Subscribe
Sign in
Home
Most Popular
About
Archive
Latest
Top
Discussions
Rebuilding Cognition's Agentic MapReduce
How do you run large-scale agent tasks across a codebase?
Jul 5
2
June 2026
Clone Is the New Bottleneck for Agents
Agents increasingly work in ephemeral sandboxes. But they can't start working until the code is there.
Jun 12
2
Too Many Homers
Ὅμηρον ἐξ Ὁμήρου σαφηνίζειν.
Jun 10
15
4
May 2026
Where Should Agent-Generated Code Live?
Every company is going to have agents.
May 30
7
3
The Unreasonable Effectiveness of Mini-App Specs
The Unreasonable Effectiveness of Mini-App Specs
May 10
10
1
1
April 2026
The Spec Layer
Why Spec-Driven Development (SDD) Works
Apr 1
31
5
August 2025
Using Claude Code from Anywhere
I've been using multiple instances of Claude Code and Codex CLI almost every day.
Aug 30, 2025
16
5
December 2023
Pseudonyms in American History
Debates around the ratification of the Constitution and the early formation of the United States happened through pseudonymous authors.
Dec 5, 2023
9
1
Fairchildren
In 1956, William Shockley, Stanford professor and winner of the Nobel Prize in Physics for his work on semiconductors, recruited a team of young Ph.D.
Dec 4, 2023
10
1
ChatGPT After One Year
ChatGPT was released on November 30th 2022.
Dec 3, 2023
13
1
2
McNamara Fallacy
The McNamara Fallacy is named after Robert McNamara, the US Secretary of Defense during the Vietnam War.
Dec 2, 2023
26
1
2
Data Quality in LLMs
Good data is the difference between Mistral’s LLMs and Llama, which share similar architectures but different datasets.
Dec 1, 2023
7
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
