Coding Just Changed Forever…NVIDIA ChatRTX

Want to create your own local chatbot powered by NVIDIA RTX GPUs? Download ChatRTX here: nvda.ws/4a3lgw8
#AIonRTX @NVIDIAGeForce
Coding just changed forever because Nvidia has announced Chat with RTX AI which allows you to run and personalize a GPT large language model (LLM) connected to your own content-docs, notes, or other data - all locally powered by NVIDIA GeForce RTX GPUs.
And I got the chance to test it out so I can show you everything it can do and how it can give you an advantage as a programmer.
🧠 Algo University - Master Data Structures & Algorithms - academy.internetmadecoder.com...
🚀 Zero to Python Developer: Full Course - academy.internetmadecoder.com...
🚀 Land a $70k+- Job in 4 Months - coursecareers.com/a/internetm...
💰 60+ Coding Courses for less than $1 per day - academy.zerotomastery.io/a/af...
🚀 Developer's Brain - academy.internetmadecoder.com...
📸 FOLLOW ME ON INSTAGRAM - / tuomaskivioja
📝 TWITTER - / internetcoder

[@InternetMadeCoder]

Want to create your own local chatbot powered by NVIDIA RTX GPUs? Download ChatRTX here: nvda.ws/4a3lgw8

[@horikatanifuji5038]

Nothing revolutionary, you've been able to do the same thing with Ollama for quite some time now.

[@VolodymyrBohomolov]

Where’s the actual coding? Didn’t get it, sorry

[@carolopara6069]

Exactly! I was confused too.

[@umpy3tJ]

@@carolopara6069 exactly

[@WolfsDenShop]

I like the fact that you explained the installation process and how to use N.RTX. Even though you're sponsored by N, the security protocol of locally stored data, is a fantastic unique selling point over other web hosted AI.

[@SarFirraEdits]

Which laptop are you using?

[@MrJoeMontano]

Does it have limitations of NSFW data? like is it filtered?

[@smurfC]

4:50 The AI was clearly unable to process your request and here you are saying it will like others, and then you scroll up in the next scene acting like it never happened lol

[@fahomenhera2820]

Bro what? Changing in terms of what 😂 This is just another LLM tool.

[@lucascaruso7275]

Bro needed content is all.

[@gmaxgaming7657]

yeah@@lucascaruso7275

[@barbmorey3742]

It's entirely local to my understanding; the benefit could potentially be the ability to utilize gtp without disclosing proprietary code. Potentially lol. THAT would be huge

[@jamjam3448]

😂 😂 😂 Obviously content

[@yoshid8987]

@@barbmorey3742 LM Studio?

[@NyxesRealms]

Coding hasnt changed at all based on what's currently available here. Unless you want to spend ages copying your code into a readable format like a txt file. Writing, however... I imagine you could take a dataset of your writing samples and have it generate new things in your writing style.

[@finalbotgaming]

That is actually an insane tool...

[@Leto2ndAtreides]

Feel like they should've waited to launch it... Once it supported code files.

[@user-nh5fg4se5w]

Please kindly mention, How the gpt correcting itself if it is not taking our data?

[@user-nh5fg4se5w]

@@yarpenzigrin1893 sorry, on what basis they make the updates. There must be a feedback, right? Correct me

[@user-nh5fg4se5w]

​@@yarpenzigrin1893 sorry, To update this, there did they get the feedback from. I think the Data. Please correct me, if there any other ways.

[@pastuh]

using it for heroes3 board game :)) Too much rules, so it can find answers in seconds.. insane :X

[@yiannispapagiannopoulos9549]

Imagine if this had stable diffusion capabilities too

[@mikemorrison7774]

it can only look at one folder at a time.. which pretty much makes it useless

[@hv6411]

I would love to hear your opinion on Devin

[@francoisotis3560]

what was that????

[@LeandroDellOrso]

In general I think Coding is reshaping itself without any idea of the final shape, so let's see what will happen.

[@jasperdecraene6239]

If i have a laptop with an 3060 GPU and 6gb of VRAM, can i still use chatRTX?

[@Lawry7807]

I Guess not. Min. 8 GB of VRAM.

[@yssnb]

I have an RTX3050 with 4gb on the vram, do I have any chance of running this??

[@Olloxan]

yes, you can run it but I have an RTX3070 with 8GB VRam and when i ask it anything about my files i wait about 5min. for an answer. So you might wait 10 minnutes on your machine :D

[@Leonardo_D1]

Did you manage to run it? I saw it requres 8GB VRAM.

[@balamdavinci]

Hello

[@Ynerson9003]

Are us coders done for?

[@randomstranger8326]

nah we still keep going

[@hasnain4186]

Sorry bro but ,Yes. But I guess you will still do Great in life

[@neilallen460]

Harvesting your data.

[@matYT123]

AI's kinda scary

[@khanyisodev]

Video is a big waste of time, has nothing to do with coders

[@JARFAST]

what languages ​​does nvidia support? chat with rtx. arabic