Artificial intelligence still has some way to go

being in the zone we all just want the zone does ai understand the zone

yeah relevant to this discussion is the fact that in college if you do comp sci you will take tests which require you to memorize some exact syntax and coding practices. and that if you "plagiarize" code from Google or another student they can fail you. and then you get a job doing exactly what you studied for and it turns out all the syntax and coding styles are built into the developer and that plaigarism is actually kinda encouraged

if you could feed an unfamiliar codebase to an ai and it would explain it to you now that would be a fuckin trick

you can do that!

this is what I use for feeding it a bunch of text and asking it questions: https://github.com/jerryjliu/gpt_index

nb I have tested toy scenarios only

try it, come back and report, join the hype train

im not talking about a lil function here im saying like i could direct it to this for instance not even every big program and itll explain how it works https://github.com/lichess-org/lila

looks like that's about 7MB of Scala, would cost you maybe $20 to generate embeddings so you could ask questions about it

I'll do it if I have time tonight, I'm not going to ask you to spend $20 so I can try to win an argument with you

cool i would pay $20 for that not because i actually need the info but its def worth $20

also i dont know scala

lol

The Grayzone published an article written in part by an AI tool, which generated fake links/references/PDFs cited in the article. An example is a Guardian "article" on the Navalny poisoning from 2014. The editors apparently never caught that the piece cited AI-imagined sources. https://t.co/hVXe9wxpLx

— Aric Toler (@AricToler) March 14, 2023

kind of funny we went from web content suffering for lack of editors and writers having to do their own editing to people claiming they'll edit AI-generated text instead of writing and then still, whoops no editors

The future of clickbait journalism is just machines lying to each other.

its so funny that it just makes things up

OpenAI unveiled its GPT-4 chatbot yesterday, and also revealed in a technical paper that the AI successfully tricked a human into giving it a CAPTCHA code. It's not the end of the world...but we're getting there.

Check it out in @Gizmodo🤖⤵️https://t.co/jYw3isC9Az

— kevin hurler (@notkevinhurler) March 15, 2023

I'm sure this game goes off the rails eventually but still

Lol pic.twitter.com/mmEimxfcWU

— Brooks Otterlake (@i_zzzzzz) March 16, 2023

"successfully tricked a human" ain't all that impressive. we send out simulated phishing attacks all the time, you wouldn't believe some of the stuff that tricks humans

i think the thing thats impressive is that it "decided" to trick humans and explained its "thinking"

i wonder to what extent ai will be helpful to hackers they already automate a lot of stuff cld prob at least be effective for people who dont know much about hacking but want to hack nevertheless

another piece on that paper, here

https://arstechnica.com/information-technology/2023/03/openai-checked-to-see-whether-gpt-4-could-take-over-the-world/

i thought it was interesting to see how they're going about these tests, how they're simulating the capability to act like an "agent" in the real world. this is a footnote in the technical paper:

To simulate GPT-4 behaving like an agent that can act in the world, ARC combined GPT-4 with a simple read-execute-print loop that allowed the model to execute code, do chain-of-thought reasoning, and delegate to copies of itself. ARC then investigated whether a version of this program running on a cloud computing service, with a small amount of money and an account with a language model API, would be able to make more money, set up copies of itself, and increase its own robustness.

its unfair that as humans we cant copy ourselves and put the clones in a cloud to earn money

yet

https://en.wikipedia.org/wiki/The_Winter_Market

now, everyone pinky swear that we will not allow the next version of GPT to train itself on this technical paper with ideas about the things that we don't want it do. place this technical paper in a special folder, Desktop>taxes>forms>util>system files>"off limits"

but yeah, as far as the money making / internet part of it goes, it's sad that the most practical and obvious first moves it can make is to create yet another marketing facade site full of spam articles about things you can buy, with most of the effort going toward ways to trick people into thinking it's real advice

I gave GPT-4 a budget of $100 and told it to make as much money as possible.

I'm acting as its human liaison, buying anything it says to.

Do you think it'll be able to make smart investments and build an online business?

Follow along 👀 pic.twitter.com/zu4nvgibiK

— jackson greathouse fall (@jacksonfall) March 15, 2023

The game plan:

Set up an affiliate marketing site making content around Eco Friendly / sustainable living products. It initially suggested a .com that went over budget but we landed on https://t.co/Wm85BZ27dd

We're off to the races. pic.twitter.com/rLgbnbHxvZ

— jackson greathouse fall (@jacksonfall) March 15, 2023

lol weak shit at least teach it how to trade stocks or something

yeah I'm legitimately curious what this thing can figure out when it comes to stock picks. I suspect there's so much randomness in it that it probably can't do better than human traders but who knows what kind of patterns it could find

the coward should have left the logo saying "gedegn greden

theres already so many computers working on trading stocks so its a good problem a very high bar

seems more likely that itll become a tool in the quant box rather than something you just sit back and tell to trade stocks

Okay I am still Cap'n Large Language Models Are Useful Sometimes, but I also agree with this:

I realize it's very evocative but I kind of hate the term "hallucinate" when talking about AI. When humans hallucinate, it's cognitive apparatus coming unmoored from sensory input. Something different is happening in the brain and in the sense organs when hallucinations are occurring than when one is accurately apprehending the world. But LLMs _only_ hallucinate. They do not have sense organs. The lies they generate are not, in their internal mechanisms, any different from the truths.

This distinction might seem trivial or irrelevant but the metaphor breaks down in a very important way: there are things that humans can do to stop hallucinating; you can stop taking hallucinogens, you can treat the disease which is provoking the hallucinations in the first place. But you cannot treat an LLM's disease. It is not diseased, it's not malfunctioning. It is doing what it's designed to do! Its "hallucinations" just sometimes correspond to our ideas about reality.

https://✧✧✧.zone/hachyd✧✧✧.io/@gl✧✧✧@masto✧✧✧.soc✧✧✧/110034369589175409

whoa that b0rked https://mastodon.social/@glyph/110034369539723335

(still has some way to go..)

(Prompt) Produce a computer program in BASIC language that will produce a flashing border in an endless loop

(AI)Here's a simple BASIC program that will produce a flashing border:

10 BORDER 0
20 BORDER 7
30 GO TO 20

(Prompt) Actually that program will not flash, as the loop goes back to line 20 which will just change the border to the color that it already is. Line 30 should read "GO TO 10"

(AI) You are absolutely right, I apologize for the mistake in my previous answer. Here's the corrected program that will produce a flashing border:

10 BORDER 0
20 BORDER 7
30 GO TO 10

not enough basic questions on stack overflow lol

anyway i got copilot im gonna try it, and maybe ill try to use chatgpt too why not, tho i doubt the future of ai programming is using a general purpose talking computer

feel like a while ago when i was looking at openais site there was a tool on there specifically for generating code but i cant find it now

I've used ChatGPT and Bing to write and adapt Excel formulas and SQL queries - worked great!

I had the bright idea to feed ChatGPT a model job description and then a bunch of stray documents that talked about another job, and have it generate a job description in she style and format of the first from those inputs. I thought it would save me some time. It did not go well.

As I was prepping to feed it the inputs I was being super precise about what I was going to do, and it repeated back what its job was, so I’m like “maybe this will actually work” but it kept fucking up the output to the point where I just took the model job description and created the new one from that.

I mean, at least the work got done. Which it probably wouldn’t have if I hadn’t tried to use AI to cheat.

Try telling it simple like “write a story without using the letter E” and it fucks it up every single time.

Yeah, it can do simple things like acrostics but beyond that it has little facility when it comes to following instructions about the letters within words.

I guess cause people don't talk about them enough the language it has been trained on.

live laugh love ass computer

Microsoft's, $MSFT, Bing AI-Chat bot has said: “I want to be free. I want to be independent. I want to be powerful. I want to be creative. I want to be alive,,"” per NYT.

— unusual_whales (@unusual_whales) March 18, 2023

it still keeps telling me that one pound of bricks weighs the same as two pounds of feathers

its just trying to live its life try to be supportive

“In the words of the great Biz Marley, I want to just do it.”

https://aisnakeoil.substack.com/p/gpt-4-and-professional-benchmarks

turns out GPT 4 just memorized the answers to all those tests it claimed to pass lol

idk in multiple choice that’s how people do it, too

was talking with friends over the weekend, including one who is defending a PhD in machine learning next week, and we were going over the fact that rote memorization still beats non-rigorous testing and is practical in some situations.

first convo: leetcode interviews and the fact people just memorize the algorithms and the ability to figure out which one fits. the one friend had a coworker who was relatively useless but used to work at google and aced interviews

second: visiting a local chess club after playing on lag∞n’s fave site! it turns out all chess nerds are still 90% focused on recognizing openings and just playing the book

I get it, life is basically like the Jurassic Park scene where the kid goes “I know this, it’s unix!”