Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
Alvaro Cintas Profile picture
Alvaro Cintas
@dr_cintas
Educating about AI, Cybersecurity and Technology | Professor | PhD in Computer Science & Engineering | 👨‍🏫@therundownai
16 subscribers
Apr 9 • 5 tweets • 2 min read
🚨 BREAKING: Google just announced Agent2Agent.

This protocol enables AI agents to communicate across platforms regardless of framework or vendor.

Here’s how it works: A2A facilitates communication between "client" and "remote" agents through four key capabilities:

Secure Collaboration, Task Management, User Experience Negotiation, and Capability Discovery

All built popular standards like HTTP, JSON-RPC standards with enterprise auth. Image
Apr 4 • 10 tweets • 3 min read
What a wild week in AI 🤯

- Midjourney v7
- Runway Gen-4
- Apple AI Health Coach
- Lindy AI Agent Swamps
- Amazon Browser Agent
- LLMs passing the Turing Test
- Meta MoCha AI talking characters
- AI brain signal to speech breakthrough

Here’s everything you need to know: Midjourney just released v7, the latest upgrade to the AI art generator loved by creatives.

Its new “Draft Mode” slashes costs by 50% and speeds up generation 10x, perfect for quick sketches.
Mar 27 • 14 tweets • 5 min read
What a wild week in AI 🤯

- Reve Image
- Ideogram 3.0
- Qwen new models
- ARC-AGI-2 launch
- Alibaba LHM model
- Microsoft Researcher
- Google Gemini 2.5 Pro
- Perplexity Answer Tabs
- DeepSeek’s V3 AI model
- OpenAI’s Image Generator

Here’s everything you need to know: 1. Reve has launched Reve Image 1.0.

Fresh out of stealth, it has claimed the top spot in global image model rankings and outperforming big names like Midjourney and Google’s Imagen.

It provides stunning photorealism, best-in-class prompt accuracy, and wild text rendering.
Mar 26 • 11 tweets • 3 min read
OpenAI’s native Al image generation is insane.

The image and text quality are so good that it has unlocked unlimited possibilities.

10 crazy use cases:

1. Thumbnail maker Image 2. Create product marketing images Image
Mar 24 • 6 tweets • 3 min read
AI photoshoots are taking over e-comm and fashion.

You can now upload a product design, choose a model, and generate a fashion photoshoot for your idea like this.

Here's how: Image
Image 1. Go to and sign up for a free account htch.ai/HHbmhOE
Mar 20 • 11 tweets • 4 min read
What a wild week in AI 🤯

- Mistral Small 3.1
- Claude Web Search
- OpenAI Audio Models
- Krea AI Video Training
- NotebookLM Mind Maps
- Hunyuan 3D Generation AI
- Stability AI New Virtual Camera
- Gemini Canvas & Audio Overview

Here’s everything you need to know: 1. Mistral AI has released Mistral Small 3.1

A 24B open-source model that outperforms Google’s Gemma 3 and OpenAI’s GPT-4o Mini in key benchmarks.

It supports multimodal inputs, handles up to 128k tokens in context, and processes 150 tokens per second for high efficiency.
Mar 17 • 12 tweets • 4 min read
Google's Gemini native Al image generation is insane.

You can now generate or edit photos with just plain text and completely free.

10 crazy use cases:

1. Thumbnail optimizer Image 2. Professional look Image
Mar 15 • 6 tweets • 3 min read
You can now add Deep Research to your AI code editors.

Simply add the new Firecrawl MCP with Deep Research, and it will autonomously explore the web, and extract the latest findings for your code projects.

Here’s how: First, you are going to need an API key from Firecrawl. You can get one to try free here: firecrawl.dev
Mar 13 • 11 tweets • 4 min read
What a wild week in AI 🤯

- Google’s Gemma 3
- Luma AI Ray2 Flash
- Reka Flash 3 Reasoning
- Hunyuan-TurboS model
- OpenAI’s Building Agents
- Gemini Native Image Editing
- Hedra Character 3 Omnimodal
- Freepik & Veo 2 Image to Video

Here’s everything you need to know: 1. Google has released Gemma 3, a family of open-source AI models built from Gemini 2.0 technology.

It comes in sizes from 1B to 27B parameters, offering a 128K-token context window and multimodal support.
Mar 9 • 8 tweets • 3 min read
You can connect Claude to the Internet using MCPs.

I’ve been using an MCP server that connects to the Brave Search API for web searches with Claude 3.7 Sonnet.

Here’s how: First, head over to:

And download the latest desktop version. claude.ai/downloadImage
Mar 6 • 12 tweets • 4 min read
What a wild week in AI 🤯

- Mistral OCR
- Google’s AI Mode
- Windsurf Previews
- Anthropic Console
- ChatGPT Edit in IDEs
- Microsoft Dragon Copilot
- HunyuanVideo I2V Model
- Sesame Realistic AI Voices
- Alibaba releases QwQ-32B

Here’s everything you need to know: 1. Mistral AI has launched Mistral OCR, a new API designed for document understanding.

This tool extracts text from images and PDFs with high accuracy, making it ideal for use with RAG systems.

It’s priced at 1000 pages per dollar and is already available.
Mar 3 • 5 tweets • 2 min read
You can now clone any website just by writing a prompt.

Simply add the new Firecrawl MCP server to your favorite AI coding tool for improved web data extraction, and let Claude code it for you.

Here’s how: First, you are going to need an API key from Firecrawl. You can get one to try free here: firecrawl.dev
Mar 1 • 5 tweets • 2 min read
Real-time AI voice agents for businesses are here.

I created this AI assistant in minutes with no code and used my cloned voice to help handle customers at a fictitious store.

Plus, there’s now a marketplace with ready-made templates where you can sell yours. First, head over to:

Create an AI voice agent by adding its name, a voice, and instructions of how it should behave via the “Prompt” section. synthflow.ai
Feb 27 • 11 tweets • 4 min read
What a wild week in AI 🤯

• OpenAI GPT 4.5
• Claude 3.7 Sonnet
• Alibaba Wan 2.1 AI video
• Grok 3 & Perplexity Voice
• Google Gemini Code Assist
• Amazon AI assistant Alexa+
• ElevenLabs Speech-to-Text
• Hume AI new LLM built for TTS

Here’s everything you need to know: 1. OpenAI has launched GPT-4.5, its largest AI model yet.

It focuses on unsupervised learning, improving intuition and reducing hallucinations.

Early testers say interactions feel more natural. Currently available to Pro users.
Feb 23 • 6 tweets • 3 min read
Grok 3 is an incredible AI coding assistant.

After a couple of hours and +1000 lines of code generated, I have now a fully functional 2D vertical jumping game.

With different heroes, monsters, platforms, difficulties, and lives.

Here are the prompts and process I followed: 🧑‍💻CODING PART

I will provide the prompt below, let me give you a few tips:

- Don’t try to ask for every single detail and feature. Try to first ask for a very simple game.
- For complex tasks, use the Grok Think button, it’s quite good.
- Ask for shapes as your characters, platforms, etc. Do not worry about the assets at first.
- You will probably get some errors. Just ask @Grok to solve them for you if you don’t know.

Once you have a first version working, you can start adding the images and other features.

In my case, I added the settings, lives, score, animations, different platforms, main menu and enemies later.Image
Feb 15 • 7 tweets • 3 min read
OpenAI has released a new prompting guide for their reasoning models.

It emphasizes simplicity, avoiding chain-of-thought prompts, the use of delimiters, and when to use them.

Here’s a breakdown and an optimized prompt to have it write like you: Image
Image ChatGPT models excel in different ways:

🔹 o-series (“the planners”)

• Think deeply for complex tasks
• Great at strategy, planning & decision-making
• Ideal for expert-level fields: math, science, finance, law

🔹 GPT (“the workhorses”)

• Optimized for speed & efficiency
• Excels at straightforward execution • Best when cost & speed outweigh perfect accuracy
Feb 13 • 11 tweets • 4 min read
Windsurf just announced Wave 3.

It takes AI coding to a whole new level with so many incredible features.

8 wild examples: Image 1. Tab to Jump

The autocomplete model is getting a huge upgrade.

Windsurf can now anticipate your next cursor position and navigate through your file by just pressing tab.
Feb 6 • 10 tweets • 4 min read
What a crazy week in AI 🤯

- Mistral Le Chat app
- Anthropic Jailbreaks
- Pika adds Pikaddition
- Google Gemini 2.0 Pro
- Replit free text-to-app
- ByteDance’s AI avatars
- OpenAI’s Deep Research
- HuggingFace AI App Store

Here’s everything you need to know: 1. Mistral has updated its famous “Le Chat” AI platform. It can Search the Web, create images, and analyze uploaded documents.

They also just released its new phone app for Android and iOS
Feb 5 • 7 tweets • 3 min read
I just created my own web AI agent.

I can give it a topic or a news URL and it will take over my computer to look it up, summarize it, and draft a post about it in my own writing style.

All on its own 🤯

Here’s how you can do it too: For this, I used Stagehand, which is the AI interface to the internet.

It is the easiest way to build browser automations. You can find more info here: and here are their tags @Stagehanddev @browserbasehq
 
But let’s get you started 👇 stagehand.devImage
Feb 4 • 8 tweets • 2 min read
OpenAI’s Deep Research is a major shift.

It’s like having a PhD-level assistant that can perform deep web analysis and generate reports in minutes.

But it’s limited to Pro Users…

Here are 6 free open source alternatives 🧵: 1. Open Deep Research
Feb 1 • 13 tweets • 4 min read
ChatGPT released a new beast model.

o3-mini is a fast reasoning model that can search the web, and is particularly good at science, math, and coding.

10 wild examples: Image 1. New AidanBench records

AidanBench rewards Creativity, Reliability, Contextual attention, and Instruction following of LLMs.