Initial thought: Well… but this is a transparently absurd way to set up an ML system to manage a vending machine. I mean it is a useful data point I guess, but to me it leads to the conclusion “Even though LLMs sound to humans like they know what they’re doing, they does not, don’t just stick the whole situation into the LLM input and expect good decisions and strategies to come out of the output, you have to embed it into a more capable and structured system for any good to come of it.”

Updated thought, after reading a little bit of the paper: Holy Christ on a pancake. Is this architecture what people have been meaning by “AI agents” this whole time I’ve been hearing about them? Yeah this isn’t going to work. What the fuck, of course it goes insane over time. I stand corrected, I guess, this is valid research pointing out the stupidity of basically putting the LLM in the driver’s seat of something even more complicated than the stuff it’s already been shown to fuck up, and hoping that goes okay.

Edit: Final thought, after reading more of the paper: Okay, now I’m back closer to the original reaction. I’ve done stuff like this before, this is not how you do it. Have it output JSON, have some tolerance and retries in the framework code for parsing the JSON, be more careful with the prompts to make sure that it’s set up for success, definitely don’t include all the damn history in the context up to the full wildly-inflated context window to send it off the rails, basically, be a lot more careful with how to set it up than this, and put a lot more limits on how much you are asking of the LLM so that it can actually succeed within the little box you’ve put it in. I am not at all surprised that this setup went off the rails in hilarious fashion (and it really is hilarious, you should read). Anyway that’s what LLMs do. I don’t know if this is because the researchers didn’t know any better, or because they were deliberately setting up the framework around the LLM to produce bad results, or because this stupid approach really is the state of the art right now, but this is not how you do it. I actually am a little bit skeptical about whether you even could set up a framework for a current-generation LLM that would enable to succeed at an objective and pretty frickin’ complicated task like they set it up for here, but regardless, this wasn’t a fair test. If it was meant as a test of “are LLMs capable of AGI all on their own regardless of the setup like humans generally are,” then congratulations, you learned the answer is no. But you could have framed it a little more directly to talk about that being the answer instead of setting up a poorly-designed agent framework to be involved in it.

Yeah it’s a bunch of shit. I’m not an expert obviously, just talking out of my ass, but:

1. Running inference for all the devices in the building to “our dev server” would not have maintained a usable level of response time for any of them, unless he meant to say “the dev cluster” or something and his home wifi glitched right at that moment and made it sound different
2. LLMs don’t degrade by giving wrong answers, they degrade by stopping producing tokens
3. Meta already has shown itself to be okay with lying
4. GUYS JUST USE FUCKING CANNED ANSWERS WITH THE RIGHT SOUNDING VOICE, THIS ISN’T ROCKET SCIENCE, THAT’S HOW YOU DO DEMOS WHEN YOUR SHIT’S NOT DONE YET

Hey, try this instead:

“We have an armed response force ready to protect you against ICE if they come to try to snatch you. We have lawyers at the ready, and we’re fine mobilizing the state’s National Guard if it comes to that. If you’re in another part of the country and worried about your safety, come to Vegas! You can do some gambling and see the sights without worrying if you’re going to make it home to your family or not.”

Guaranteed spike in tourism. Don’t just ask for what you want. Earn it.

“Don’t worry,” I said. “It’s just because it’s new. The novelty will wear off. And if it doesn’t, we’ll get rid of it.”

I feel like this belongs in a horror movie

Edit: Jumping Christ

“I’m afraid I’m locking you in a cupboard,” I inform it after it asks if I’m ready for some fun. “Oh no,” it says. “That sounds dark and lonely. But I’ll be here when you open it, ready for snuggles and hugs.”

Also, spoiler for the article: The kid quickly got bored and moved on from the toy because the toy kind of sucks. She is ahead of some tech CEOs I could name.

I think the crisis of Trump is likely to be worse than any crisis in the Western world for the last 50 years. I think the closest analogue is probably the collapse of the USSR. So yes, some of the rich people upped their wealth by orders of magnitude, and honestly you might be right that Zuck might manage to be one of that category, but also some of them lost everything or got thrown out windows, or had to survive in reduced capacity within their new walled fortresses in the horrifying new meta. I feel like more likely is that the MAGA world will remember Facebook censoring their posts about ivermectin, and not feel like Zuck needs to have a seat at the table, no matter how many ass-kissing sessions he shows up at the White House to do.

For example I feel like breaking up Meta and mandating Truth Social and TikTok as the only new sanctioned social media going forward might be one possible outcome. It’s kind of hard to say and I won’t swear that you’re definitely wrong that he might come out way ahead in the end. I’m just saying that this type of crisis is a very different type of crisis.

Part of my point is that the damage Trump is going to do will cost them tons more money than if they had helped to prop up the fairly safe and civil society they previously were allowed to exist within, under which secure umbrella they’ve been able to rake in money like leaves in autumn on a wide country estate.

Hopefully the idiots who run these tech companies will learn their lesson soon.

“If the thing is free, you’re the product” applies just as much to dinners at the White House as it does to social media apps.

“Meatball Ron” was another stroke of real genius. “Sloppy Steve” was another decently good one, but honestly, “Weird Stephen” is fuckin’ perfection.

Got it. I tried to watch the movie but I wasn’t into it. I may check out the comics, they are clearly a masterpiece. Sometimes you don’t have to look at too much of something to tell.

Trump’s biographer Michael Wolff previously said on The Daily Beast Podcast that the president has a less-than-flattering nickname for one of his most loyal henchmen: “Weird Stephen.”

Honestly, even with his brain mostly rotted away now, little glimpses of Trump’s idiot-savant ability to bully at a grandmaster level can still shine through sometimes.

Is this “Weird Tales”? I found some of them in a comics collection when I was little and some of the stories fucked with me.

It is shocking to remember sometimes, but hypocritical self-centered ass gaskets are represented in every racial grouping. The white people voting for Trump are fucking themselves just as are the Cuban people voting for Trump, and they all got hoodwinked into it via pretty much the same methods.

First possibility that comes to mind is a backed up federation queue on lemmy.world for some reason.

It could also be some failure on sh.itjust.works, but if I had to guess I would say it’s more likely an issue on the sending end.

If you look at a lot of the weird stuff that LLMs create, and just remember that they’re predicting the next symbol one token at a time without engaging any factual reasoning, it makes perfect sense why they are doing the weird shit that they’re doing.

Yep, I’m pretty sure that’s the one. Thank

In retrospect, Seinfeld was a very dark show. Somewhere on YouTube there is an insightful little video essay about how the first few seasons of the show are basically the story of how Elaine, a perfectly decent person, gets drawn into their little circle and over time adopts their awful selfishness and sociopathic behavior to try to fit in. How most of the problems of the show are caused by their selfishness and dishonesty, and often involve significant harm coming to someone else, and they don’t care.

I can’t even remember which comedian it is, but someone had a bit about how the darkest joke he ever heard was a Seinfeld bit about being at the movie theater and just throwing his drink on the ground at the end for someone else to clean up. Like it’s a small thing, but the guy talking about it was genuinely alarmed by the depth of how far he genuinely just doesn’t give a fuck and doesn’t mind if you know it.

That oughta fix it

Yeah, dental issue. Sure.

“This is forbidden! It is illegal for you to do this!”

“Hey remember when you shot those kids?”

“Yeah but that was fine tho”

FAFO

One of the very few times recently I have felt proud of my country was reading stories about pickpockets at the Paris Olympics, encountering the new phenomenon of Americans who when they get pickpocketed would respond by physically assaulting the pickpockets and taking back their stuff.

“Le merde! This is forbidden! Unfair!” lol