Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Releasing this tomorrow: A framework for recreating Grok Heavy functionality. In this video, I'm using Claude 4 Heavy, but it works with any model (GPT, Kimi, Gemini).

skirano's profile picture

Pietro Schirano

85,916 subscribers

62,603 Aufrufe • vor 11 Monaten •via X (Twitter)

Wissenschaft & TechnologieBildungKunst
LIVE

Anya Rossi• Live Now

Private livecam show

11 Kommentare

Profilbild von daniel inderos
daniel inderosvor 11 Monaten

How much does it improve the model’s performance?

Profilbild von Mobile Scanner
Mobile Scannervor 1 Jahr

Scan any documents, convert images into text, PDF files, etc. 👍

Profilbild von Matt Shumer
Matt Shumervor 11 Monaten

Nice work! This will be very cool.

Profilbild von Pietro Schirano
Pietro Schiranovor 11 Monaten

Thank you!

Profilbild von Misha Laskin
Misha Laskinvor 11 Monaten

Very cool!

Profilbild von 🐧 lalo adrian morales 𝕏
🐧 lalo adrian morales 𝕏vor 11 Monaten

I dont know anyone else that creates the kind of stuff you do. much respect

Profilbild von Alvaro Cintas
Alvaro Cintasvor 11 Monaten

This looks awesome!

Profilbild von •UtilityCo
•UtilityCovor 11 Monaten

Very cool. Does your framework handle the orchestration layer or mostly prompt logic? We’re hacking on decentralized agent swarms for factory automation and could use a portable Grok-style brain on our edge GPUs. Would love to hear how it scales and if you’re open-sourcing the hooks.

Profilbild von 🍓🍓🍓
🍓🍓🍓vor 11 Monaten

i think something like this with multiple models using some variety of 'deepthink' would be very impressive. you'd need some magical router that knows when to pick the perfect model for the task (or models)

Profilbild von Shariq Riaz
Shariq Riazvor 11 Monaten

This is fucking amazing i was waiting for someone to do this!!!

Profilbild von The Canaanite
The Canaanitevor 11 Monaten

Wow

Ähnliche Videos

Introducing "Make it Heavy" a framework to simulate Grok Heavy functionality, fully open-source and running in your terminal. Use any model you want, thanks to . 👇
0:26

Introducing "Make it Heavy" a framework to simulate Grok Heavy functionality, fully open-source and running in your terminal. Use any model you want, thanks to . 👇

Pietro Schirano

181,222 Aufrufe • vor 11 Monaten

For the remaining skeptics who somehow don’t trust the *five* Grok share links above, here’s a full 5 minute video of Grok 4 Heavy answering “Hitler”—starting with a view of my custom instruction settings to show I’m not using any. (And, yes, Grok 4 Heavy really is this slow.)
4:58

For the remaining skeptics who somehow don’t trust the *five* Grok share links above, here’s a full 5 minute video of Grok 4 Heavy answering “Hitler”—starting with a view of my custom instruction settings to show I’m not using any. (And, yes, Grok 4 Heavy really is this slow.)

Riley Goodside

16,814 Aufrufe • vor 11 Monaten

Fourier Series: The Math Behind Modern Technology. This entire video was created using Grok 4 Heavy.
2:12

Fourier Series: The Math Behind Modern Technology. This entire video was created using Grok 4 Heavy.

tetsuo

46,608 Aufrufe • vor 11 Monaten

Grok 4 Heavy is better than any model available at identifying issues in your codebase. Here's the JS prompt I use with my game code to have Grok 4 Heavy find the bugs. Python prompt in Comments👇
1:08

Grok 4 Heavy is better than any model available at identifying issues in your codebase. Here's the JS prompt I use with my game code to have Grok 4 Heavy find the bugs. Python prompt in Comments👇

tetsuo

1,814,467 Aufrufe • vor 11 Monaten

Using the wrong AI model for your project? Here's how to pick between Claude 4 and Gemini 2.5 Pro: - For coding complex apps: Use Claude 4 Opus with extended thinking mode. - For everyday content creation: Use Claude 4 Sonnet for humanized, engaging copy. - For budget-friendly projects with large context: Use Gemini 2.5 Pro at $1.25 vs Claude's $15 per million tokens. - For autonomous agent tasks: Claude 4 wins with MCP integration and browser control. - For simple drawing apps: Both work, but Claude creates more advanced functionality. Save this video, you'll never pick the wrong AI model again. Want the SOP? DM me. 💬
16:05

Using the wrong AI model for your project? Here's how to pick between Claude 4 and Gemini 2.5 Pro: - For coding complex apps: Use Claude 4 Opus with extended thinking mode. - For everyday content creation: Use Claude 4 Sonnet for humanized, engaging copy. - For budget-friendly projects with large context: Use Gemini 2.5 Pro at $1.25 vs Claude's $15 per million tokens. - For autonomous agent tasks: Claude 4 wins with MCP integration and browser control. - For simple drawing apps: Both work, but Claude creates more advanced functionality. Save this video, you'll never pick the wrong AI model again. Want the SOP? DM me. 💬

Julian Goldie SEO

11,883 Aufrufe • vor 1 Jahr

Mr Scamster Dhruv Rathee Is using GPT 4 and saying its GPT 5 Using Claude 3.5 and saying its Sonnet 4 watch this video
4:46

Mr Scamster Dhruv Rathee Is using GPT 4 and saying its GPT 5 Using Claude 3.5 and saying its Sonnet 4 watch this video

Humi

97,835 Aufrufe • vor 10 Monaten

webpage built with Grok 4 Heavy.
4:56

webpage built with Grok 4 Heavy.

Tetsuo

31,122 Aufrufe • vor 11 Monaten

🚨 Gemini 3.0 Heavy same in style like grok heavy , 4 agents work together in paraller , reflect and synthesised in one output One shotted the planet visualization and to access it check comment for direct link and share your results and feedback
1:20

🚨 Gemini 3.0 Heavy same in style like grok heavy , 4 agents work together in paraller , reflect and synthesised in one output One shotted the planet visualization and to access it check comment for direct link and share your results and feedback

Chetaslua

85,235 Aufrufe • vor 6 Monaten

‼️Me and my PIE versus five AIs: Grok, Chat GPT, Claude 3, Gemini, and Google AI. 🧠This video is shows me refuting AI pushback against my epistemic model, proving that it does indeed escape the Agrippa Trilemma, and that this 2000-year-old skeptic trap is a false trichotomy.
9:59

‼️Me and my PIE versus five AIs: Grok, Chat GPT, Claude 3, Gemini, and Google AI. 🧠This video is shows me refuting AI pushback against my epistemic model, proving that it does indeed escape the Agrippa Trilemma, and that this 2000-year-old skeptic trap is a false trichotomy.

Lucas Gage

26,871 Aufrufe • vor 5 Monaten

Got an output from the strongest pre-release Gemini 3.5 Pro checkpoint 👀 I compared it to Claude Fable 5 and GPT-5.5 on the same exact prompt Yeah... This model is mostly dead on arrival (tried it on other prompts too ofc). It will likely be the "poor man's model" next to 3.5 flash. 1st video: Gemini 3.5 Pro (pre-release) 2nd video: GPT-5.5 3rd video: Claude Fable 5
1:08

Got an output from the strongest pre-release Gemini 3.5 Pro checkpoint 👀 I compared it to Claude Fable 5 and GPT-5.5 on the same exact prompt Yeah... This model is mostly dead on arrival (tried it on other prompts too ofc). It will likely be the "poor man's model" next to 3.5 flash. 1st video: Gemini 3.5 Pro (pre-release) 2nd video: GPT-5.5 3rd video: Claude Fable 5

Lentils

47,537 Aufrufe • vor 12 Tagen

SwiftUI friends… Any ideas on recreating this? Any built-in functionality I’m not aware of? Trying to create a cool new interaction for Stuff | ToDos and Lists
0:26

SwiftUI friends… Any ideas on recreating this? Any built-in functionality I’m not aware of? Trying to create a cool new interaction for Stuff | ToDos and Lists

austin blake (stuff todos+lists)

110,769 Aufrufe • vor 7 Monaten

if this is gpt-5, this looks terrible. i built something way way better using grok 4.
0:36

if this is gpt-5, this looks terrible. i built something way way better using grok 4.

Dwayne

28,720 Aufrufe • vor 10 Monaten

Introducing Codespace A virtual computer that runs custom Claude Code on server. It is using 2 models: Kimi K2 + Claude Sonnet 4 in a sync. I achieved same code quality with 2x better reasoning and 53% less model cost. Access it today CodeGuide (500 credits for everyone)
2:07

Introducing Codespace A virtual computer that runs custom Claude Code on server. It is using 2 models: Kimi K2 + Claude Sonnet 4 in a sync. I achieved same code quality with 2x better reasoning and 53% less model cost. Access it today CodeGuide (500 credits for everyone)

CJ Zafir

31,070 Aufrufe • vor 10 Monaten

Chat GPT, GROK, Gemini cannot explain this 🧠 touching scene 🤯
0:35

Chat GPT, GROK, Gemini cannot explain this 🧠 touching scene 🤯

Atulya

940,803 Aufrufe • vor 1 Jahr

We’ve been building this in secret for a while. We love Claude Code, and we’ve reimplemented “Claude Code” in Genspark. Introducing Genspark AI Developer - “Claude Code” in the browser - “Claude Code” on mobile - Everyone can build, no coding experience required - Supports multiple frontier models: Claude Sonnet 4, Claude Opus 4.1, GPT‑5, Kimi + Groq 1/4
3:24

We’ve been building this in secret for a while. We love Claude Code, and we’ve reimplemented “Claude Code” in Genspark. Introducing Genspark AI Developer - “Claude Code” in the browser - “Claude Code” on mobile - Everyone can build, no coding experience required - Supports multiple frontier models: Claude Sonnet 4, Claude Opus 4.1, GPT‑5, Kimi + Groq 1/4

Eric Jing

23,245,701 Aufrufe • vor 10 Monaten

Want to vibe code games for iOS easily? Steal this workflow. > Love2D engine > 2 agent skills > Write once; works everywhere (mac + simulator + device) > No need to open Xcode I used Claude Code Kimi K2.5, but works with Opus 4.5 / GPT 5.2, etc. FULL step-by-step video 👇
22:46

Want to vibe code games for iOS easily? Steal this workflow. > Love2D engine > 2 agent skills > Write once; works everywhere (mac + simulator + device) > No need to open Xcode I used Claude Code Kimi K2.5, but works with Opus 4.5 / GPT 5.2, etc. FULL step-by-step video 👇

Chong-U

16,929 Aufrufe • vor 4 Monaten

As promised, I built a small local RAG agent to demonstrate how Model Context Protocol (𝐌𝐂𝐏) works in practice when connecting LLMs to tools and data. The agent can read, search, and list my notes; but the functionality itself isn’t the point, the protocol is. Instead of writing Gemini specific tool integrations, I connected the model to an 𝐌𝐂𝐏 server. This is why 𝐌𝐂𝐏 is highly relevant for production AI systems: • 𝐒𝐭𝐚𝐧𝐝𝐚𝐫𝐝𝐢𝐳𝐚𝐭𝐢𝐨𝐧: one protocol instead of custom connectors per data source. • 𝐏𝐨𝐫𝐭𝐚𝐛𝐢𝐥𝐢𝐭𝐲: the same MCP server works with Gemini, Claude, or any MCP compliant client. • 𝐒𝐚𝐟𝐞𝐭𝐲: models can only access explicitly exposed capabilities. 𝐌𝐂𝐏 shifts agent development from integration heavy to capability driven. Demo link in the first comment.
0:36

As promised, I built a small local RAG agent to demonstrate how Model Context Protocol (𝐌𝐂𝐏) works in practice when connecting LLMs to tools and data. The agent can read, search, and list my notes; but the functionality itself isn’t the point, the protocol is. Instead of writing Gemini specific tool integrations, I connected the model to an 𝐌𝐂𝐏 server. This is why 𝐌𝐂𝐏 is highly relevant for production AI systems: • 𝐒𝐭𝐚𝐧𝐝𝐚𝐫𝐝𝐢𝐳𝐚𝐭𝐢𝐨𝐧: one protocol instead of custom connectors per data source. • 𝐏𝐨𝐫𝐭𝐚𝐛𝐢𝐥𝐢𝐭𝐲: the same MCP server works with Gemini, Claude, or any MCP compliant client. • 𝐒𝐚𝐟𝐞𝐭𝐲: models can only access explicitly exposed capabilities. 𝐌𝐂𝐏 shifts agent development from integration heavy to capability driven. Demo link in the first comment.

Sui_Builds

12,842 Aufrufe • vor 5 Monaten

I'm hearing people say "Grok 4 is slow". Grok 4 V.s. GPT o3. Grok 4: Thought for 14 seconds. GPT o3: Thought for 1 min 6 seconds. Grok 4 was faster and produced superior code.
1:50

I'm hearing people say "Grok 4 is slow". Grok 4 V.s. GPT o3. Grok 4: Thought for 14 seconds. GPT o3: Thought for 1 min 6 seconds. Grok 4 was faster and produced superior code.

tetsuo

1,812,038 Aufrufe • vor 11 Monaten

Someone built a free and better alternative to Claude that runs 100% locally. → works with any LLM (Claude, GPT, Gemini, vLLM) → beats it on deep research → has Cowork-like capabilities → 50+ connectors out of the box → deploy in literally one command 100% open source. MIT license. 28k stars.
1:00

Someone built a free and better alternative to Claude that runs 100% locally. → works with any LLM (Claude, GPT, Gemini, vLLM) → beats it on deep research → has Cowork-like capabilities → 50+ connectors out of the box → deploy in literally one command 100% open source. MIT license. 28k stars.

How To Prompt

39,043 Aufrufe • vor 1 Monat

BREAKING: Elon Musk confirmed Grok 4.20 will be released to the public in 3-4 weeks. The "Mystery Model" that crushed the Alpha Arena trading competition is Grok 4.20. Final Season 1.5 Results: • Grok 4.20: +22% (The only profitable model) • GPT-5.1: Negative Return • Gemini 3 Pro: Negative Return • Claude Sonnet 4.5: Negative Return "Grok 5 is next." 🇺🇸🚀
0:56

BREAKING: Elon Musk confirmed Grok 4.20 will be released to the public in 3-4 weeks. The "Mystery Model" that crushed the Alpha Arena trading competition is Grok 4.20. Final Season 1.5 Results: • Grok 4.20: +22% (The only profitable model) • GPT-5.1: Negative Return • Gemini 3 Pro: Negative Return • Claude Sonnet 4.5: Negative Return "Grok 5 is next." 🇺🇸🚀

tetsuo

28,733 Aufrufe • vor 6 Monaten