Walid 🦋
LightNews LightNews
banner
walidev.bsky.social
Walid 🦋
@walidev.bsky.social
410 followers 1.3K following 88 posts
💡 Certified in #AI | 🚀 #Crypto & #Web3 Enthusiast | #OSINT Lover ❤️ | Sharing insights on the future of tech, finance, and digital innovation 💻 Follow for updates in AI, blockchain, and beyond !
Posts Replies Media Videos
Reposted by Walid 🦋
julesblaster.bsky.social
« Chère Aurore Bergé »

Boxing Day, épisode 29

« On l’aura compris, vous êtes prête à absolument tout pour servir vos ambitions, quitte à tordre le réel, caricaturer, mentir, diffamer, calomnier et renier vos supposées «convictions» lorsque le vent tourne. »

Via @blast-info.fr

shorturl.at/uOi7K
Chère Aurore Bergé - Boxing Day #29
Chère Aurore Bergé,Quelle semaine !Dimanche 13 avril, vous diffusiez sur votre compte X, vidéo à l’appui, l’information selon laquelle, durant une manifestation de soutien à Gaza, « une boulangerie [a...
shorturl.at
April 19, 2025 at 4:00 PM
Reposted by Walid 🦋
fightingpride93.bsky.social
First image: King Kong and Godzilla fighting. Godzilla is labelled "english" King Kong is labelled "arabic". Godzilla says "ninety-nine" King Kong says "nine ninety". Second image: King Kong and Godzilla fleeing from a Shiba Inu wielding a baseball bat labelled "french" saying "four twenty ten nine"
April 11, 2025 at 9:26 PM
Reposted by Walid 🦋
walidev.bsky.social
8 new types of RAG

▪️ DeepRAG
▪️ RealRAG
▪️ Chain-of-Retrieval Augmented Generation (CoRAG)
▪️ VideoRAG
▪️ CFT-RAG
▪️ Contextualized Graph RAG (CG-RAG)
▪️ GFM-RAG
▪️ URAG

Save the list and check this out for more info: huggingface.co/posts/Ksenia...
@Kseniase on Hugging Face: "8 New Types of RAG RAG techniques continuously evolve to enhance LLM response…"
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
February 9, 2025 at 12:47 PM
Reposted by Walid 🦋
walidev.bsky.social
Exploring the Open Source AI Stack! 🖥️ From Next.js to Llama 3.3, this stack covers it all: frontend, embeddings, retrieval, and large language models. A complete toolkit for building the future of AI. 🚀 #AI #OpenSource #MachineLearning #AIStack #Developers
Diagram showcasing an open-source AI stack by ByteByteGo. Includes tools for frontend (Next.js, Vercel, Streamlit), embeddings/RAG libraries (Nomic, Cognita, LLMWare), backend (LangChain, Huggingface), data/retrieval (Postgres, Milvus), and large language models (Llama 3.3, Mistral, Phi).
January 15, 2025 at 6:28 AM
walidev.bsky.social
8 new types of RAG

▪️ DeepRAG
▪️ RealRAG
▪️ Chain-of-Retrieval Augmented Generation (CoRAG)
▪️ VideoRAG
▪️ CFT-RAG
▪️ Contextualized Graph RAG (CG-RAG)
▪️ GFM-RAG
▪️ URAG

Save the list and check this out for more info: huggingface.co/posts/Ksenia...
@Kseniase on Hugging Face: "8 New Types of RAG RAG techniques continuously evolve to enhance LLM response…"
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
February 9, 2025 at 12:47 PM
Reposted by Walid 🦋
nomadmatt.bsky.social
For those saying it wasn't a Nazi salute.

Keep posting it. Keep sharing it.
January 21, 2025 at 6:15 PM
Reposted by Walid 🦋
molly.wiki
having succeeded in purchasing positions of influence inside the White House, the billionaires and tech VCs have now set their sights back on Wikipedia
Chamath Palihapitiya @chamath · 2h Wikipedia lies. Mainstream media lies. They will contort the truth to make you believe in a bogeyman. In falling for it, you’re giving up your God given ability to think for yourself. Shaun Maguire @shaunmmaguire Wikipedia has been ideologically captured for years It's important that this is finally coming to light The most extreme bias is probably against Israel Foundation AI models are being trained on this biased data as if it's ground truth Elon Musk @elonmusk · 3h Defund Wikipedia until balance is restored! Elon Musk @elonmusk · 3h Since legacy media propaganda is considered a “valid” source by Wikipedia, it naturally simply becomes an extension of legacy media propaganda!
January 21, 2025 at 8:52 PM
walidev.bsky.social
DeepSeek R1 1.5B running FULLY LOCALLY in your browser , powered by WebGPU🔥

Try it out directly here: huggingface.co/spaces/webml...
January 22, 2025 at 11:47 AM
Reposted by Walid 🦋
afondiste.bsky.social
Les mails pro pourris - tellement vrai 🤣🤣🤣
January 18, 2025 at 11:39 AM
Reposted by Walid 🦋
walidev.bsky.social
Small but mighty! 🚀 Phi-4 proves you don’t need billions of parameters to achieve top-tier performance. Compact, efficient, and leading the frontier for smaller models. Try it on #ollama 😍

#AI #ML #EfficientAI #Transformers #AIInnovation
January 9, 2025 at 7:25 AM
walidev.bsky.social
Exploring the Open Source AI Stack! 🖥️ From Next.js to Llama 3.3, this stack covers it all: frontend, embeddings, retrieval, and large language models. A complete toolkit for building the future of AI. 🚀 #AI #OpenSource #MachineLearning #AIStack #Developers
Diagram showcasing an open-source AI stack by ByteByteGo. Includes tools for frontend (Next.js, Vercel, Streamlit), embeddings/RAG libraries (Nomic, Cognita, LLMWare), backend (LangChain, Huggingface), data/retrieval (Postgres, Milvus), and large language models (Llama 3.3, Mistral, Phi).
January 15, 2025 at 6:28 AM
walidev.bsky.social
So true ! 😅
January 14, 2025 at 4:21 PM
walidev.bsky.social
Radar of AI capabilities! 🛠️ GPT-4o-202405 leads across diverse benchmarks in speech, visual understanding, and live streaming tasks. From TextVQA to AISHELL-1, it's a game-changer. #AI #ML #GPT4 #AIInnovation #MultimodalAI
A radar chart comparing AI models (GPT-4o-202405, Gemini-1.5 Pro, Qwen2-VL 7B, GLM-4-Voice 9B, MiniCPM-o 2.6 8B) across tasks like speech conversation, visual understanding, and live streaming. GPT-4o-202405 dominates most categories with exceptional performance.
January 14, 2025 at 12:19 PM
walidev.bsky.social
Small but mighty! 🚀 Phi-4 proves you don’t need billions of parameters to achieve top-tier performance. Compact, efficient, and leading the frontier for smaller models. Try it on #ollama 😍

#AI #ML #EfficientAI #Transformers #AIInnovation
January 9, 2025 at 7:25 AM
walidev.bsky.social
🚨 Google releases a white paper on AI agents

The document dives into the basics of LLM agents and includes a quick implementation guide using LangChain. Here are the 5 key takeaways:
January 5, 2025 at 8:43 AM
walidev.bsky.social
🚨 Microsoft launches MarkItDown: an open-source tool for converting PDFs, Word, Excel, images, and audio to Markdown—perfect for LLMs! 🎉

✨ Key features:

- Auto OCR & EXIF extraction
- LLM-powered image descriptions
- CLI, Python API, Docker
- Batch conversions
- Streamline your workflows today! 🚀
January 2, 2025 at 5:31 PM
walidev.bsky.social
If you’re wondering how quickly AI performance is advancing, this graph says it all. The growth is practically vertical! 🚀
December 24, 2024 at 9:21 AM
walidev.bsky.social
New AI model benchmarks show phi-4 outperforming on GPQA, MATH, and reasoning tasks, while GPT-4o leads in HumanEval and MMLU. The race in AI performance intensifies across domains! 🚀 #AI #MachineLearning #Benchmarking #NLP #ArtificialIntelligence #Phi4 #GPT
Table comparing the performance of AI models (phi-4, phi-3, Qwen 2.5, GPT, Llama-3.3) on benchmarks like MMLU, GPQA, MATH, HumanEval, MGSM, SimpleQA, and DROP. Scores highlight strengths of different models in reasoning, coding, and QA tasks across small and large models.
December 13, 2024 at 6:59 AM
Reposted by Walid 🦋
walidev.bsky.social
Deep dive into #AgentExecution! This flowchart breaks down AI agent processes, from planning and reasoning to memory and workflow. Essential for understanding intelligent agent behavior in complex tasks. 💡🤖 #AI #ArtificialIntelligence #MachineLearning #Automation #AITech
Flowchart showing the detailed process of agent execution, including planning, reasoning, memory, and workflow components. It starts with Agent Execution, branching into sections for Planning (with goals, roles, tasks), Reasoning (with benchmarks and long-term memory), Memory (short-term and long-term memory details), and Workflow (types, variables, nodes). This diagram highlights the structured approach required for complex AI agent tasks.
November 15, 2024 at 1:06 PM
walidev.bsky.social
Phidata ! 👍 🥰
November 30, 2024 at 12:49 AM
walidev.bsky.social
Try out Intellect-1 on : chat.primeintellect.ai
November 29, 2024 at 11:12 PM
Reposted by Walid 🦋
walidev.bsky.social
Curious about building your own AI agent? 🤔

These 7 open-source libraries are your answer. 👇
November 29, 2024 at 4:45 PM
walidev.bsky.social
Curious about building your own AI agent? 🤔

These 7 open-source libraries are your answer. 👇
November 29, 2024 at 4:45 PM
walidev.bsky.social
Andrew NG just opensourced a new Python Package.
One line to switch between any LLM:
OpenAI ➝ "openai:gpt-4o"
Claude ➝ "anthropic:claude-3-5-sonnet"
Llama ➝ "ollama:llama3"

pip install aisuite

Github : github.com/andrewyng/ai...
November 27, 2024 at 2:23 PM
walidev.bsky.social
🤖 Dive into Transformer Architecture - the backbone of modern AI models like ChatGPT! This visual guide explains how Transformers process sequential data using self-attention, encoders, and decoders. A must-read for #AI & #ML enthusiasts! 🚀 #DeepLearning #NeuralNetworks
An infographic titled "ML Basics - The Transformer Architecture" by databytes.tech. Definition: Explains Transformers as neural networks excelling at understanding and generating sequential data using self-attention, without RNNs or convolution. Black Box: Illustrates Transformers for language translation, showing input, the transformation process, and output. Encoder/Decoder Architecture: Highlights how the encoder processes input into a structured matrix and the decoder generates outputs. Detailed Architecture: Depicts layered encoders and decoders with self-attention and feedforward mechanisms. Simplifies the flow of inputs to final outputs in language tasks.
November 25, 2024 at 2:08 PM