@mattdm Turing test as captcha?
Posts
-
I'm sorry to complain again about captchas, but I have to. "Find the item that breaks the pattern" — wtf. -
A pet peeve is the idea Americans are a cultural bloc or that general statements can be made about what Americans are like in every part of the countryA pet peeve is the idea Americans are a cultural bloc or that general statements can be made about what Americans are like in every part of the country
-
If you’re generating code, and you’re *not* doing it with an LLM, is it reasonable to use metrics like F1 and recall to measure how well the tools you use are doing? This is bothering me because it feels a bit weird to apply metrics like this to static...@ryanc the thing in question is a talk I’m watching about using LLMs to figure out if code variants are equivalent, and as their baseline they seem to have used precision, recall, and F1 to measure how well methods that leverage non-ML things do at determining when code variants are equivalent
-
If you’re generating code, and you’re *not* doing it with an LLM, is it reasonable to use metrics like F1 and recall to measure how well the tools you use are doing? This is bothering me because it feels a bit weird to apply metrics like this to static...@ryanc yeah, if you want a bunch of semi-reasonable test cases for a compiler or something and you generate a bunch of build variants, is the case I was thinking about
-
If you’re generating code, and you’re *not* doing it with an LLM, is it reasonable to use metrics like F1 and recall to measure how well the tools you use are doing? This is bothering me because it feels a bit weird to apply metrics like this to static...If you’re generating code, and you’re *not* doing it with an LLM, is it reasonable to use metrics like F1 and recall to measure how well the tools you use are doing? This is bothering me because it feels a bit weird to apply metrics like this to static analyses, build tooling frameworks, or things that just plain don’t have any recall to begin with.
-
I have a tendency to unintentionally assume all regular expression implementations are pretty much like PCRE, but that's not necessarily the case.I have a tendency to unintentionally assume all regular expression implementations are pretty much like PCRE, but that's not necessarily the case. Only knowing one flavor of regex well might not be enough if you need to use them in different language environments! Example:
"Regex language syntax varies between different platforms; it is not standard. In particular, the “$” anchor does not only match the end of the string in Python and PHP, but it does in JavaScript."
https://best.openssf.org/Correctly-Using-Regular-Expressions
-
That intelligence is artificial, alrightThat intelligence is artificial, alright
-
https://time.com/4558510/electoral-college-history-slavery/ this is worth slightly more texthttps://techhub.social/@GryphonSK/113104867306548705https://time.com/4558510/electoral-college-history-slavery/ this is worth slightly more text
https://techhub.social/@GryphonSK/113104867306548705 -
Duolingo is fun, but why on earth is the icon stuck like this, it looks like it has a head cold? I’d almost rather delete the app than look at thisDuolingo is fun, but why on earth is the icon stuck like this, it looks like it has a head cold? I’d almost rather delete the app than look at this