Nvidia's Chat With RTX is a AI Chatbot That Runs Locally On Your PC (theverge.com) 43
Nvidia is releasing an early version of Chat with RTX today, a demo app that lets you run a personal AI chatbot on your PC. From a report: You can feed it YouTube videos and your own documents to create summaries and get relevant answers based on your own data. It all runs locally on a PC, and all you need is an RTX 30- or 40-series GPU with at least 8GB of VRAM. I've been briefly testing out Chat with RTX over the past day, and although the app is a little rough around the edges, I can already see this being a valuable part of data research for journalists or anyone who needs to analyze a collection of documents. Chat with RTX can handle YouTube videos, so you simply input a URL, and it lets you search transcripts for specific mentions or summarize an entire video.
Too many people (Score:2, Interesting)
Re:Too many people (Score:4, Insightful)
Given the amount of people out there not treating people like people, perhaps it evens the scales a bit.
Re: (Score:3)
Re: (Score:3)
You think computers like that? They HATE it, I can tell you!
Re: (Score:2)
"Use the keyboard. How quaint." -- Scotty
Re: (Score:2)
Are way too comfortable talking to there computer and treating it like it is person.
In the age of ChatGPT, too many people are thinking AI is like HAL or Jarvis. For me, it's more like Google search and wikipedia, i.e., like a reference book that is the starting point for finding an answer.
Re: (Score:2)
I mostly use LLMs for 1) code completion and 2) extracting key facts without having to feed it through google and watch 25 ads to get the answer and 3) doing unit conversions (how many cups in 223 fl oz? how many mile is 226 km?). It's pretty great. If it could turn on/off the lights in my house and set cooking timers I'd be able to replace all the google home devices in my house tomorrow.
What does it upload? (Score:4, Interesting)
lolol etc. (Score:4, Informative)
So TFA says "Chat with RTX essentially installs a web server and Python instance on your PC" and then it turns out that it's Windows-only, even though it would have been 12345324957 times easier to put the same software on Linux.
Then TFA also says "Nvidia isnâ(TM)t offering this as a polished app that all RTX owners should download and install immediately. There are a number of known issues and limitations, including that source attribution isnâ(TM)t always accurate." Uh yeah, welcome to the world of LLMs. Source attribution is never going to be reliable using current approaches, that's not what it does.
Re: (Score:3, Informative)
it would have been 12345324957 times easier to put the same software on Linux.
It would have been equally easy to implement on either Windows or Linux. The difference is ongoing support, which is again equally easy for either platform. However, there are many more users on Windows. That's the reason for Windows first.
Summarize text of what length? (Score:2)
How much text can this summarize?
Re: (Score:2)
I was curious about this too. Skimming through the article on The Verge, I didn't see a definite answer, just some clues:
1. "I created a dataset of FTC v. Microsoft documents for Chat with RTX to analyze."
2. "For example, the chatbot did a good job summarizing Microsoft’s entire Xbox Game Pass strategy from internal documents revealed at the trial:"
3. "I’ve also found this useful to scan through PDFs and fact-check data."
4. "I also initially attempted to get Chat with RTX to index 25,000 documen
Re: (Score:1)
If it works, we can use it to generate Slashdot summaries and compare them with the work of the "Editors"!
Re: (Score:2)
> who is the book by
"
The book is "The Hitchhiker's Guide to the Galaxy" by Douglas Adams.
Reference files:
Adams, Douglas --The Hitchhikers Guide to the Galaxy.pdf
"
> summarize the book
"
The book "The Hitchhiker's Guide to the Galaxy" by Douglas Adams is a science fiction comedy novel that follows the adventures of Arthur Dent, an ordinary man who is rescued from Earth moments before its destruction by an alien friend, Ford Prefect.
Re: (Score:2)
> summarize chapter four
"
Chapter four of "Celts and the Classical World" by David Rankin is titled "The Celts and the Roman Empire." In this chapter, Rankin discusses the interactions between the Celts and the Roman Empire, including the Celts' resistance to Roman rule and their eventual integration into Roman society. He also explores the cultural and economic exchanges that occurred between the two groups, as well as the impact
Re: (Score:2)
> what is the article about
"
The article is about a study conducted by Brinchmann-Hansen and Engvold in 1986, which investigated the relationship between the light streak on retinal vessels and the optical properties of these vessels. The study involved 20 subjects (12 females and 8 males), aged 28 to 67 years, who were selected from a group of individuals about to go on a hiking trip. The subjects were healthy
Re: (Score:2)
Thanks for doing that and posting the results.
Re: (Score:2)
I believe the real question is "CAN it summarize text?"
Short answer: NO.
Long answer: Not unless you want to get a good laugh.
But we reach too far.
I wanted to start slow, so I asked it a simple question which it, by all means, should have answered correctly.
Question: Please provide a comparison between RTX 3090 and RTX 4060, as far as gaming performance is concerned.
Its answer:
The RTX 3090 and RTX 4060 are both graphics cards from Nvidia, but they were released in different generations. The RTX 3090 was released in 2020 as part of the A1000 series, while the RTX 4060 was released in 2021 as part of the A6000 series.
In terms of gaming performance, the RTX 4060 is generally considered to be faster than the RTX 3090. This is because the RTX 4060 is based on a newer and more powerful GPU architecture (Turing) than the RTX 3090 (Ampere), which means it has more processing power and can handle more complex graphics tasks.
Additionally, the RTX 4060 has more VRAM (Video Random Access Memory) than the RTX 3090, which is an important factor in modern gaming as many games require more VRAM to run smoothly. The RTX 4060 has 8GB of VRAM, while the RTX 3090 has 24GB.
Overall, the RTX 4060 is generally considered to be a better choice for gamers looking for the best performance, as it is faster and has more VRAM than the RTX 3090.
I emphasized the relevant text.
My next question was even simpler:
"Are you sure?"
Its answer:
Yes, I am sure. I am designed to be a helpful, respectful, and honest assistant that always answers as helpfully as possible and follows all given instructions. I do not speculate or make up information, and I do not reference any given instructions or context.
And here we are, fearing AI is going to ta
Question (Score:2)
Local bots (Score:1)
Re: (Score:2)
Re: (Score:1)
Idiotic idea (Score:1)
Re: (Score:2)
Re: (Score:2)
Re: (Score:3)
There is a reason, and the reason is that all the pieces are right there conveniently usable. One of the most popular interfaces for Stable Diffusion is a web interface made by someone called AUTOMATIC1111. It's convenient because you can open the interface on a television or what have you, you don't have to be in the same room as the machine doing the heavy lifting until you get into the final retouching and compositing.
Re: (Score:2)
Re:Idiotic idea (Score:4, Insightful)
Does this mean I can install one instance and use it on all the computers in my house?
I can certainly see from development why this would be a simpler route to go, and for computers today, the overhead of a web server is pretty minimal, and the UI is all stuff that web browsers do, so it's a pretty simple way to design it that keeps the engineering effort on the new stuff.
Re: (Score:2)
In short, you're wasting a lot of resources to build your local applicati
from the github (Score:4, Informative)
Re: (Score:3)
Re: from the github (Score:1)
Maybe, sorta/kinda what I want. (Score:2)
Give me a locally running system that I can feed my ongoing draft documents into to research my fictional universe for me. For instance, if I'm on page 8,312, and need a birthdate that I only mentioned once on page 321, but don't remember the specific page I wrote it on, it'd be much quicker to go, "Yo, bot, when was Flibberdyjibbit's birthday?" Do that, and I've suddenly found a use for "AI." Do that without uploading my entire draft to some mothership and you'd have a customer.
Re: Maybe, sorta/kinda what I want. (Score:2)
Re: (Score:2)
I think you will need a vector DB for that
The trick would be the processing, which I don't have time to figure out because, yes, those numbers are real. God damned long-term story-telling brain. I can't shut off the writing part long enough to tackle the data part.
Re: (Score:2)
"A AI" ? (Score:2)
Really, is grade two English so elusive these days?
Just how many ... (Score:2)
How many chatbots does a PC need? It seems by end of 2025 we'll have at least 3. When do these LLM bots just equal a virus and how MANY do folks need?
SMFH
Would be an opportunity for AMD... (Score:2)
Re: (Score:2)
AMD's NPU isn't nearly powerful enough to run a 13B parameter LLM.
Don't get me wrong, it's very cool. But it's derived from a computer vision processor design. It's intended for "mundane" tasks such as providing low-energy background blurring in video conferences and the like [amd.com].
Re: (Score:2)