StTexan Suggestions??? 7067 Posts user info edit post |
^now that you say something, gnsp really is kind of a wolfweb thing right? 5/30/2024 10:26:03 PM |
justinh524 Sprots Talk Mod 27802 Posts user info edit post |
Does mine say i hate Ryan Finley and Maverick Rowan 6/1/2024 1:25:23 AM |
TreeTwista10 minisoldr 148390 Posts user info edit post |
Quote : | "His role as a "Sprots Talk Mod" indicates he has responsibilities for moderating discussions and maintaining the forum's activity and decorum" |
6/1/2024 7:00:16 PM |
justinh524 Sprots Talk Mod 27802 Posts user info edit post |
Yep that's me 6/2/2024 3:13:38 PM |
qntmfred retired 40659 Posts user info edit post |
https://www.reuters.com/technology/artificial-intelligence/openai-co-founder-sutskevers-new-safety-focused-ai-startup-ssi-raises-1-billion-2024-09-04/ 9/4/2024 11:07:29 AM |
qntmfred retired 40659 Posts user info edit post |
Quote : | "this will be an interesting metric along which to track its evolution" |
https://twitter.com/maximlott/status/18350433713392026399/15/2024 11:54:27 AM |
The Coz Tempus Fugitive 26003 Posts user info edit post |
Can we let the smartest AI elect our leaders? 9/15/2024 1:19:33 PM |
moron All American 34125 Posts user info edit post |
^^ not a fan of the methodology for that, but the trend is pretty clear
hopefully people start thinking what that means... a few cents in electricity and you can have a domain expert answer in an in depth question for you in a few minutes 9/17/2024 1:38:26 AM |
emnsk All American 2781 Posts user info edit post |
FEUDAL RETURN
FEUDAL RETURN
[Edited on September 17, 2024 at 7:52 PM. Reason : FEUDAL RETURN] 9/17/2024 7:52:24 PM |
CaelNCSU All American 7027 Posts user info edit post |
The real time conversation API is more expensive than a 900 number per minute, but you get rate limited before you finish. NAMSAYIN! 10/12/2024 10:42:20 AM |
The Coz Tempus Fugitive 26003 Posts user info edit post |
I'll be honest. I do not. 10/12/2024 11:32:31 AM |
CaelNCSU All American 7027 Posts user info edit post |
"Okay, so imagine those old 900 numbers from the '90s where people paid to chat on the phone by the minute. Now, a real-time conversation API is kind of like that—you pay for each minute you're using it. The thing is, it's actually more expensive than those old 900 numbers. And to make it worse, with the API, you might even get cut off (rate-limited) before you're done talking. You know what I’m sayin’?" 10/12/2024 11:37:03 AM |
darkone (\/) (;,,,;) (\/) 11610 Posts user info edit post |
LLMs don't reason. https://arxiv.org/pdf/2410.05229 10/13/2024 12:55:37 AM |
The Coz Tempus Fugitive 26003 Posts user info edit post |
^^Yes! Now I do! 10/13/2024 10:38:49 AM |
CaelNCSU All American 7027 Posts user info edit post |
Spent some time fine tuning with OpenAI and Llama 3 models. Used Esgargs posting history before I got two afraid of my account getting locked. He does not adhere to the terms of service in 2024. It's intermittently like 4chan. He was before his time.
I used Llama 3 with LoRA, but even with an A100 GPU with 80GB of RAM, I had to stick to the smaller 8B parameter models. It's pretty slow even with that setup. Got mixed results. Some hilarious like cussing someone for mentioning Apple (on point).
Other cool shit I've done work related: used Googles API Improvement Spec and checked API designs to see if they conform and code review on pull request. 11/3/2024 4:04:51 PM |
qntmfred retired 40659 Posts user info edit post |
what did you use? i've done a little of qntmbot training on my tww+twitter history but nothing i am ready to host publicly yet. i'm sure before the next election we'll be rock'n and roll'n though 11/3/2024 9:03:39 PM |
StTexan Suggestions??? 7067 Posts user info edit post |
Ultimately, what are the benefits for the end user on the things you two are discussing? Like after combining twitter+tww, what would be some benefits qntmfred? 11/3/2024 10:17:59 PM |
CaelNCSU All American 7027 Posts user info edit post |
Used the huggingface Python libraries. Using the base data loader and LoRA didn't work, had to load it manually and create tensors.
Used this: https://huggingface.co/docs/peft/en/index. The openAI fine-tuning library is easy to use and reasonable. I spent about $3 fine tuning there and a little more with A100 renting.
I did a talk about a plugin I made and part of the talk writes newspaper article about the talk as a demo (in the style of the local rag). For work I've experimented getting information baked in that isn't there. Largely, I just wanted to know how it all worked.
Took ML at Stanford for credit and did the AI Certification too.
[Edited on November 3, 2024 at 10:36 PM. Reason : A] 11/3/2024 10:34:40 PM |
qntmfred retired 40659 Posts user info edit post |
^^ my name will be etched into the cave.
[Edited on November 3, 2024 at 11:27 PM. Reason : your great-grandchildren are watching] 11/3/2024 11:27:08 PM |
kiljadn All American 44690 Posts user info edit post |
Just put in my notice at work and am gonna spend the rest of the year building some AI shit / some shit with AI.
Already built a couple of things but nothing too magical - langchain slackbot, etc 11/9/2024 10:06:52 AM |
FroshKiller All American 51909 Posts user info edit post |
Gross 11/9/2024 11:31:38 AM |
CaelNCSU All American 7027 Posts user info edit post |
^^ may the vectors always point you in the right direction.
Not sure if you are in Raleigh still but there are some AI places hiring.
[Edited on November 9, 2024 at 3:30 PM. Reason : A] 11/9/2024 3:29:54 PM |