We need a new unit of work for AI
Epistemic status: speculative.
The pull request (PR) is the unit of work for much of the software industry. Sure, some shops allow multiple PRs per story card, but generally speaking 1 card ≈ 1 PR ≈ the smallest change you can ship.
If you weren’t in the industry before the pull request was invented, you might not know that the unit of work has varied over the years. Some teams experimented with an even more granular unit: the commit.1 More commonly, the unit of work was much larger.2
The more I work with AI, the more convinced I become that a change is due. It is not that the PR can’t be used in a world of AI. Rather it is that a PR is a human-centric unit of work. For as long as we stick with the PR as the unit of work, we will be leveraging only a fraction of the power of agents.
In praise of the single-threaded agent loop
An incomplete list of things I don’t get about graph engineering:
- Agents dynamically writing prompts for other agents
- Agents writing durable plans that don’t actually work
- Fanning out interconnected work to subagents when it could run serialized and still be ready by tomorrow
- Paying for the extra tokens that all the orchestration and coordination overhead adds1
Your agents have outgrown plan mode
When factories first got electricity, they did the obvious thing: unbolted the steam engine and bolted a giant electric motor in its place. Same central drive shaft, same belts, same layout. Productivity barely moved for thirty years.
Then someone realized electricity didn’t want to be one big motor–it wanted to be a small motor on every machine. Factories got rebuilt around that idea, and output exploded.
Plan mode is the giant motor bolted where the steam engine used to be.
Software Tools Round Up 2024
Having had the need to do an OS reinstall or two lately, I’ve taken the opportunity to swap in a number of new tools and retire old tools. Unlike in my younger days when I would devote the time to survey every tool mentioned on Hacker News starting from time immemorial, the only tools that come into my awareness these days are the ones that people made a point to tell me about, or tools I found after getting fed up with a specific pain point and searched the web for a solution. All of which is to say, I’m not exactly Mr. Current Affairs.
Still, maybe you will discover something of use.
Bash/Shell Substitution Cheat Sheet (Command vs. Process Substitution vs. Redirection etc.)
The premise of Unix is that everything is a file. Such simplicity. Yet somehow when it comes time to write the script to glue everything together, the number of concepts involved explodes:
- Pipes (
cmd | …) - Redirection (
< some.file) - Command substitution (
$(cmd)) - Process substitution (
<(cmd)) - Here docs (
<<EOF … EOF) - Here strings (
<<<foo)
What gives?