ExocortX

NoCode / automation / AI / productivity 🇱🇺🇫🇷🇬🇧🇨🇴

[Min Choi @minchoi]

MCP is going crazy viral right now🤯

AI apps can now instantly connect to any tool or live data.

USB-C moment for AI.

10 wild examples:

[OpenAI Developers @OpenAIDevs]

🔎📄 We’ve put together a guide on how to do RAG on PDFs using file search in the new Responses API: https://t.co/M7l6xdtyba

[Robin Payot @RobinPayot]

I’m a big fan of Zelda: The Wind Waker game and a fan of #webgl / #threejs too, and these last months I’ve been trying to combine them👇

https://t.co/eWBFuTAU7o 🎧

Hope you’ll like it! Send me your best screenshots with #WindWakerJS 😀 #JavaScript

Feedback is welcome!

[Alvaro Cintas @dr_cintas]

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:

[Balaji @balajis]

Among decentralized models:

Llama is best generalist
Qwen is best multimodal/multilingual
Mistral has lightest footprint

But the space moves so fast that may change tomorrow.

[Balaji @balajis]

Grok is the best integrated
ChatGPT is the fastest
Claude is the smartest
Perplexity is best for web search
Gemini handles the largest files

[Alvaro Cintas @dr_cintas]

Yesterday revealed what’s coming in 2025, with more possibly on the way:

> OpenAI’s o3 (confirmed)
> xAI Grok 3 (confirmed)
> Claude 3.5 Opus
> Google Gemini 2.0 Pro
> Meta Llama 4 (confirmed)

Buckle up. The AI race is heating up.

[Philipp Schmid @_philschmid]

The only fine-tuning guide you need for 2025 ‼️ Excited to share “How to fine-tune open LLMs in 2025 with @huggingface” covering everything from Q-LoRA to Spectrum methods with focus on optimization, efficiency and distributed training. 👀

Fine-tuning still matters for specialized use cases despite better models - especially for consistency, domain expertise, controlling output style, or reducing costs. In this guide, you will learn how:
🎯 Define good use cases for fine-tuning vs. prompting
🛠️ Set up your development environment using Hugging Face libraries
📚 Create and prepare datasets in conversation format
⚡ Use Q-LoRA for efficient 4-bit training or Spectrum method to selectively fine-tune important layers
💨 Speed up training with Flash Attention and Liger Kernels
💻 Scale across multiple GPUs with DeepSpeed and accelerate
📊 Test and evaluate models with evaluation harness
🔥 Run for production using TGI/vLLM

[ExocortX @ExocortX]

Comment analyser gratuitement vos documents et vidéos grâce à l'IA ? Découvrez Google NotebookLM !
https://t.co/42AYnVjlZG

[ExocortX @ExocortX]

Si vous cherchez à déployer des apps opensource facilement (N8N, https://t.co/Jjb2HVCt61, etc), ne cherchez plus: utilisez https://t.co/Me0LndlFtd ! ça coûte 3 euros par mois... un nobrainer

[ExocortX @ExocortX]

@elonmusk You should create a productivity course. It's beyond my human understanding how much you can accomplish in a week.

[ExocortX @ExocortX]

@FrancescoD_Ales Which one is it?

[ExocortX @ExocortX]

@elest_io well deserved ! I really like your reviews of Open Source apps! keep going !

[ExocortX @ExocortX]

@nb4ld j'y étais y a qq jours, ça affichait 0 kW de prod en plein jour...

[ExocortX @ExocortX]

@Korben Avec o1 mini tu as pas des meilleurs résultats ? Ou alors avec structure outputs?

[ExocortX @ExocortX]

Nouvelle vidéo et article : L'IA ne vous servira à rien... sauf si vous faites exactement ÇA!!!
https://t.co/GtrjWCE3rW

[ExocortX @ExocortX]

Je suis personnellement (Très excellent) Marabout en automatisation/IA.
Je peux vous générer une voix puis une image de l'être aimé(e) (avec Midjourney ou DALL-E), si besoin.

[SaxX ¯\_(ツ)_/¯ @_SaxX_]

Même les marabouts se mettent désormais à la cyber ���🤷🏽‍♂️😂 #jpp

[ExocortX @ExocortX]

@TomFrankly For me there is no way I vote for Trump or Harris !

(there is literally no way since I am French in the UK ^^)

[ExocortX @ExocortX]

@Anthyra_dev super début déjà !

[ExocortX @ExocortX]

@nicksaraev It takes me only 15mn/day. My secret? .... well I don't have community 😅 (yet)