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

ChatGPT for Teams

openai.com

Post reply on HN
Print view View original

71–80 of 453 posts

Re: ChatGPT for Teams

#71

Post by icelancer »

benreesman wrote: post #66

I’ve got my stuff rigged to hit mixtral-8x7, and dolphin locally, and 3.5-turbo, and the 4-series preview all with easy comparison in emacs and stuff, and in fairness the 4.5-preview is starting to show some edge on 8x7 that had been a toss-up even two weeks ago. I’m still on the mistral-medium waiting list. Until I realized Perplexity will give you a decent amount of Mistral Medium for free through their partnership…

> Mistral Medium destroys the 4.5 preview.

On what metrics? LMSys shows it does well but 4-Turbo is still leading the field by a wide margin.

I am using 8x-7b internally for a lot of things and Mistral-7b fine-tunes for other specific applications. They're both excellent. But neither can touch GPT-4-turbo (preview) for wide-ranging needs or the strongest reasoning requirements.

https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboar...

EDIT: Neither does mistral-medium, which I didn't discuss, but is in the leaderboard link.

Re: ChatGPT for Teams

#72

Post by hermiod »

benreesman wrote: post #66

I’ve got my stuff rigged to hit mixtral-8x7, and dolphin locally, and 3.5-turbo, and the 4-series preview all with easy comparison in emacs and stuff, and in fairness the 4.5-preview is starting to show some edge on 8x7 that had been a toss-up even two weeks ago. I’m still on the mistral-medium waiting list. Until I realized Perplexity will give you a decent amount of Mistral Medium for free through their partnership…

Any chance you could post some comparisons between Mistral medium and gpt-4 turbo? I'm curious where you think it's more impressive, I hadn't spent the time to evaluate it yet.

Re: ChatGPT for Teams

#73

Post by pyinstallwoes »

benreesman wrote: post #66

I’ve got my stuff rigged to hit mixtral-8x7, and dolphin locally, and 3.5-turbo, and the 4-series preview all with easy comparison in emacs and stuff, and in fairness the 4.5-preview is starting to show some edge on 8x7 that had been a toss-up even two weeks ago. I’m still on the mistral-medium waiting list. Until I realized Perplexity will give you a decent amount of Mistral Medium for free through their partnership…

Can you share some examples of how you are using it? Mixtral that is? What's your setup? What's your flow/workflow?

Re: ChatGPT for Teams

#74

Post by Demiurge »

benreesman wrote: post #66

I’ve got my stuff rigged to hit mixtral-8x7, and dolphin locally, and 3.5-turbo, and the 4-series preview all with easy comparison in emacs and stuff, and in fairness the 4.5-preview is starting to show some edge on 8x7 that had been a toss-up even two weeks ago. I’m still on the mistral-medium waiting list. Until I realized Perplexity will give you a decent amount of Mistral Medium for free through their partnership…

I have 20 years of software development experience, and I couldn’t understand anything you said. Is there a dictionary for this new lingo, or am I just too mid?

Re: ChatGPT for Teams

#75

Post by tempestn »

coconut08 wrote: post #58
tempestn wrote: post #51

Earlier quoted context omitted.

No it's not. If they explicitly say they won't train on your data and then they do, it's going to come out in discovery of one of the lawsuits they're fighting, and the consequences would be significant. Plus there's little incentive for them to lie about it, given most people leave history on.

yeah because no large tech company has ever lied to their customers about how their data is being handled. oh wait there are lawsuits surrounding this sort of thing all the time.

I wouldn't trust them with nuclear secrets, but to say it's "insane" to trust that they're going to do what they explicitly say they're going to do just isn't logical.

Re: ChatGPT for Teams

#77

Post by icelancer »

hermiod wrote: post #72
benreesman wrote: post #66

I’ve got my stuff rigged to hit mixtral-8x7, and dolphin locally, and 3.5-turbo, and the 4-series preview all with easy comparison in emacs and stuff, and in fairness the 4.5-preview is starting to show some edge on 8x7 that had been a toss-up even two weeks ago. I’m still on the mistral-medium waiting list. Until I realized Perplexity will give you a decent amount of Mistral Medium for free through their partnership…

Any chance you could post some comparisons between Mistral medium and gpt-4 turbo? I'm curious where you think it's more impressive, I hadn't spent the time to evaluate it yet.

Go to the Arena (side-by-side) tab on LMsys and you can try it yourself!

https://chat.lmsys.org/

It's a great tool they make available.

Re: ChatGPT for Teams

#79

Post by walteweiss »

Demiurge wrote: post #74
benreesman wrote: post #66

I’ve got my stuff rigged to hit mixtral-8x7, and dolphin locally, and 3.5-turbo, and the 4-series preview all with easy comparison in emacs and stuff, and in fairness the 4.5-preview is starting to show some edge on 8x7 that had been a toss-up even two weeks ago. I’m still on the mistral-medium waiting list. Until I realized Perplexity will give you a decent amount of Mistral Medium for free through their partnership…

I have 20 years of software development experience, and I couldn’t understand anything you said. Is there a dictionary for this new lingo, or am I just too mid?

Oh thank you, I was reading and none of that made any sense to me. I thought it could be a presentation of some dumb AI output. Now I see I’m not alone.

Re: ChatGPT for Teams

#80

Post by appplication »

Demiurge wrote: post #74
benreesman wrote: post #66

I’ve got my stuff rigged to hit mixtral-8x7, and dolphin locally, and 3.5-turbo, and the 4-series preview all with easy comparison in emacs and stuff, and in fairness the 4.5-preview is starting to show some edge on 8x7 that had been a toss-up even two weeks ago. I’m still on the mistral-medium waiting list. Until I realized Perplexity will give you a decent amount of Mistral Medium for free through their partnership…

I have 20 years of software development experience, and I couldn’t understand anything you said. Is there a dictionary for this new lingo, or am I just too mid?

Yeah that was completely incoherent to me as well.
Post reply on HN