Elevated Errors on API and ChatGPT • Hacker News Board

Re: Elevated Errors on API and ChatGPT

#111

Post by suby » Tue, Nov 21, 2023, 11:55 PM UTC

lopatin wrote: post #78

It's usually up. No way this unrelated.

They just launched chatgpt with voice for free users. Could very well be related to that.

Re: Elevated Errors on API and ChatGPT

#112

Post by mmasu » Tue, Nov 21, 2023, 11:55 PM UTC

Very interestingly, my company has GPT through Azure OpenAI and it worked like a charm.

Re: Elevated Errors on API and ChatGPT

#113

Post by diamondfist25 » Tue, Nov 21, 2023, 11:56 PM UTC

rushingcreek wrote: post #87

mcbishop wrote: post #81

Its outage shows me how much I now rely on ChatGPT during novel programming. I've been smashing that refresh button like a lab rat with a pellet lever.

https://phind.com is up and running if you're looking for a replacement. Disclosure: I'm a co-founder.

Love phind.com. U guys are great

Re: Elevated Errors on API and ChatGPT

#114

Post by MaximilianEmel » Tue, Nov 21, 2023, 11:56 PM UTC

Why is ChatGPT so commonly misspelled as ChatGTP?

Re: Elevated Errors on API and ChatGPT

#115

Post by ChatGTP » Tue, Nov 21, 2023, 11:58 PM UTC

MaximilianEmel wrote: post #114

Why is ChatGPT so commonly misspelled as ChatGTP?

No idea

Re: Elevated Errors on API and ChatGPT

#116

Post by kruxigt » Wed, Nov 22, 2023, 12:00 AM UTC

rushingcreek wrote: post #87

mcbishop wrote: post #81

Its outage shows me how much I now rely on ChatGPT during novel programming. I've been smashing that refresh button like a lab rat with a pellet lever.

https://phind.com is up and running if you're looking for a replacement. Disclosure: I'm a co-founder.

[dead]

Re: Elevated Errors on API and ChatGPT

#117

Post by GaggiX » Wed, Nov 22, 2023, 12:01 AM UTC

borg16 wrote: post #110

GaggiX wrote: post #102

Earlier quoted context omitted.

I like using the OpenChat model based on Mistral, I think it is by far the best 7B model: https://openchat.team/ (you can also use it online here)

thanks for this recommendation. have you been using this one for a while? How do you like it?

It's pretty new but it performs very well when I use it, it is also the third best non-proprietary model on the chatbot arena: https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboar... (the ELO is calculated from blinded comparisons so it really shows the actual performance of the model).

Re: Elevated Errors on API and ChatGPT

#118

Post by FartyMcFarter » Wed, Nov 22, 2023, 12:02 AM UTC

MaximilianEmel wrote: post #114

Why is ChatGPT so commonly misspelled as ChatGTP?

I guess if you're gonna mispell a three letter acronym one is more likely to fail on the last two letters than on the first letter.

Re: Elevated Errors on API and ChatGPT

#119

Post by tracerbulletx » Wed, Nov 22, 2023, 12:02 AM UTC

mmasu wrote: post #112

Very interestingly, my company has GPT through Azure OpenAI and it worked like a charm.

I think it was pretty well known prior to this it's a different environment.

Re: Elevated Errors on API and ChatGPT

#120

Post by bkyan » Wed, Nov 22, 2023, 12:04 AM UTC

rushingcreek wrote: post #87

mcbishop wrote: post #81

Its outage shows me how much I now rely on ChatGPT during novel programming. I've been smashing that refresh button like a lab rat with a pellet lever.

https://phind.com is up and running if you're looking for a replacement. Disclosure: I'm a co-founder.

Quick Question -- The tutorial says:

"The Phind Model is not currently supported in Pair Programmer mode."

... but I'm able to select "Pair Programming" and choose the Phind model at the same time in the user interface. Is the tutorial simply out-of-date?