I further suggest that if using these defined terms, instead of including a table of definitions somewhere you include the actual probability range or point estimate in parentheses after the term. This avoids any need to explain the conventions, and makes it clear at the point of use that the author had a precise quantitative definition in mind.
For example: it’s likely (75%) that flipping a pair of fair coins will get less than two heads, and extremely unlikely (0-5%) that most readers of AI safety papers are familiar with the quantitative convention proposed above—although they may (>20%) be familiar with the general concept. Note that the inline convention allows for other descriptions if they make the sentence more natural!
Agreed that that’s often an improvement! And as I say in the post, I do think that more often than not (> 50%) the best choice is to just give the numbers. My intended proposal is just to standardize in cases where the authors find it more natural to use natural language terms.
I further suggest that if using these defined terms, instead of including a table of definitions somewhere you include the actual probability range or point estimate in parentheses after the term. This avoids any need to explain the conventions, and makes it clear at the point of use that the author had a precise quantitative definition in mind.
For example: it’s likely (75%) that flipping a pair of fair coins will get less than two heads, and extremely unlikely (0-5%) that most readers of AI safety papers are familiar with the quantitative convention proposed above—although they may (>20%) be familiar with the general concept. Note that the inline convention allows for other descriptions if they make the sentence more natural!
Agreed that that’s often an improvement! And as I say in the post, I do think that more often than not (> 50%) the best choice is to just give the numbers. My intended proposal is just to standardize in cases where the authors find it more natural to use natural language terms.