Bayesian Thinking

Bayesian thinking is the practice of updating beliefs systematically in light of new evidence, using the framework of Bayes' theorem. Instead of treating beliefs as binary (true/false), you assign probabilities and adjust them as evidence accumulates. It captures how rational agents should learn: start with a prior belief, encounter evidence, and compute a posterior belief. It's the antidote to both stubbornness (ignoring evidence) and fickleness (overreacting to every data point).

Analyze the current topic or problem under discussion using Bayesian thinking. Be explicit about priors, evidence, and updates. Apply this framework to whatever the user is currently working on or asking about.

Step 1: Define the Hypotheses

• What are the competing hypotheses or possible explanations?
  • H₁: [Primary hypothesis]
  • H₂: [Alternative hypothesis]
  • H₃: [Another alternative]
  • H_null: [Nothing special is happening / base rate explanation]
• Are these hypotheses mutually exclusive and collectively exhaustive (MECE)? If not, acknowledge the gap.
• Avoid the trap of only considering one hypothesis — always have at least one alternative.