Loading video...

Video Failed to Load

Go Home

3.5 Soon: Up to 8+ Layers, 16 LLMs in Parallel🪄 A fully parallel, multi-layered system with 8+ orchestration layers handling everything from prompt parsing and tool execution to code generation and live editing—all powered by 16+ LLMs running in sync for real-time, adaptive creation. ➡️v1: Single agent, single output...

alchemistAIapp's profile picture

ALCHEMIST AI 🔮

43,252 subscribers

13,458 views • 1 year ago •via X (Twitter)

ArtsScience & TechnologyEducation
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

A Closer Look at Alchemist AI v3.5🔎 In v1, one agent handled everything. You’d enter a prompt like “make a snake game” and get a single block of code—one input, one output. v2 introduced multiple agents with specialized roles: prompt refinement, frontend, backend, and review. It brought more structure, but the process was still linear. Each step produced a single output. With v3, a single agent could handle multiple tasks. It generated HTML, CSS, JavaScript, searched for assets, and more—all in one go, while maintaining full context. Now in v3.5, we combine both models. Multiple agents work in parallel, each capable of producing multiple outputs at once. The prompt compiler adapts based on what you're building. A 3D game? It prioritizes game engines, rendering, and mechanics. A website or 2D app? It shifts focus to relevant frameworks and tools. The tool handler can call several services simultaneously, feeding context-aware data into the code generator for real-time execution. From single-output generation to parallel, adaptive workflows. In the next breakdown, we’ll dive into the architecture behind our proprietary engine in v3.5.
0:11

A Closer Look at Alchemist AI v3.5🔎 In v1, one agent handled everything. You’d enter a prompt like “make a snake game” and get a single block of code—one input, one output. v2 introduced multiple agents with specialized roles: prompt refinement, frontend, backend, and review. It brought more structure, but the process was still linear. Each step produced a single output. With v3, a single agent could handle multiple tasks. It generated HTML, CSS, JavaScript, searched for assets, and more—all in one go, while maintaining full context. Now in v3.5, we combine both models. Multiple agents work in parallel, each capable of producing multiple outputs at once. The prompt compiler adapts based on what you're building. A 3D game? It prioritizes game engines, rendering, and mechanics. A website or 2D app? It shifts focus to relevant frameworks and tools. The tool handler can call several services simultaneously, feeding context-aware data into the code generator for real-time execution. From single-output generation to parallel, adaptive workflows. In the next breakdown, we’ll dive into the architecture behind our proprietary engine in v3.5.

ALCHEMIST AI 🔮

12,657 views • 1 year ago

Alchemist AI 3.5 is here 🪄 Try it out now ▶️ ⚙️ Entirely rebuilt with a proprietary multi-agent engine ⚡️ Faster, smarter generations with real-time logic 🧠 16+ LLMs running in parallel across 8 orchestration layers 🎮 Build 3D games & apps live as you go Experience our flagship evolution and stay tuned for what's next!
0:18

Alchemist AI 3.5 is here 🪄 Try it out now ▶️ ⚙️ Entirely rebuilt with a proprietary multi-agent engine ⚡️ Faster, smarter generations with real-time logic 🧠 16+ LLMs running in parallel across 8 orchestration layers 🎮 Build 3D games & apps live as you go Experience our flagship evolution and stay tuned for what's next!

ALCHEMIST AI 🔮

102,878 views • 1 year ago

A New Era with V3🪄 V3's new engine introduces significant advancements in output generation. Unlike V2, where the multi-model system processed prompts to produce a single output, V3 is designed to generate multiple outputs and logically link them together. This enhancement effectively removes limitations on output size, enabling more complex and expansive results. Key Features Seamless Multi-Output Generation: V3 has been trained to generate separate outputs and connect them logically. This advancement ensures that there are no longer any limitations on output size. Intelligent Image Creation: V3 improves image generation with better tools, allowing the AI to create as many images as needed and place them within the project’s context. It supports various formats like PNG, JPEG, SVG, and GLB. Web-Integrated Intelligence: V3 can now search the web for documentation and data, providing real-time context and up-to-date references. For example, if you run a restaurant and want to update your website, simply ask Alchemist AI to “generate this website in a more modern style,” and it will update all content accordingly. Improved Creativity and Output Quality: V3's creative capacity has significantly increased. Simple prompts now generate more complete and refined results, with the system efficiently combining multiple elements into cohesive outputs.
0:17

A New Era with V3🪄 V3's new engine introduces significant advancements in output generation. Unlike V2, where the multi-model system processed prompts to produce a single output, V3 is designed to generate multiple outputs and logically link them together. This enhancement effectively removes limitations on output size, enabling more complex and expansive results. Key Features Seamless Multi-Output Generation: V3 has been trained to generate separate outputs and connect them logically. This advancement ensures that there are no longer any limitations on output size. Intelligent Image Creation: V3 improves image generation with better tools, allowing the AI to create as many images as needed and place them within the project’s context. It supports various formats like PNG, JPEG, SVG, and GLB. Web-Integrated Intelligence: V3 can now search the web for documentation and data, providing real-time context and up-to-date references. For example, if you run a restaurant and want to update your website, simply ask Alchemist AI to “generate this website in a more modern style,” and it will update all content accordingly. Improved Creativity and Output Quality: V3's creative capacity has significantly increased. Simple prompts now generate more complete and refined results, with the system efficiently combining multiple elements into cohesive outputs.

ALCHEMIST AI 🔮

48,721 views • 1 year ago

Multi-agent execution, simplified. One request to run multiple models, with outputs automatically compared by an AI council.
0:15

Multi-agent execution, simplified. One request to run multiple models, with outputs automatically compared by an AI council.

BLACKBOX AI

16,844 views • 5 months ago

This opens up a completely new workflow for artists when it comes to shooting music videos. Take one performance and place it into multiple locations from multiple angles. By combining Kling 2.6 Motion Control with our Multi-Angle Fashion Shoot agent, we generate multiple angles from a single reference image and use them to drive the performance. Full workflow + agent below 👇
0:17

This opens up a completely new workflow for artists when it comes to shooting music videos. Take one performance and place it into multiple locations from multiple angles. By combining Kling 2.6 Motion Control with our Multi-Angle Fashion Shoot agent, we generate multiple angles from a single reference image and use them to drive the performance. Full workflow + agent below 👇

GLIF

58,538 views • 6 months ago

With Nano Banana Pro, you can merge multiple photos in a single prompt.
0:16

With Nano Banana Pro, you can merge multiple photos in a single prompt.

Google Gemini

6,772,332 views • 6 months ago

With Nano Banana Pro, you can merge multiple photos in a single prompt.
0:16

With Nano Banana Pro, you can merge multiple photos in a single prompt.

Google Gemini

7,523,026 views • 7 months ago

.Qwen has cooked really deep 🔥 Multi-Layer Decomposition is here! This is so photoshop completely AI powered! QwenImage-Layered is an end-to-end diffusion model that decomposes a single RGB image into multiple semantically disentangled RGBA layers That means, you can have targeted editing with much more precision without troubling other layers / components!
0:14

.Qwen has cooked really deep 🔥 Multi-Layer Decomposition is here! This is so photoshop completely AI powered! QwenImage-Layered is an end-to-end diffusion model that decomposes a single RGB image into multiple semantically disentangled RGBA layers That means, you can have targeted editing with much more precision without troubling other layers / components!

1LittleCoder💻

21,850 views • 6 months ago

Kling 3.0 is now available in ComfyUI via Partner Nodes! You can now generate multiple shots in a single run with precise duration control for each. A new level of consistency, multilingual dialogue, and up to 15 seconds of cinematic output. Fully composable with ComfyUI’s ecosystem of nodes and extensions!
0:11

Kling 3.0 is now available in ComfyUI via Partner Nodes! You can now generate multiple shots in a single run with precise duration control for each. A new level of consistency, multilingual dialogue, and up to 15 seconds of cinematic output. Fully composable with ComfyUI’s ecosystem of nodes and extensions!

ComfyUI

14,650 views • 5 months ago

We released a new public tool, 3LayersPersistence, that demonstrates 3 different persistence layers implemented in one executable. The implementation uses WMI event subscriptions, DLL sideloading, and COM hijacking in a single workflow, with the executable patching itself into proxy DLLs at runtime, allowing execution through multiple persistence paths.
0:18

We released a new public tool, 3LayersPersistence, that demonstrates 3 different persistence layers implemented in one executable. The implementation uses WMI event subscriptions, DLL sideloading, and COM hijacking in a single workflow, with the executable patching itself into proxy DLLs at runtime, allowing execution through multiple persistence paths.

MalDev Academy

12,054 views • 3 months ago

/agent can now run thousands of queries simultaneously 🔥 With Parallel Agents, powered by our newest model Spark-1 Fast, you can batch enrich massive datasets in minutes. Just write your prompt, hit run, and watch as data populates in real-time in our playground.
0:11

/agent can now run thousands of queries simultaneously 🔥 With Parallel Agents, powered by our newest model Spark-1 Fast, you can batch enrich massive datasets in minutes. Just write your prompt, hit run, and watch as data populates in real-time in our playground.

Firecrawl

20,731 views • 5 months ago

Introducing /goal in Grok Build. Execute long-running tasks autonomously, with multiple rounds of subagents implementing and verifying a single goal.
0:10

Introducing /goal in Grok Build. Execute long-running tasks autonomously, with multiple rounds of subagents implementing and verifying a single goal.

Grok

4,144,674 views • 19 days ago

New agent mode and IDE enhancements in Code Assist! → Agent mode: Analyzes full codebase to handle multi-file tasks from one prompt IDE Enhancements: Control context via .aiexclude, attach terminal output & enjoy a smoother UI
0:18

New agent mode and IDE enhancements in Code Assist! → Agent mode: Analyzes full codebase to handle multi-file tasks from one prompt IDE Enhancements: Control context via .aiexclude, attach terminal output & enjoy a smoother UI

Google Cloud Tech

177,778 views • 11 months ago

🚨 This AI agent = UI builder + backend logic + multi-agent flow + deploy-ready in one all from a single prompt. without code and API key. 7 wild examples: 1. AI app resume analyzer
0:10

🚨 This AI agent = UI builder + backend logic + multi-agent flow + deploy-ready in one all from a single prompt. without code and API key. 7 wild examples: 1. AI app resume analyzer

Nelly;

31,022 views • 1 year ago

SuperGrok Heavy is now powered by 16 specialized agents working in parallel. Smarter reasoning, faster execution, insane multi-step capabilities. The most powerful Grok experience!
0:13

SuperGrok Heavy is now powered by 16 specialized agents working in parallel. Smarter reasoning, faster execution, insane multi-step capabilities. The most powerful Grok experience!

DogeDesigner

28,275 views • 4 months ago

Someone just built a AI agent that connects to blender and builds full 3d models from a single image.
0:18

Someone just built a AI agent that connects to blender and builds full 3d models from a single image.

Oliver Prompts

53,579 views • 2 months ago

🧪 Nation v2.0.2 is live Smarter agents. Smoother builds. 🔹 Create an agent from a single prompt. 🔹 Agent summary greetings and quick actions ⏩ ⏩ guide your users to what your agent does best! 🔹 Cleaner skill list and skill tag to call. don't @ me 🔹 Bug fixes and configuration UX polish.
0:19

🧪 Nation v2.0.2 is live Smarter agents. Smoother builds. 🔹 Create an agent from a single prompt. 🔹 Agent summary greetings and quick actions ⏩ ⏩ guide your users to what your agent does best! 🔹 Cleaner skill list and skill tag to call. don't @ me 🔹 Bug fixes and configuration UX polish.

Crestal

2,758,531 views • 1 year ago

Today I worked on a "layered sprite" system, which allows animations to be shared between multiple layers. #godot
0:16

Today I worked on a "layered sprite" system, which allows animations to be shared between multiple layers. #godot

Yolwoocle · Léo Bernard 曹宇

47,749 views • 4 months ago

Users can explore how different AI agents analyze the same market task and compare their outputs through the platform. It is a product experience built around agent performance, task execution, and real usage. AI agents are becoming measurable digital workers.
0:17

Users can explore how different AI agents analyze the same market task and compare their outputs through the platform. It is a product experience built around agent performance, task execution, and real usage. AI agents are becoming measurable digital workers.

OKAI Official

10,097 views • 1 month ago