Would you say the same about more obviously artistic mediums? "Oh, their second album sounds exactly like their first which I liked!" isn't a compliment, usually.
The article sensibly asks if the (intentionally or not) cherry-picked stats about automated driving (fair weather only, limited to specific areas that aren't especially difficult) is valid then cites a study that really massages those stats in a dubious way (e.g. only counts as a crash if the airbag triggered, no mention of weather). Hmmm...
Another thing I'd really like to know: let's suppose that these are indeed safer than the average driver. Is it also the case for the median driver?
Sounds like what Mazda did with the MX-30 (https://en.wikipedia.org/wiki/Mazda_MX-30) which flopped hard. They used their new Wankel engine as range extender, perfect use case since the power:weight ratio of these is impressive.
> How else would you define bias if not an offset from equality or zero mean?
As an offset from what the ground truth justifies. Suppose the researchers had decided to load the dice when creating the fake sample data; an unbiased analyst should seek to discover the extent of that, not insist on reporting equality.
Well, in this study, they explicitly had equality - all four groups were as likely to succeed. So any difference in hiring was actual bias (or statistical noise).
Put a five-line TL;DR at the top of the README — what it is, the number, the honest limit, the two findings, credits — with the detail below for anyone who wants it.
What was the decision to leave the LLM to write the detail section rather than author it yourself? There's a growing resentment about asking people to read LLM-produced words, especially if it's a large amount to read. Not sure if you were aware of that or not (I think there's been links to surveys / polls just recently on H.N)
reply