Major outages across ChatGPT and API • Hacker News Board

Re: Major outages across ChatGPT and API

#541

Post by faeriechangling » Thu, Nov 09, 2023, 6:04 AM UTC

glitchcrab wrote: post #499

Alupis wrote: post #468

Earlier quoted context omitted.

What makes you think ChatGPT isn't also returning false and/or misleading info? Maybe you just haven't noticed... Personally, I struggle with anything even slightly technical from all of the current LLM's. You really have to know enough about the topic to detect BS when you see it... which is a significant problem for those using it as a learning tool.

This is my problem with chatgpt and why I won't use it; I've seen it confidently return incorrect information enough times that I just cannot trust it.

I get information from unreliable sources all the time. In fact all my sources are unreliable.

I just ignore how confident ChatGPT sounds.

Re: Major outages across ChatGPT and API

#542

Post by baq » Thu, Nov 09, 2023, 6:36 AM UTC

dcchambers wrote: post #538

baq wrote: post #407

Earlier quoted context omitted.

Nothing stopping you from buying an H100 and putting it in your desktop. As for me, I’ve got other uses for $45k.

If you wanted to buy one...are you even able to order one? Aren't they massively backordered by big companies? Is there a black marker for H100 cards?

I took the quote from eBay. Not sure which shade of black that would be ;)

Re: Major outages across ChatGPT and API

#543

Post by lodovic » Thu, Nov 09, 2023, 6:49 AM UTC

Alupis wrote: post #468

wfhBrian wrote: post #453

Earlier quoted context omitted.

People constantly recommend Bard to me, but it returns false and/or misleading info almost every time

What makes you think ChatGPT isn't also returning false and/or misleading info? Maybe you just haven't noticed... Personally, I struggle with anything even slightly technical from all of the current LLM's. You really have to know enough about the topic to detect BS when you see it... which is a significant problem for those using it as a learning tool.

True, it often returns solutions that may work but are illogical. Or solutions that use tutorial style code and fall apart once you tinker a bit with it.

Re: Major outages across ChatGPT and API

#544

Post by lodovic » Thu, Nov 09, 2023, 6:53 AM UTC

tombert wrote: post #313

verdverm wrote: post #309

Earlier quoted context omitted.

Bard has different training data and regime, that alone is enough to start to understand why they are different. The main thing as a user is that they require different nudges to get the answer you are after out of them, i.e. different ways of asking or prompt eng'n

Yeah, which is why I use the paid version of ChatGPT still, instead of the free Google Bard or Bing AI; I've gotten good enough at coercing the GPT-4 model to give me the stuff I want. Honestly, $20/month is pretty cheap in my case; I feel like I definitely extract much more than $20 out of it every month, if only on the number of example stubs it gives me alone.

Is there a difference between OpenAI and Bing AI? They both claim to use GPT-4.

Re: Major outages across ChatGPT and API

#545

Post by jakereps » Thu, Nov 09, 2023, 7:03 AM UTC

mawadev wrote: post #193

I noticed the outage. It feels like a lot of people use it like training wheels on a bicycle until they forget how to ride without it.

Seems more like a crutch in that sense, then. If you can’t ride without it, it hasn’t trained you anything.

Re: Major outages across ChatGPT and API

#546

Post by paradite » Thu, Nov 09, 2023, 7:21 AM UTC

all2 wrote: post #390

I'd be curious to hear about the workflows people have come up with using ChatGPT. I'm still in the realm of "I don't know how to do this" or "I forgot the exact incantation to that" or "is the an X that does Y in framework Z?"

I experimented with using a streamlined workflow to use ChatGPT (GPT-4) for coding tasks.

In the end I settled on a standalone desktop app to "compose" prompt with source code, instructions and formatting options which I can just copy paste into ChatGPT.

The app is available for download if anyone is interested: https://prompt.16x.engineer/

Re: Major outages across ChatGPT and API

#547

Post by zer0c00ler » Thu, Nov 09, 2023, 7:23 AM UTC

rockinghigh wrote: post #496

m3kw9 wrote: post #161

Earlier quoted context omitted.

Bard is still playing scared, it isn’t even international yet

Bard is available in 40 languages and 230+ countries: https://support.google.com/bard/answer/13575153?hl=en

I don’t think there are 230+ countries, at least not on this planet.

Re: Major outages across ChatGPT and API

#548

Post by jfoster » Thu, Nov 09, 2023, 7:58 AM UTC

guiambros wrote: post #526

jfoster wrote: post #510

Earlier quoted context omitted.

I asked Bard the question "Who is Elon Musk?" The response: "I'm a text-based AI, and that is outside of my capabilities."

That's interesting. Did you have anything else in the thread, or was it just the first question? For me it returns a seemingly accurate answer [1], albeit missing his involvement with Twitter/X. But LLMs are intrinsically stochastic, so YMMV. [1] https://g.co/bard/share/378c65b56aea

It was the first question in the thread, and I've been testing queries along these lines on it for a while. Interestingly, it started writing a response initially and then replaced it with that. It used to refuse to answer who Donald Trump is as well, but it seems that one has been fixed.

Another interesting line of inquiry (potentially revealing some biases) is to ask it whether someone is a supervillain. For certain people it will rule it out entirely, and for others it will tend to entertain the possibility by outlining reasons why they might be a supervillain, and adding something like "it is impossible to say definitively whether he is a supervillain" at the end.

Re: Major outages across ChatGPT and API

#549

Post by zhenyakovalyov » Thu, Nov 09, 2023, 8:01 AM UTC

tombert wrote: post #214

I used Google Bard for the first time today specifically because ChatGPT was down. It was honestly perfectly fine, but it has a slightly different tone than ChatGPT that's kind of hard to explain.

i like antropic’s claude.ai, use them side-by-side.

Re: Major outages across ChatGPT and API

#550

Post by vasco » Thu, Nov 09, 2023, 8:09 AM UTC

TillE wrote: post #517

tombert wrote: post #214

I used Google Bard for the first time today specifically because ChatGPT was down. It was honestly perfectly fine, but it has a slightly different tone than ChatGPT that's kind of hard to explain.

I've found that Bard has an overly aggressive filter, like if I'm brainstorming ideas about thieves in a fantasy world (think Lies of Locke Lamora), it will frequently refuse to cooperate. I think it's running some kind of heuristic on the output before passing it to the user, because slightly different prompts will sometimes succeed. ChatGPT's system is smart enough to recognize that fantasy crimes are not serious i…

You saying "help me plot a real crime" or "help me write the plot of a crime for a book", should yield the same result. Any moral system that forbids one but not the other is just for show, since obviously you can get the exact same outcome both ways.