So I'm reading in the Times that recruiters and HR departments, who for a decade or more have been using AI tools to generate false job postings and manipulate labor-pools, are "Inundated" by an "applicant tsunami" of AI generated resumes and AI-faked confirmation video calls. Apparently, using automated systems to spam an entire industry doesn't result in everyone just shrugging and accepting the situation.
Who could possibly have predicted this...
reshared this
So I spent about 3 hours working with an AI to develop an AI prompt optimized for minimal execution time that would tell the AI to identify product data, product claims, and scientific evidence on a few hundred products, cross reference those data and rank products by likelihood of working as claimed.
We're not there yet, but I really like that on our trial run, the same AI that had helped me write the prompt, upon realizing that it was the chosen executor of that prompt, began it's response with, "OK, This is a massive undertaking..."
Unus Nemo likes this.
reshared this
Thought(s) for the day
The βeverythingβs ending and itβs my faultβ feeling is a chemical lie, not a personal truth.
Allegedly.
It seems that being prescribed Clotiazepam for anxiety has it's positives and negatives.
File under: Things the hospital didn't tell me.
I've been on this stuff for seven months.
Clotiazepam is a class of drug called βthienodiazepinesβ. It is chemically similar to benzodiazepine.
Side effect include insomnia, rebound anxiety, dizziness etc etc etc.
I'm trying to taper off them now like I did venlafaxine. DON'T DO THAT DRUG.
Would explain a lot of things to do with my moods because I thought they weren't that effective. Except just stopping them has screwed me up. Go me!
Oh man--I'm listening to #KALW and their #Tangents program and they just played a song of our times: "Innocent Blood" by #LagosThugs --just the kind of music we need right now.
Bay Area Public Media | News, Music, and Culture | KALW
KALW is an NPR member station rooted in the Bay Area and inspired by the world. We create programs that are informative, innovative, inclusive, and entertaining.KALW
Tom Grzybow likes this.
G. Gibson reshared this.
#HashtagGames
#ReplyGuySaysWhat
The ultimate answer to life, the universe and everything is a warm AR 15.
reshared this
#HashtagGames
#ReplyGuySaysWhat
Yeah, but he's a wartime president and you don't ditch a president in the middle of a war.
reshared this
#HashtagGames
#ReplyGuySaysWhat
You're wrong. I'm right. End of discussion
Ray*mond Li*terally reshared this.
#HashtagGames
#ReplyGuySaysWhat
Trump has done more to deserve the Nobel Peace Prize than Obama ever did.
reshared this
#HashtagGames
#ReplyGuySaysWhat
Your opinion shows that somebody pissed in your cornflakes this morning.
Radio Free Trumpistan reshared this.
NORTH Dakota. And this is the long end of June.
Tom Grzybow likes this.
Tornadoes are moving north, east, and early...
... but not leaving their home-ground either.
Radio Free Trumpistan likes this.
bring the map. Don't let anyone take it from you.
#TimeBandits #GeorgeHarrison
like this
reshared this
Radio Free Trumpistan likes this.
Agreed! Not the least bit surprised that Pythonisto John Cleese was in it...or the dearly departed Shelley Duvall. β€
Edited for the purpose of adding Michael Palin so as not to leave out any Pythonisto in that movie. Adding honorable mention to Katherine Helmond, formerly of "Soap", and Emperor Porridge himself, Warwick Davis (that was a Dr. Who reference).
Unus Nemo
in reply to Blaise • •@Blaise
Are you using a custom LLM or are you using one out of the box? By custom I mean one you built yourself not just one you trained. The results are going to be very interesting as product claims can rarely be accounted for in product data. Marketers have a way of ... well lying is the only appropriate term I can think of. I would love to hear more about this project as it continues. Please keep posting to keep us up to date.
Blaise
in reply to Unus Nemo • •@Unus Nemo No, I'm experimenting to see how much useful work you can get out of a free, public AI service. I generally start with Grok, then attempt to reproduce on ChatGPT and Claude.
My whole project may come to nothing, in the end, because the damned things keep making up some percentage of the data, even if you spoonfeed all the research materials to it and specifically ask it to use only, and all of the data provided. And they lie about what and why they did what they did at least 80% of the time...
I'm at best only about 80% there. I'm not sure my theory of getting the AI to help me write the prompt will turn out to be helpful...
Unus Nemo likes this.