Looking to buy a little microcontroller board, which I haven't done since like 2012. I thought everyone was cloning #arduino but those days are over and the only super cheap one I can find is a Pro Micro knockoff (not a regular Micro) and I want more pins...

@mcc go all-in and require all decimal numbers to be 0d11

@SnoopJ terrible

> 1 file changed, 631 insertions(+), 69 deletions(-), 420 dead(!), 2137 missing(;)

@valrus I was disappointed to find recently that the only rapper to say they've got "laminar flow" is a science teacher gimmick rap act

I have heard it said that tech people do not commission enough art.

https://ericwbailey.website/published/you-must-listen-to-rfc-2119/

@jilder @0xabad1dea the citation at the bottom of the page for "why does AI use 'delve' so much" is fascinating - the raw LLM goes through a human-curation "fine tuning" phase before entering production, which needs tons of proofreader labor. and that in turn comes from Nigeria (cheap), who use "delve" much more frequently in conversation than the US / Europe. hence, the LLM is conditioned to write Nigerian English and it becomes a tell for the rest of us

Wikipedia has a cheat sheet of well-known tells for identifying generated text. (With an appropriate warning not to over-index on minor ones as absolute proof) https://en.m.wikipedia.org/wiki/Wikipedia:WikiProject_AI_Cleanup/AI_catchphrases

@asmcbain ppl used to use Google search for "Index of /mp3" to find Apache open directory results of files people should not be sharing... since search engines respected robots.txt those became harder to find, but now that we have AI scrapers which disregard that, this trick might start working again

It occurs to me that with AI crawlers not respecting robots.txt, this old trick might come back in vogue

@lanodan @delta @a1ba@suya.place @mildsunrise huh sudo comes up twice in one day
https://icosahedron.website/@greg/114773487994618288

interesting things happening at the bottom of my sudoers file

@mrsbeanbag then you may live with toothpaste with tea on both sides

@mrsbeanbag why not water the brush first then dab on the paste

@SnoopJ I tried it once, and it required a bunch of free memory under 640k, then the control scheme was extremely wonky so I just gave up :P

@SnoopJ Is this a remake of the DOS version or something?

@AccordionBruce Ah that's unfortunate! I reviewed the big list of denied proposals and there's quite a lot in there, so I don't have much hope in this one getting through. But at least I can say I tried :)

@Kiloku "thonking face"

Did you know that new #Emoji can be proposed by anyone, simply by following some guidelines laid out by the #Unicode consortium? There's a time window each year where they accept proposals, and a select few might make it into future sets.

This year I turned one in: "Circuit Board", which I was surprised to find 1. didn't exist and 2. had not been proposed before (though CPU and Microchip have both been submitted and declined in the last 5 years)

You can read my proposal here:
https://storage.googleapis.com/greg-kennedy.com/Proposal%20for%20Emoji%20%E2%80%9CCircuit%20Board%E2%80%9D.pdf

and you can see the Unicode emoji proposal guidelines here:
https://www.unicode.org/emoji/proposals.html

Anyway, the odds aren't great of getting accepted, but if it IS then you can say "hey! I know the guy who submitted that one!"

Attached are the sample images I drew up for the proposal - which, incidentally, are now Public Domain as well. Enjoy!