LLM apps with RAG and AI agents using GPT-4o, Claude Sonnet 3.5, Llama-3, Gemini and opensource models.
Plus, latest AI news from Google, Microsoft, OpenAI, Meta and other AI startups. And tips build and deploy AI apps in production.
All for FREE:
AI code assistant in VS code using GPT-4o with Stack Overflow Search.
This feature lets you search through millions of code questions on Stack Overflow using GPT-4o to find the most accurate answers.
Google Gemini 1.5 Pro Exp generates Python code for a fully working ChatGPT Clone by just looking at a video.
The LLM app uses Llama 3.1 running locally via LM Studio.
Takes ~15 seconds
CodeGPT AI extension in VS Code can quickly fix and refactor your Python Code using Llama-3 running locally on your computer (100% free and without internet):
Claude 3.5 Sonnet creates fully working ChatGPT clone from just a screenshot in 2 minutes.
It uses Llama-3 running locally on your computer (100% free and without internet).
Build a RAG pipeline to chat with Google Drive data using Mistral or Llama-3 running locally on your computer without wiring a single line of Python Code (100% free and without internet):
OpenInterpreter uses Mistral AI's Codestral running locally on your computer (100% free and without internet).
It uses LLM & vision capabilities to autonomously control the computer.
Show a sticky note and a prompt, and the AI agent automatically connects PC to the Wifi.
GitHub AI Models Playground with Llama 3.1 405B, GPT-4o, Mistral Large, Phi-3 and other opensource models for RAG (100% free and in GitHub).
Plus, deploy these LLMs in production using Azure AI Inference SDK.
AI software engineer using Claude Sonnet 3.5
Meet Claude Engineer, a CLI tool that combines the power of Sonnet 3.5 with practical file system operations, web search, vision support and intelligent code analysis.
Open Interpreter with Mistral AI's Codestral running locally on your computer (100% free and without internet):
AI agent training and inferencing an AI model on autopilot.
Run local Llama 3.1 405B distributed across two Macbooks on your home AI cluster.
Connect multiple laptops and mobile phones together to run any LLM of your choice locally.
Chat with LLMs to build GenAI apps using AWS Studio without writing a single line of Python Code.
Go from a simple English prompt to fully working AI application in just 2 minutes.
Claude Sonnet 3.5 creates an Audio visualizer from a simple text prompt in just 30 seconds.
Claude Artifacts increases it's applications by 10x compared to GPT-4o, Gemini, Llama-3 or other existing LLMs.
Claude Sonnet 3.5 builds an interactive world history explorer with cause-effect visualizations and "what if" scenarios, all from a simple text prompt in just 30 seconds.
Education will never be the same again with AI.
Build an LLM app with Mixture of AI Agents using small Opensource LLMs that can beat GPT-4o in just 40 lines of Python Code (step-by-step instructions):
Claude Sonnet 3.5 artifacts is now available to use with GPT-4o, Gemini and Llama-3.
ChatLLM playground provides access to GPT-4o, Claude, Llama-3, and Gemini in just $10 a month.
Plus, build custom AI agents with RAG to chat with your internal data with zero Python Code.
Gemini 1.5 Pro summarizes a 1-hour+ long video in just 30 seconds 🤯
~ 1.37 million tokens
Google has made Gemini 1.5 Pro with 2 Million tokens context length generally available.
Drag & Drop to build and deploy your team of AI agents.
Integrate RAG agents for dynamic knowledge and custom AI tools to automate tasks, conduct research, and enable real-time collaboration among your AI agents.
Google Gemini now has Advanced Voice Mode similar or better than OpenAI ChatGPT
Works just like any other human. You can interrupt to ask questions or pause a chat and come back to it later.
BREAKING: The future of object detection is here.
Meta AI just released the opensource SAM 2 model that can segment any promptable objects from images or videos in real-time.
Claude 3.5 Sonnet creates fully working ChatGPT clone from just a screenshot in 2 minutes.
It uses Llama-3 running locally on your computer (100% free and without internet).
Introduction to Deep Learning 2024 by MIT is here and it's more dynamic than ever.
AI Courses taught by MIT faculty and industry veterans from Google and Comet.
Claude Sonnet 3.5 transforms simple event details into an interactive event planning dashboard in just 30 seconds.
It hugely surpasses the AI event assistants you can create with GPT-4o, Gemini, Llama and other existing LLMs.
Source Code:
It currently supports running Python code with support for JavaScript, R, Nextjs coming soon.
If you find this useful, RT to share it with your friends.
Don't forget to follow
@_unwind_ai
for more such AI updates.
Microsoft just released 18 FREE courses on Generative AI for beginners.
The courses include prompt engineering, building LLM apps in Python, RAG, AI agents, and vector databases.
Each course features video tutorials and step-by-step Python code walkthroughs.
Claude 3.5 Sonnet as multimodal AI assistant for your computer.
It can navigate UIs, type text, and even send messages, all via voice commands.
This is like Siri but 100x smarter.
Build a Multi LLM Routing app with Llama 3.1 and GPT-4o that automatically routes the input to the most efficient LLM in just 30 lines of Python Code (step-by-step instructions)
Claude Sonnet 3.5 transforms a simple PDF earnings report into an interactive dashboard in just 30 seconds.
It goes beyond the capabilities of GPT-4o, Gemini Pro, Llama and other existing LLMs.
Build a local ChatGPT clone using Llama-3 (100% free and without internet):
• Deploy Llama-3 locally using the LM Studio
• Exposes Llama-3 model as OpenAI API in LM Studio
• Provides chat interface using Streamlit
Claude 3.5 Sonnet creates fully working ChatGPT clone from just a screenshot in 2 minutes.
It uses Llama-3 running locally on your computer (100% free and without internet).
Microsoft is offering 15 FREE Generative AI courses for beginners.
Bookmark for later 📌
1. Generative AI & LLMs: Dive deep into the fascinating world of Large Language Models.
2. Exploring LLMs: Discover and choose the best model
for your needs.
3. Using Generative AI
1. Ollama
An open-source project that provides an easy way to download and run LLMs like Llama-3 on regular PCs.
It integrates with the OpenWebUI project, which gives you a web-based user interface to interact with the local LLMs.
GitHub rolls out new AI tool: code scanning autofix
GitHub's new code-scanning autofix feature is now in public beta for all GitHub Advanced Security customers.
- Powered by Copilot and CodeQL
- Scans code automatically
- Suggests remedy code
- Gives explanation for suggestions
3. GPT4All
An open-source project that provides tools and software to run powerful LLMs on your computer, without needing access to expensive GPU hardware or cloud services.
2. LM Studio
It is a tool that allows you to run Llama-3 and other opensource LLMs offline on your local PC.
You can download the LM Studio application, install it, and then use it to download and run any opensource LLM completely offline.
Run local Llama 3.1 405B distributed across two Macbooks on your home AI cluster.
Connect multiple laptops and mobile phones together to run any LLM of your choice locally.
Build a RAG pipeline to chat with Google Drive data using Mistral or Llama-3 running locally on your computer without wiring a single line of Python Code (100% free and without internet):
Opensource of AI apps using
@mem0ai
:
If you find this useful, RT to share it with your friends.
Don't forget to follow
@_unwind_ai
for more such AI updates.
1. Ollama + OpenWebUI
Ollama is an opensource project that provides an easy way to download and run local LLMs like Llama 3.1 on your computer.
Ollama integrates with the OpenWebUI project, which gives you a web-based ChatGPT-like user interface to interact with the local
First opensource language model computer
Open Interpreter releases 01, a portable AI device that can operate our computer on voice commands. It can see our screen, use our apps, and learn new skills.
- opensource
- Powered by Llama 2, Whisper and Piper
Claude 3.5 Sonnet just created a fully functional snake and ladders game in 2 minutes.
Plus, I can see the code and play the game in real-time with the new artifacts feature.
Coding experience with Claude is 10x than GPT-4o and Gemini.
Running on Macbook M1 pro (16GB RAM) using the
@LMStudioAI
.
If you find this useful, RT to share it with your friends.
Don't forget to follow
@_unwind_ai
for more such AI updates.
Great OpenSource project by
@turungkadircan
:
If you find this useful, RT to share it with your friends.
Don't forget to follow
@_unwind_ai
for more such AI updates.
Latest in AI:
- Sam Altman says GPT-4 is the dumbest model any of you ever have to use
- OpenAI might be launching ChatGPT + search engine
- Nvidia's ChatRTX gets new AI models and can understand images and voice commands
plus top AI tools!
Build an LLM app with Mixture of AI Agents using small Opensource LLMs that can beat GPT-4o in just 40 lines of Python Code (step-by-step instructions):
GPTs could be your ticket to unlock millions of dollars 🤯
OpenAI released GPTs a few days ago, and they are already breaking the internet. Ride this new AI wave now, or be left behind.
Here are 15 amazing GPTs blowing people's mind:
@fablesimulation
, the company behind last year’s viral South Park AI episode generator, has launched its own platform, Showrunner, that lets you create your own TV shows with AI.