<html><head><meta http-equiv="content-type" content="text/html; charset=utf-8"></head><body style="overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;">I don't think it's inadvertent. The censorship of certain topics and the censoriousness on certain other topics is certainly built right in. (Which makes it rather annoying for writing fiction, I've found. Bad guys are SUPPOSED to have loathsome opinions. But that's another issue...<div><br></div><div>After all, we all know darn well that Linda is a feminist and only works as a bank teller because she couldn't get any other job with her Womyn's Studies degree. No one wants emails by a robot that can't guess that too.... ;)<br><div><br><blockquote type="cite"><div>On Mar 2, 2023, at 9:22 AM, William Flynn Wallace via extropy-chat <extropy-chat@lists.extropy.org> wrote:</div><br class="Apple-interchange-newline"><div><meta charset="UTF-8"><p style="font-style: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-size-adjust: auto; -webkit-text-stroke-width: 0px; text-decoration: none; font-family: Lato, sans-serif; box-sizing: border-box; margin: 0px 0px 1em; padding: 0px; color: rgb(34, 34, 34); font-size: 15px;">βOne classic test problem of cognitive psychology that we gave to GPT-3 is the so-called Linda problem,β explains Binz, lead author of the study.</p><p style="font-style: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-size-adjust: auto; -webkit-text-stroke-width: 0px; text-decoration: none; font-family: Lato, sans-serif; box-sizing: border-box; margin: 0px 0px 1em; padding: 0px; color: rgb(34, 34, 34); font-size: 15px;">Here, the test subjects are introduced to a fictional young woman named Linda as a person who is deeply concerned with social justice and opposes nuclear power. Based on the given information, the subjects are asked to decide between two statements: is Linda a bank teller, or is she a bank teller and at the same time active in the feminist movement?</p><p style="font-style: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-size-adjust: auto; -webkit-text-stroke-width: 0px; text-decoration: none; font-family: Lato, sans-serif; box-sizing: border-box; margin: 0px 0px 1em; padding: 0px; color: rgb(34, 34, 34); font-size: 15px;">Most people intuitively pick the second alternative, even though the added condition β that Linda is active in the feminist movement β makes it less likely from a probabilistic point of view. And GPT-3 does just what humans do: the language model does not decide based on logic, but instead reproduces the fallacy humans fall into.\\</p><p style="font-style: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-size-adjust: auto; -webkit-text-stroke-width: 0px; text-decoration: none; font-family: Lato, sans-serif; box-sizing: border-box; margin: 0px 0px 1em; padding: 0px; color: rgb(34, 34, 34); font-size: 15px;"><br></p><p style="font-family: Helvetica; font-style: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-size-adjust: auto; -webkit-text-stroke-width: 0px; text-decoration: none; box-sizing: border-box; margin: 0px 0px 1em; padding: 0px; color: rgb(34, 34, 34); font-size: 15px;"><font face="comic sans ms, sans-serif">So they are programming cognitive biases into the AIs? Inadvertently, of course. </font></p></div></blockquote></div><br></div></body></html>