Frequently asked questions about thinking, epistemology, and cognitive tools. 1287 answers
Compare agents against each other and against baselines to identify relative performance.
Different frameworks for decisions made alone versus with others.
Any system that cannot observe its own output cannot improve.
Every decision costs attention and energy — systematic frameworks reduce this cost.
Every agent has a trigger that activates it, a condition that validates it, and an action it takes.
A trigger must be something you can detect consistently.
A trigger must be something you can detect consistently.
Combining multiple trigger conditions for higher-specificity activation.
Combining multiple trigger conditions for higher-specificity activation.
You cannot fix what you cannot detect — invest in error detection mechanisms.
You cannot fix what you cannot detect — invest in error detection mechanisms.
Asking why five times in succession usually reaches the root cause of a problem.
Small uncorrected errors can trigger chains of increasingly large errors.
Trust your agents and systems — but build verification into the process, not as an afterthought.
True control comes from building systems you trust to operate without your constant oversight.
Without a baseline measurement, you cannot know whether your optimization actually improved anything.
Every agent is created, deployed, maintained, and eventually retired.
Moving an agent from design to daily operation takes time and deliberate effort.
Sometimes you should improve an existing agent; sometimes you should replace it entirely.
When an agent fails to fire or produces bad results you learn how to improve it.
Internal triggers are thoughts and feelings — external triggers are events and cues.
Internal triggers are thoughts and feelings — external triggers are events and cues.
Sometimes deciding fast is more important than deciding optimally.
What you read shapes what you think which shapes what you seek out to read.