Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

ChatGPT Cheat Sheet

drive.google.com

Post reply on HN
Print view View original

81–90 of 145 posts

Re: ChatGPT Cheat Sheet

#81

Post by time_to_smile »

slaymaker1907 wrote: post #68
scifibestfi wrote: post #9

I'm trying to understand how big of a deal ChatGPT and the like is or isn't. Even people in AI don't seem to agree on whether it's going to change everything or it's overhyped and not a major advancement. Which is it? Or somewhere in the middle? "if you think AI chatter has reached an annoying level right now you're in for something else. it's going to be the only thing on anybody's mind starting shortly... i'm findi…

ChatGPT made me rethink my assessment of how close we are to general AI. I was of the opinion that we need some major architectural innovations to actually get to general AI and while I think we still need some huge discoveries, I think ChatGPT was one of those milestones.

Has everyone else been using a different tool than me? ChatGPT is interesting, but is laughably bad at any non-trivial instruction.

It's fantastic at generating content that on first glance looks remarkably right, but always fails fine inspection.

All I've seen from LLMs is much better demos of the types of funny things markov chains were generating two decades ago (anyone remember the various academic paper generators?). However I have yet to see anything that stands out as really remarkable.

My read is that people want to see incredible progress towards strong AI, and LLMs do a great job of letting people feel like they're seeing that if they want to.

I suspect in 5 years we'll largely have forgotten about LLMs and in 10 they'll come back into popularity because techniques will become more efficient and computing power will increase enough that people can train them on their home PCs... but they'll still just be a fun novelty.

Re: ChatGPT Cheat Sheet

#82

Post by sarchertech »

simonw wrote: post #71
6keZbCECT2uB wrote: post #53

Earlier quoted context omitted.

I think that ChatGPT could be a big accelerator for creative activity, but I wouldn't trust any output that I've only partially verified. That limits it to human scale problems in its direct output, but there are many ways that human scale output like code snippets can be useful on computer scale data.

There are plenty of valuable use-cases that aren't at much risk from hallucinations at all: - Asking it to summarize text - Using it to extract facts from text and present them in an alternative format - turning a chunk of HTML into JSON for example - Creative writing - poems, stories etc - Getting feedback on your own text - asking it what should be tightened up, which bits are confusing and so on - All kinds of cod…

> turning a chunk of HTML into JSON for example

I haven't done exactly that, but based on similar examples this is likely very vulnerable to hallucinations.

Re: ChatGPT Cheat Sheet

#84

Post by flir »

aradox66 wrote: post #74
flir wrote: post #65

I can throw a couple more in: If you split the song generation and the chords ("write me a song in the style of Nick Cave"/"Can you suggest a chord progression for the Nick Cave song you wrote earlier?") I find you get a more complete explanation of the chords ("This progression uses mostly basic chords that are easy to play and allows for a lot of room for interpretation and personalization. The G to C progression i…

I have had zero success getting a guitar tab out of ChatGPT. Well, sometimes it'll write a short tab, but it will be total nonsense. Any suggestions?

No, simple here, too ("Can you write a guitar tab for a folk song?"). I suspect it's like the code generation - good for 10 line functions, bad for writing a Photoshop clone.

Re: ChatGPT Cheat Sheet

#85

Post by tmountain »

williamcotton wrote: post #50
scifibestfi wrote: post #9

I'm trying to understand how big of a deal ChatGPT and the like is or isn't. Even people in AI don't seem to agree on whether it's going to change everything or it's overhyped and not a major advancement. Which is it? Or somewhere in the middle? "if you think AI chatter has reached an annoying level right now you're in for something else. it's going to be the only thing on anybody's mind starting shortly... i'm findi…

"if you think AI chatter has reached an annoying level right now you're in for something else. it's going to be the only thing on anybody's mind starting shortly... i'm finding it a bit hard to communicate the urgency and heaviness of what's going on" "Personally I can give you a formal definition of intelligence and even a number of speculative sketches of how I think it could be implemented, but I will also tell yo…

Sounds awesome, care to share?

Re: ChatGPT Cheat Sheet

#86

Post by imoverclocked »

vb-8448 wrote: post #42
scifibestfi wrote: post #9

I'm trying to understand how big of a deal ChatGPT and the like is or isn't. Even people in AI don't seem to agree on whether it's going to change everything or it's overhyped and not a major advancement. Which is it? Or somewhere in the middle? "if you think AI chatter has reached an annoying level right now you're in for something else. it's going to be the only thing on anybody's mind starting shortly... i'm findi…

The main problem is that, if you don't know enough details about the domain, *you can never be sure that the response is correct or not*. So, if you are using it as a “personal assistant” and “supervise it” is a big (very big) deal since it's going to save a lot of time. There are also some unknowns related to the cost/time needed to train and run the infrastructure behind it that could change a lot of things.

After dealing with a lot of contractors for my house, I feel like close supervision with knowledge of the problem domain is also required of many humans.

Re: ChatGPT Cheat Sheet

#87

Post by omgomgomgomg »

Hedepig wrote: post #49
omgomgomgomg wrote: post #34

Chatgpt certainly spits out answers and is often right or reasonably close to right. But it cant be trusted on complex tasks and I do not think it is a good AI, I have to repeat, this thing is supposed to be an AI,but it does the AI part very poorly. We all know it will trip over questions like what is the record for crossing the atlantic by car/foot and such. But I have realized there is no feedback loop, or a wrong…

Despite all the (legitimate) criticisms, I still don't understand how some people are not impressed by what has been achieved by OpenAI. I agree, it's far from perfect, but as a tool it's certainly usable and useful, with quite fascinating emergent behaviour.

I agree, it is something new and refreshing, I consult it frequently on random matters out of curiosity.

It appears it can pass faculty tests, but lets keep in mind you do not need a 100/100 accuracy for that, but in business apps like in fintech, you better deliver 100/100.

So far, it is concatenating google search results and displays that in readable manner.

Co-pilot comes up with better code so far.

I am curious to see where this is going, there must be a plan to monetize, this launch and media presence cannot be explained away differently.

Re: ChatGPT Cheat Sheet

#88

Post by scottLobster »

gcanyon wrote: post #69
scottLobster wrote: post #39

Earlier quoted context omitted.

IMO it's analogous to adaptive cruise control on cars. It's very useful in certain specific circumstances, and genuinely helpful. But not yet necessary or transformative unless you live in LA/sit in traffic for a living. People are claiming to use it to write code, I'm curious how sophisticated said code is. Sure it might take out of some of the grunt work, like an ultra-sophisticated find-and-replace, but you still…

Re: how sophisticated the code it generates is: I wrote up generating code in a language I'm very familiar with here: https://docs.google.com/document/d/1W3j5WaFhYZaqSt0ceRQj8j16... tl;dr: in some instances I had to coach it pretty directly to get what I wanted. In other instances it was flawless. And to your point, some of the code it generated was both clearer and faster than the code I would have written for the s…

Sure but this kinda proves my point. It can potentially generate good code for simple, atomic problems. It can't write me a REST service that hooks into an existing web backed spread over multiple repos of proprietary code.

Any relationship not visible in the code seems to be outside its capabilities to understand for the moment. I'll be impressed when I can point it at a server cluster and the associated dozen repos, give it some clues, and it can understand how the code for a server cluster interacts with said cluster's configuration and database hookups by simply scanning the files/repos and the info I textually provide.

Re: ChatGPT Cheat Sheet

#89

Post by knome »

scrollaway wrote: post #64
lukev wrote: post #59

Earlier quoted context omitted.

That's because it's a large language model, not an AI. Anyone calling it an AI is buying/selling the hype cycle, or (at best) using an over-general term for ML in general.

Super disingenuous. It's an "AI chatbot", by a company called "OpenAI", whose goal is to "make AI systems more natural". It's artificial, and it actually shows some forms of intelligence including chain-of-thought and understanding of natural language. It's also clearly the most advanced AI product available to date. Meanwhile, I'm almost certain you have no problem saying a guard NPC in Skyrim has "an AI", so, eh.

every time we reach an AI goalpost, someone is quick to claim that goalpost wasn't /really/ AI.

Re: ChatGPT Cheat Sheet

#90

Post by highhedgehog »

Daunk wrote: post #80
highhedgehog wrote: post #78

little bit of a side question here, but. I've been wanting to try chatGPT for weeks and it seems it's always busy. Is this actually what it is? Or is there a place somewhere else where I can test it?

It's working just fine right now over at - https://chat.openai.com

not for me. I keep getting "ChatGPT is at capacity right now". Could it be localized? like, only from the US?
Post reply on HN