AI ALIGNMENT FORUMTags
AF

Humility

•
Applied to Dangers of deference by Noosphere89 ago
•
Applied to acronyms ftw by Emrik ago

"humility" has a different meaning on LessWrong than In common parlance, where itOutside of LessWrong, "humility" usually refers to "a modest or low view of one's own importance". In common parlance, to be humble is to be meek, deferential, submissive, or unpretentious, "not arrogant or prideful". Thus, in ordinary languageEnglish "humility" and "modesty" have pretty similar connotations.

On LessWrong, Eliezer Yudkowsky has proposed that we instead draw a sharp distinction between two kinds of "humility" — social modesty, versus "epistemic humility" or "scientific humility".

"humility" has a different meaning on LessWrong than In common parlance, "humility"where it refers to "a modest ofor low view of one's own importance". ToIn common parlance, to be humble is to be meek, deferential, submissive, or unpretentious, "not arrogant or prideful". Thus, in ordinary language "humility" and "modesty""modesty" have pretty similar connotations.

On LW, then, we tend to follow the convention of using "humility" as a term of art for an important part of reasoning: combating overconfidence,overconfidence, recognizing and improving on your weaknesses, anticipating and preparing for likely errors you'll make, etc.

  • Given your fallibility, you should rely heavily on various techniques associated with "the outside view", and try to avoid using "inside views".
  • Given the human tendency to rationalize and self-deceive, you should trust average opinions, or the average opinion of authoritative-sounding sources, more than your own opinions (including your own fine-grained opinions about which authorities have good epistemics on which topics).
  • Given the risks and commonness of overconfidence,overconfidence, you should worry much more about overconfidence, and worry little (or not at all) about underconfidence.

Humility describes the conceptIn common parlance, "humility" refers to "a modest of low view of one's own importance". To be humble is to be meek, deferential, submissive, or unpretentious, "not arrogant or prideful". Thus, in ordinary language "humility" and "modesty" have pretty similar connotations.

On LessWrong, Eliezer Yudkowsky has proposed that we should,instead draw a sharp distinction between two kinds of "humility" — social modesty, versus "epistemic humility" or "scientific humility".

In The Proper Use of Humility (2006), Yudkowsky writes:

You suggest studying harder, and the student replies: “No, it wouldn’t work for me; I’m not one of the smart kids like you; nay, one so lowly as myself can hope for no better lot.”

This is social modesty, not humility. It has to do with regulating status in general,the tribe, rather than scientific process.

If you ask someone to “be more humble,” by default they’ll associate the words to social modesty—which is an intuitive, everyday, ancestrally relevant concept. Scientific humility is a more recent and rarefied invention, and it is not inherently social. Scientific humility is something you would practice even if you were alone in a spacesuit, light years from Earth with no one watching. Or even if you received an absolute guarantee that no one would ever criticize you again, no matter what you said or thought of yourself. You’d still double-check your calculations if you were wise.

On LW, then, we tend to follow the convention of using "humility" as a term of art for an important part of reasoning: combating overconfidence, recognizing and improving on your weaknesses, anticipating and preparing for likely errors you'll make, etc.

In contrast, "modesty" here refers to the bad habit of letting your behavior and epistemics be ruled by not wanting to look arrogant or conceited. Yudkowsky argues in Inadequate Equilibria (2017) that psychological impulses like "status regulation and anxious underconfidence" have caused many people in the effective altruism and rationality communities to adopt a "modest epistemology" that involves rationalizing various false world-models and invalid reasoning heuristics.

LW tries to create a social environment where social reward and punishment is generally less sure about what we know than intuition implies. Itsalient, and where (to the extent it persists) it incentivizes honesty and truth-seeking as much as possible. LW doesn't always succeed in this goal, but this is closely related to epistemology.nonetheless the goal.

The basic concept heremost commonly cited explanation of scientific/epistemic humility on LW is that humans are over-confident on average (found in Yudkowsky's "Inside-view forecasting is a classic example) -- people are not only wrong, they are very confidently wrong. Consequently, it seems to beTwelve Virtues of benefit to assume that your assessment of confidence (how sure you are in a given theory) is overconfident in any...

Read More (515 more words)