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

Elevated Errors on API and ChatGPT

status.openai.com

Post reply on HN
Print view View original

121–130 of 182 posts

Re: Elevated Errors on API and ChatGPT

#121

Post by mk_stjames »

mk_stjames wrote: post #107

If the last week of OpenAI's ordeal was a setup in a hollywood flick it would be at this point where there is a hard cut to the third-billed, yet-to-be-seen-onscreen actor popping out a metal backdoor of a server room while stuffing a solid state drive into an inner jacket pocket while donning a motorcycle helmet and gloves, with a music score change indicating that the entire first two-act slow burn of this corporat…

(Sorry - The drive is to hold stolen model weights. Keen audience members would have figured that out by this point in the film. Cue music.)

Re: Elevated Errors on API and ChatGPT

#124

Post by rushingcreek »

bkyan wrote: post #120
rushingcreek wrote: post #87

Earlier quoted context omitted.

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 Is the tutorial simply out-of-date?

Ah good catch, we do need to update the tutorial. Thanks!

Re: Elevated Errors on API and ChatGPT

#128

Post by insanitybit »

GaggiX wrote: post #102
runjake wrote: post #90

If you’re on a Mac, Ollama with the Code Llama model and a bit of prompting is pretty decent if you’re doing Python or Javascript. Runs locally on Apple Silicon. 5-10 minute setup. It’s all free. https://ollama.ai Edit: a couple of comments below are recommending Mistral 7B over Code Llama/Llama2, so give that a try with Ollama too: ollama run mistral https://ollama.ai/library/mistral

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)

Mistral is a big step up from llama2 in my experience, really impressive to see a 7B model that can do so much. I haven't noticed a considerable improvement from the 13b version, and by using 7b I can keep my context size very large.

Re: Elevated Errors on API and ChatGPT

#129

Post by hereme888 »

davidguetta wrote: post #106
hereme888 wrote: post #54

Earlier quoted context omitted.

Not when my workflow has been modified to rely on present tech and time is of the essence. Going back to "the old ways" breaks my workflow and makes me not trust them. They can experiment all they want with beta testers or internal networks.

I mean business survival 101 is not depend on a single failure point

Yes, this is my personal workflow though. Academic/school.

My backup is much more manual/slow, and I can't always keep pace with live lectures w/o my GPT setup for note-taking, etc.

Re: Elevated Errors on API and ChatGPT

#130

Post by jonchurch_ »

MaximilianEmel wrote: post #114

Why is ChatGPT so commonly misspelled as ChatGTP?

I'd assume because it's faster to move the index finger immediately up a row to the T when typing quickly than it is to move the ring finger up and over to the P. So chorded together, you end up hitting the T before the P to make GTP. Maybe it's a novel enough key chord that we can't rely on muscle memory to execute it well.

At least on my US qwerty keyboard, I notice this class of typo myself often enough.

We all have our quirks when it comes to common typos based on keystrokes. Not gonna speculate on spelling mistakes. Glass houses, stones, and all that.

Post reply on HN