Frequently asked questions about thinking, epistemology, and cognitive tools. 1647 answers
Documentation should evolve with the agent — outdated docs are worse than no docs.
Documentation should evolve with the agent — outdated docs are worse than no docs.
Too many agents create coordination overhead that can exceed their collective value.
Internal agents run in your mind while external agents are embedded in tools and systems.
Agents for how to structure emails presentations and difficult conversations.
You are designing the user experience of your own cognitive systems.
For most decisions good enough is better than perfect because the search cost exceeds the improvement.
Record decisions, their reasoning, and their outcomes to improve future decision-making.
Reviewing what happened after completing a task surfaces errors for future correction.
Effectiveness means your agent produces the intended outcome, not just that it runs.
Agents for how to structure emails presentations and difficult conversations.
Self-correcting loops maintain balance by countering deviations.
Identify one area of your life or work where you experience recurring oscillation — energy levels, spending, task completion rates, or emotional states. Map the balancing loop: what is the set point (target), what is the sensor (how you detect deviation), and what is the corrective action? Write.
Confusing negative feedback with criticism or punishment. The word 'negative' here means directionally opposing — it counters the deviation. People who hear 'negative feedback loop' and think 'bad loop' will misdiagnose every stabilizing mechanism in their life as a problem to fix rather than a.
Self-correcting loops maintain balance by countering deviations.
For every important process have a documented way to recover from common failures.
An agent that acts fast but wrong is worse than one that acts slowly but right.
What you read shapes what you think which shapes what you seek out to read.
Regularly check that your feedback loops are still connected to meaningful outcomes.
Accept that some error rate is normal and define how much error is tolerable.
Optimizing before you understand the system is the root of much wasted effort.
Pick one system in your life that you have spent time optimizing — a workflow, a tool, a routine. Write down: (1) What exactly did you optimize? (2) What evidence did you have that this was the bottleneck? (3) What would have happened if you had done nothing? If your honest answer to #2 is 'I.
Confusing the pleasure of optimizing with the discipline of improving. Optimization feels productive — you are building, refining, engineering. But when directed at the wrong target, it is a sophisticated form of procrastination. You will know you have fallen into this trap when you can describe.
Optimizing before you understand the system is the root of much wasted effort.