A place to share screenshots of Microblog posts, whether from Mastodon, tumblr, ~~Twitter~~ X, KBin, Threads or elsewhere.
Created as an evolution of White People Twitter and other tweet-capture subreddits.
Rules:
Related communities:
https://twipped.social/@twipped/114662771295312758
article they are referencing: https://futurism.com/atari-beats-chatgpt-chess
LLM sucks at maths, sucks at chess, sucks at remembering stuff and being consistent ... They suck at everything a computer is usually good at.
It's a very specialized program intended to get a computer to do something that computers are generally very, very bad at - write sensible language about a wide variety of topics. Trying to then get that one specialized program to turn around and do things that computers are good at, and expect to do it well, is very silly.
Yes, LLMs are designed to emulate how a human would respond to a prompt by digesting a huge amount of human-generated content. They can do that fairly well except when they can't.
Nobody thought it would do very well. This was a software dev's little diversion.
We should praise attempts to make the public aware of the limitations of LLMs, not laugh at the guy who did this.
Asking ChatGPT to play chess is like asking someone who's not played Chess to play well, and then documenting how poorly it played. Like no shit the hammer did a bad job as a saw. You wanted it cut, you should have used the tool for the job.
ChatGPT isn't Deep Blue. It's not made for that. You're asking a word processor to calculate pi.
Yes but there are many out there that don't have this sort of understanding and believe the LLMs can do almost anything.
There people are the higher ups at large companies...
It also demonstrates how much AI companies mislead the public on what their products can do. If a guy is selling lawnmowers that actually just generate grass clippings without mowing the lawn, you’re not an idiot for thinking it was going to mow grass.
furthermore. companies mislead journalists, investors, philosphers, influencers etc. most of which dont have a technical background but a lot of reach. They then carry their misunderstanding into the general public.
All these public "academic" panel debates on conferences about AGI being the next nuclear weapon and singularity. They lead to Highbrow publications, opinion peaces, books and blog articles, which then lead to tweets, memes and pop cultural references
Huh.... wait... what if we make a box... generate electricity bills... Call it a crypto miner?
Cram a bunch of space heaters into a box. Convince investors that all the electricity it burns up means it's basically printing money. The building will inevitably burn down before anyone can investigate our claims.
But once someone explains it to you and you insist the grass was mowed, they show you the unmowed grass, and you still insist it's great for mowing lawns.
And also you're in the desert where you shouldn't even have a fucking lawn, and you plant more lawns because they're so easy to mow now
What do you call that? Because it's a bit past 'idiot'.
Using an LLM to play chess is like using autocorrect to write a novel.
And that's the big problem with AI right now. People don't understand what it is, they just want the label slapped on to as many things as possible.
AI is the new IoT, it will be integrated into everything, less than useless for 99.9% of consumers, and yet, still wildly successful.
Given how much it costs it will need to be ten times more successful than web search to even hop to break even. It's the biggest dot com bubble yet.
It's because the venture capitalists who are sinking BILLION$ into these things are calling it AI even though it's not and literally never will be. And unfortunately, too many people are too stupid to understand that these aren't AI but Generative Adversarial Networks or GAN's for short. Which doesn't sound as sexy and "take my money please"-ish as Artificial Intelligence or ✨AI✨ does.
These will never be HAL9000 or Jarvis or even Roku's Basilisk. The stuff needed for that kind of "intelligence" doesn't exist in these things. And the sooner people come to realize that this is all just digital snake oil the sooner we can collectively get on with our lives.
Using an LLM to play chess is like using autocorrect to write a novel.
Hundreds of billions of dollars spent
No profitable product
No consistently usable product other than beginner code tasks
Massive environmental harms
Tens of thousands of (useful!) careers terminated
Destroyed Internet search, arguably the one necessary service on the Internet
No chance it's going to get better
Atari 2600 beating it at chess is a perfect metaphor. People who want to complain about it can bite its plastic woodgrain printed ass.
That's a very good move! To counter, you should follow these three principles:
Prepare a response move that will prevent a future good move.
Defend your own pieces and try to attack theirs.
Don't be too eager to sacrifice pieces in order to make short term gains.
Be prepared to sacrifice an unimportant piece to make a good gain.
If you want to make a good move, try Rook H8 -> G7.
Alt text
Me: Knight to C3
ChatGPT: You've played Knight to C3 — a classic developing move! That suggests we’re likely in the early phase of the game, possibly playing something like:
or perhaps you're playing the English or Reti and going for flexibility.
Let me know the full board state or moves so far if you'd like to continue the game or get commentary!
Queen to queen's bishop three, Captain.
I mean, you literally have whole videos on YouTube made by GothamChess who shows how LLMs play chess. They literally spawn pieces from air, play moves that are illegal etc.
I'm quite sure that the guy understood pretty well what LLMs can do. He just wanted to deinflate all the bullshit promises by Techbros
Man that sucks
They could probably have done better by training a crow to play chess.
Chess engines don’t have real difficulties. Every level of the chess engine is designed to make more blunders as the elo gets smaller.
In other works it is programmed to make bad moves in regular intervals. What that means is even on beginner modes when the engine isn’t blundering it is playing perfect chess. This is why it isn’t good to play against chess bots. At best you will learn some pattern recognition but chess puzzles are better at that.
In CoD MW 2 (or maybe Black Ops) the multiplayer AI bots were like this. Obviously all bots are but the kill cams were illuminating. And they didn't even try to make it look human. They'd even use a light machine gun. They'd walk around. Once they see you they'd turn towards you. The only thing the difficulty changed was how fast they turned. Then they'd shoot a single shot at your head. For things like a sniper rifle it looked mostly believable, but that's not how people use machine guns lol. The single shot with the most inaccurate weapon is just dirty lmao.
You could train an AI just to play chess. Sites like chess.com have tens, hundreds of millions of games to use as training data. But the AI isn't "thinking" though, it's just being asked given this input, what's the most likely outputs and picking one based on its settings. Then the other player moves, the context updates, rinse, repeat. Such an AI would likely whoop most people's asses but experienced players might figure how to lead it down a path where it doesn't sufficient training data to play strongly.
But it's not a generalized LLM like ChatGPT where it's picking up a handful of chess games from god knows without knowing or enforcing the rules or anything else.
Likewise I bet we'll see AIs for poker and other lucrative online sports. I bet a lot of online casinos have amassed huge stores of data to produce AIs, as well as players using scraping or logs to do the same. I could even see online casinos running AIs in games because it's a way of taking money from players beyond the normal rake.
Casinos are such a scam. The few skill based games where you actually can manage to get an edge they just stop you from playing if you're doing well. We'll never see much use of poker/blackjack bots because if they catch on they'll just limit your winnings.
LLMs can't beat anyone or anything at chess because they can't play chess at all. Try it. They don't get more than a few moves in without degrading into total nonsense.
I don't know if this is real, but AI for chess kinda has to be tailor made for chess, right?
Yes the point is that LLMs don't reason.
These articles aren’t written for people who know how LLMs work or what they do, anyway.
It’s to prove to everyday people that the techbro marketing is bullshit and these are limited tools, not conscious beings. The populace is being sold a hammer that hallucinates and told everything is a nail.
By my best feelings, this shit is a bigger bust than the .com bubble, and I predate that latter shit by roughly twenty years.
I'm quite sure that you could use a LLM to play chess and probably even successful, but you need to train it on chess notation of games instead of a pile of fanfiction and other copyright infringements. I have considered trying that but was turned off by how inaccessible LLM training is and how difficult it would be to get a sufficient amount of games written in proper chess notation. Obviously this would not be a real LLM, as it does not "speak", but I was curious how well this would work utilizing the same technique.
I had a dedicated electronic chess game - a board with LEDs on it showing where the game wanted to move. You had to move physical pieces around and press membrane switches under the squares to tell it where you moved. I don't remember if it was described as "AI" back then or not. I thought of it as a chess expert system on a chip. As a total novice player I could rarely beat it on its lowest skill level. Was never interested enough in chess to get the game for my 2600. But I still have both of those things in a box.