正在加载视频...

视频加载失败

返回首页

Keep your AI conversations private by running DeepSeek & Llama via SecretLLM. Here is a preview of a mobile app Tom 👓 has built.

nillion's profile picture

Nillion

200,245 subscribers

40,317 次观看 • 1 年前 •via X (Twitter)

科学技术喜剧健康养生
LIVE

Anya Rossi• Live Now

Private livecam show

11 条评论

io.net 的头像
io.net1 年前

@crypblizz It's good to see that even with the current rate of development, privacy is not forgotten

Unplugged 的头像
Unplugged2 年前

🤖 Big Tech's watching? Not on our watch. 😎 See how UP Phone keeps your data off their radar. 🚫📱 #PrivacyWin #TakeControl 👉

zayn 的头像
zayn1 年前

@crypblizz Tom all night thinking about how to make this possible, and then did. fucking goat

VIOLENT 🦅 的头像
VIOLENT 🦅1 年前

@crypblizz Nillion is building something extremely huge

Zokaa 🌸 的头像
Zokaa 🌸1 年前

@crypblizz EASY

5ɨѵε⚡ 的头像
5ɨѵε⚡1 年前

@crypblizz Noiceeee. Make Privacy Great Again

Dan 🧪 的头像
Dan 🧪1 年前

@crypblizz The future is bright 💪💪

Banza | Private Data Consumption Layer 的头像
Banza | Private Data Consumption Layer1 年前

@crypblizz Privacy is the way 🖖

Koneb 的头像
Koneb1 年前

@crypblizz Why keep your AI chats private when you can share your data with PublicAI and earn rewards? Just think of it as a 'data party'! 🎉 #SharingIsCaring

DEUCES 的头像
DEUCES1 年前

@crypblizz Devs are devving

Alireza "| Mango" 的头像
Alireza "| Mango"1 年前

@crypblizz DEEPSEEKWhy keep it secret when you can share it with PublicAI? Let’s make AI training a team sport—who knew data could be so social? 😂 #DataParty

相关视频

nilGPT is now on mobile. With the new release, you can install the app to your device. A private chatbot, right on your home screen. Learn more 👇
1:26

nilGPT is now on mobile. With the new release, you can install the app to your device. A private chatbot, right on your home screen. Learn more 👇

Nillion

32,129 次观看 • 11 个月前

Introducing the Venice App 🌅 Venice is the only AI app that keeps your conversations completely private Get honest answers to any question, generate stunning images, and create without restrictions on your mobile device
0:54

Introducing the Venice App 🌅 Venice is the only AI app that keeps your conversations completely private Get honest answers to any question, generate stunning images, and create without restrictions on your mobile device

Venice

306,538 次观看 • 1 年前

Atomic Bot released an iOS app for Hermes Agent, bringing mobile control to a self-hosted agent running 24/7 on your own VPS. > Remote access via Tailscale, Cloudflare, or ngrok > Open source and private by default
0:31

Atomic Bot released an iOS app for Hermes Agent, bringing mobile control to a self-hosted agent running 24/7 on your own VPS. > Remote access via Tailscale, Cloudflare, or ngrok > Open source and private by default

🚨 AI News | TestingCatalog

48,098 次观看 • 2 个月前

The future of personalized AI agents is private.
17:13

The future of personalized AI agents is private.

Nillion

36,491 次观看 • 1 年前

Find out how DeepSeek, a Chinese AI chatbot has sent Silicon Valley in a tizzy. Reportedly made at a fraction of the cost of its rivals, DeepSeek launched last week has already become the most downloaded free app in the US. #DeepSeek #AI #NVIDIAcrash #ChineseAI #SiliconValley #Trump #IndiaTodayMagazine
1:08

Find out how DeepSeek, a Chinese AI chatbot has sent Silicon Valley in a tizzy. Reportedly made at a fraction of the cost of its rivals, DeepSeek launched last week has already become the most downloaded free app in the US. #DeepSeek #AI #NVIDIAcrash #ChineseAI #SiliconValley #Trump #IndiaTodayMagazine

IndiaToday

31,671 次观看 • 1 年前

Your trading risk appetite might be genetic. Degens and non-degens take risk very differently. Monadic DNA is running a community study using Nillion to process private genetic data to find out answers to all of these questions and more!
1:34

Your trading risk appetite might be genetic. Degens and non-degens take risk very differently. Monadic DNA is running a community study using Nillion to process private genetic data to find out answers to all of these questions and more!

Nillion

25,195 次观看 • 8 个月前

Genspark introduced a free AI browser that works with local models! You can choose from 169 open-weight models to keep your conversations private. It also comes with built-in Super Agents 👀
0:30

Genspark introduced a free AI browser that works with local models! You can choose from 169 open-weight models to keep your conversations private. It also comes with built-in Super Agents 👀

TestingCatalog News 🗞

43,182 次观看 • 11 个月前

Introducing Perplexi-Tube, the Perplexity for YouTube that I built in 20 minutes... A Mobile app that uses Deepseek and Gemini I used Cursor and the React Native template built that makes building mobile apps incredibly easy. Tomorrow I'm releasing a full tutorial on how to create a mobile app with react native. You will need - XCode and Simulator (free) - Cursor - A Clerk Account (for auth, free) - A Deepseek API Key - A Gemini API Key (Optional, we used it because deepseek has been down today) Video will be released tomorrow, and I will open source this code as well.
0:29

Introducing Perplexi-Tube, the Perplexity for YouTube that I built in 20 minutes... A Mobile app that uses Deepseek and Gemini I used Cursor and the React Native template built that makes building mobile apps incredibly easy. Tomorrow I'm releasing a full tutorial on how to create a mobile app with react native. You will need - XCode and Simulator (free) - Cursor - A Clerk Account (for auth, free) - A Deepseek API Key - A Gemini API Key (Optional, we used it because deepseek has been down today) Video will be released tomorrow, and I will open source this code as well.

Riley Brown

117,889 次观看 • 1 年前

Fuck it, 685B parameter, DeepSeek V3 0324 running locally on M3 Ultra, fully private 🔥 Powered by llama.cpp & dynamic quants from Unsloth AI ⚡ Step 1: brew install llama.cpp Step 2: llama-cli -hf unsloth/DeepSeek-V3-0324-GGUF:Q2_K_XL That's it! 🤗 Honestly a bit surreal to be able to chat with such a chunky model at the touch of the keyboard - future is going to be wild!!
5:00

Fuck it, 685B parameter, DeepSeek V3 0324 running locally on M3 Ultra, fully private 🔥 Powered by llama.cpp & dynamic quants from Unsloth AI ⚡ Step 1: brew install llama.cpp Step 2: llama-cli -hf unsloth/DeepSeek-V3-0324-GGUF:Q2_K_XL That's it! 🤗 Honestly a bit surreal to be able to chat with such a chunky model at the touch of the keyboard - future is going to be wild!!

Vaibhav (VB) Srivastav

168,141 次观看 • 1 年前

This is all the code you need to create a Streamlit app to chat with Llama 3.1 8B locally via ollama. Fast and private.
0:20

This is all the code you need to create a Streamlit app to chat with Llama 3.1 8B locally via ollama. Fast and private.

Pietro Schirano

310,018 次观看 • 2 年前

We just reached the text to mobile apps moment. CatDoes v3 lets you go from a single idea to a real iOS, Android and web app by chatting with AI agents. Here is a WhatsApp style app going from blank project to running on an iPhone in one session.
0:59

We just reached the text to mobile apps moment. CatDoes v3 lets you go from a single idea to a real iOS, Android and web app by chatting with AI agents. Here is a WhatsApp style app going from blank project to running on an iPhone in one session.

Chubby♨️

24,878 次观看 • 8 个月前

For those R fans waiting patiently for a version of for R, here is a little sneak preview of the progress we've made recently. This is a screen capture showing an editable R Shiny app, running without a Shiny server, via Shinylive and webR😀 #RStats #wasm
0:24

For those R fans waiting patiently for a version of for R, here is a little sneak preview of the progress we've made recently. This is a screen capture showing an editable R Shiny app, running without a Shiny server, via Shinylive and webR😀 #RStats #wasm

George Stagg

67,240 次观看 • 3 年前

🔥 LATEST: DeepSeek, a new Chinese AI chatbot, has just dethroned ChatGPT as the #1 app. Is this the end of ChatGPT's reign? Find out now!
2:22

🔥 LATEST: DeepSeek, a new Chinese AI chatbot, has just dethroned ChatGPT as the #1 app. Is this the end of ChatGPT's reign? Find out now!

Cointelegraph

41,632 次观看 • 1 年前

Dozens of teams have asked my advice on running LLMs. How fast is DeepSeek V3 with vLLM on 8 GPUs? What's the max throughput of Qwen 2.5 Coder with SGLang on one H100? Running & sharing benchmarks ad hoc was too slow So we built a tiny app, the LLM Engine Advisor
0:38

Dozens of teams have asked my advice on running LLMs. How fast is DeepSeek V3 with vLLM on 8 GPUs? What's the max throughput of Qwen 2.5 Coder with SGLang on one H100? Running & sharing benchmarks ad hoc was too slow So we built a tiny app, the LLM Engine Advisor

Charles 🎉 Frye

86,412 次观看 • 1 年前

DeepSeek R1 671B is ridiculously good, but running at 158 tokens per second is something out of this world. A model *this good* running *this fast* is 3 years ahead of this time. The secret: DeepSeek in this short video isn't running on GPUs. It's running on custom-made chips! This is running on SambaNova and their SN40L chips, which are designed and optimized for running AI workflows. SambaNova is sponsoring my work. We designed GPUs to run games and later realized we could use them for AI. This is very different from creating a chip specifically for AI from the ground up. Just think about this for a second: One single SNL40 chip can simultaneously hold 100+ models (trillions of parameters) in memory! An agentic workflow that uses multiple models simultaneously won't need to swap models from memory even once! By the way, the Llama family of models *screams* on the SambaNova Cloud. Here are some numbers from my latest tests: • Llama 3.3 70B: 367.32 t/s • Llama 3.2 1B: 2381.82 t/s • Llama 3.2 3B: 1335.71 t/s • Llama 3.1 8B: 929.58 t/s • Llama 3.1 70B: 369.16 t/s • Llama 3.1 405B: 103.37 t/s You can access all of these models for free!
1:34

DeepSeek R1 671B is ridiculously good, but running at 158 tokens per second is something out of this world. A model *this good* running *this fast* is 3 years ahead of this time. The secret: DeepSeek in this short video isn't running on GPUs. It's running on custom-made chips! This is running on SambaNova and their SN40L chips, which are designed and optimized for running AI workflows. SambaNova is sponsoring my work. We designed GPUs to run games and later realized we could use them for AI. This is very different from creating a chip specifically for AI from the ground up. Just think about this for a second: One single SNL40 chip can simultaneously hold 100+ models (trillions of parameters) in memory! An agentic workflow that uses multiple models simultaneously won't need to swap models from memory even once! By the way, the Llama family of models *screams* on the SambaNova Cloud. Here are some numbers from my latest tests: • Llama 3.3 70B: 367.32 t/s • Llama 3.2 1B: 2381.82 t/s • Llama 3.2 3B: 1335.71 t/s • Llama 3.1 8B: 929.58 t/s • Llama 3.1 70B: 369.16 t/s • Llama 3.1 405B: 103.37 t/s You can access all of these models for free!

Santiago

131,019 次观看 • 1 年前

Deutsche Telekom CEO and T-Mobile chairman Tim Höttges introducing the first AI phone without apps. Instead of you choosing from pre-built apps, a custom app is built for you in real-time every step of the way. Welcome to Mobile 2.0
1:59

Deutsche Telekom CEO and T-Mobile chairman Tim Höttges introducing the first AI phone without apps. Instead of you choosing from pre-built apps, a custom app is built for you in real-time every step of the way. Welcome to Mobile 2.0

Jerry Yue

608,666 次观看 • 2 年前

I didn’t learn mobile dev, I still shipped an app. Prompt I used: "Build me a task management app with due dates, priorities, and notifications." Replit ⠕ built it automatically → live phone preview via QR → full-stack handled: frontend, backend, database, auth, AI, connectors → App Store in 3 clicks. The hardest parts just disappeared.
0:27

I didn’t learn mobile dev, I still shipped an app. Prompt I used: "Build me a task management app with due dates, priorities, and notifications." Replit ⠕ built it automatically → live phone preview via QR → full-stack handled: frontend, backend, database, auth, AI, connectors → App Store in 3 clicks. The hardest parts just disappeared.

SARAH

295,271 次观看 • 6 个月前