Dev it!

AI enthusiast & developer. 🤖 Sharing insights on effective coding. 💻 Stay tuned for the latest tech news and tutorials!

[Dev it! @Dev_it_with_me]

Mind-blowing creative potential unleashed with Veo 3! 🤯
Look at this stunning animation of Ahri from League of Legends. The level of detail is absolutely insane. Imagine the stories we'll be able tell ! ✨ Keep innovating, Google! 🚀 #Veo3 #AI #FutureIsNow #LeagueOfLegends 🔥💖

[Dev it! @Dev_it_with_me]

GraphRAG is future of RAG systems! 🚨

Checkout my new tutorial explaining how it works and how to build it with my open source project! 🔥

[Dev it! @Dev_it_with_me]

Stop guessing how your RAG connects the dots. 🕵️‍♂️ See it.

I built a full GraphRAG application which visualizes the entire knowledge graph using React Flow.

Full build tutorial (Theory + Code) 👇
🔗https://t.co/3hepa71XAp?
si=rLVkesfEeCVwe7yw

#AI #GraphRAG #Python

[Dev it! @Dev_it_with_me]

Checkout my new GraphRAG tutorial!

[Dev it! @Dev_it_with_me]

Stop guessing how your RAG connects the dots. 🕵️‍♂️ See it.

I built a full GraphRAG application which visualizes the entire knowledge graph using React Flow.

Full build tutorial (Theory + Code) 👇
🔗https://t.co/3hepa71XAp?
si=rLVkesfEeCVwe7yw

#AI #GraphRAG #Python

[Dev it! @Dev_it_with_me]

Want to build a Knowledge Graph but scared of the complexity? 😨
I containerized the entire Microsoft GraphRAG workflow into a single Docker Compose file.
🚀 Clone repo
🐳 docker compose up
💬 Chat with your data
Full tutorial & code walkthrough:
https://t.co/x9d0f559Ns
#GitHub #CodingTutorial #Python #AI

[Dev it! @Dev_it_with_me]

Is Standard RAG dead? 📉
Maybe not, but for complex datasets (legal, medical, history), simple chunking just doesn't cut it anymore.
Here is my tutorial on GraphRAG and the full code:
👉 https://t.co/uz0pH2WsSc

#GenerativeAI #TechTrends #Programming

[Dev it! @Dev_it_with_me]

Stop guessing how your RAG connects the dots. 🕵️‍♂️ See it.

I built a full GraphRAG application which visualizes the entire knowledge graph using React Flow.

Full build tutorial (Theory + Code) 👇
🔗https://t.co/3hepa71XAp?
si=rLVkesfEeCVwe7yw

#AI #GraphRAG #Python

[Dev it! @Dev_it_with_me]

It is definitely going in the right direction, but when we talk about the coverage it is not yet on the mypy level. But Astral knows how to do it, they proved it with uv and ruff, so it is the matter of time. And because uv is already adopted then switch for ty will be very easy for most developers

[Google AI Studio @GoogleAIStudio]

gemini 3 pro

• our most intelligent model yet
• SOTA reasoning
• 1501 Elo on LMArena
• next-level vibe coding capabilities
• complex multimodal understanding

available now in Google AI Studio and the Gemini API

[Kimi.ai @Kimi_Moonshot]

Kimi Linear Tech Report is dropped! 🚀
https://t.co/LpnPOu6KVb

Kimi Linear: A novel architecture that outperforms full attention with faster speeds and better performance—ready to serve as a drop-in replacement for full attention, featuring our open-sourced KDA kernels! Kimi Linear offers up to a 75% reduction in KV cache usage and up to 6x decoding throughput at a 1M context length.

Key highlights:
🔹 Kimi Delta Attention: A hardware-efficient linear attention mechanism that refines the gated delta rule.
🔹 Kimi Linear Architecture: The first hybrid linear architecture to surpass pure full attention quality across the board.
🔹 Empirical Validation: Scaled, fair comparisons + open-sourced KDA kernels, vLLM integration, and checkpoints.

The future of agentic-oriented attention is here! 💡

[Logan Kilpatrick @OfficialLoganK]

Tomorrow is a special day for the AI Studio team.

Since May, we have been heads down building a brand new AI vibe coding experience to accelerate the path from prompt to production with Gemini.

Can’t wait to show you all :)

[Dev it! @Dev_it_with_me]

Want to make an AI an expert on YOUR data? Here's the blueprint. 👇

This is the RAG (Retrieval-Augmented Generation) workflow, which lets an AI answer questions using your private documents.

Here's how it works:
1️⃣ Index: Your documents are broken into chunks & turned into numerical "embeddings."
2️⃣ Retrieve: When you ask a question, the system finds the most relevant chunks from your docs.
3️⃣ Generate: The AI gets your question PLUS the relevant chunks to create a factual, cited answer.

I built this entire system to run locally! My new YouTube tutorial shows you how to code it with Ollama, Docker, and Python.

Watch the full tutorial here: https://t.co/oHjxnfUsUV

#RAG #AI #LocalLLM #Python #Docker #LLM

[Dev it! @Dev_it_with_me]

Link to the full tutorial:
https://t.co/eadbf8Ja5B

#RAG #AI #Ollama #pgvector #LocalAI #Tutorial #FastAPI

[Dev it! @Dev_it_with_me]

What is an AI Embedding? 🧠

Explained in 40 seconds.

It's the key that lets AI understand meaning, not just words. And it's how you can build an AI to chat with your own documents!

Watch the quick explainer 👇

#AI #LearnToCode #Embeddings #TechExplained #RAG

[Z.ai @Zai_org]

Introducing GLM-4.6: Advanced Agentic, Reasoning and Coding Capabilities

As our new flagship model, GLM-4.6 brings significant advancements across real-world coding, long-context processing (up to 200K tokens), reasoning, search, writing, and agentic applications.

API: https://t.co/IcoRb30vY7
Subscription: https://t.co/Nk8Y98Il7s
Weights: https://t.co/JAUslrY2dk
Try it now: https://t.co/WCqWT0raFJ
Tech Blog: https://t.co/auZkrtOsYh

[Jules @julesagent]

Welcome to ship week! New Jules ship every day this week

[Dev it! @Dev_it_with_me]

🤖 Robots that think.
⚡ AI chips that shatter speed records.
💻 Coding agents that work for you.

Latest Tech Check is LIVE!

We're breaking down the game-changing innovations you need to know about:
- Google's Gemini Robotics 1.5: Robots that plan and reason.
- Euclyd's Craftwerk: A new chip monster crushing performance records.
- Microsoft Copilot: Now supercharged with Anthropic's Claude models.
- GitHub Copilot Agent: Now generally available to supercharge your workflow.

Dive into the future of tech. Watch the full episode here! https://t.co/ruBga6he7L

#AI #Tech #Robotics #Innovation #Google #Microsoft #GitHub #FutureOfTech

[Dev it! @Dev_it_with_me]

The new model from @Alibaba_Qwen is unique!

End-to-end omni-modality, open-source, and compact enough to run locally!

Excited to try it!

[Qwen @Alibaba_Qwen]

🚀 Introducing Qwen3-Omni — the first natively end-to-end omni-modal AI unifying text, image, audio & video in one model — no modality trade-offs!

🏆 SOTA on 22/36 audio & AV benchmarks
🌍 119L text / 19L speech in / 10L speech out
⚡ 211ms latency | 🎧 30-min audio understanding
🎨 Fully customizable via system prompts
🔗 Built-in tool calling
🎤 Open-source Captioner model (low-hallucination!)

🌟 What’s Open-Sourced?
We’ve open-sourced Qwen3-Omni-30B-A3B-Instruct, Qwen3-Omni-30B-A3B-Thinking, and Qwen3-Omni-30B-A3B-Captioner, to empower developers to explore a variety of applications from instruction-following to creative tasks.

Try it now 👇
💬 Qwen Chat: https://t.co/rJ5DUlBJBr
💻 GitHub: https://t.co/VHHp1jWcHT
🤗 HF Models: https://t.co/WsP8vyWltp
🤖 MS Models:
https://t.co/sGnbZRfxVz
🎬 Demo: https://t.co/v2WrZvCKD6

[Dev it! @Dev_it_with_me]

OpenAI’s launching a program to certify 10M AI-savvy job seekers! 🎓

Get ready for the AI-driven job market with new skills.

Source: https://t.co/JyjWF6gQLF

#AI #OpenAI #Careers #Tech

[Dev it! @Dev_it_with_me]

Mistral’s €1.7B funding from ASML is a massive win for European AI! 💰

How do you think this will shake up the global AI race?

Share your predictions! 🤔

Source: https://t.co/l3DpVYjIpF
#AI #Mistral #Tech

[Dev it! @Dev_it_with_me]

I was wondering when Google would integrate Gemini further into Chrome. It seems that day has arrived! 💫

Do you think Gemini is advanced enough to help rather than annoy Chrome users?🤔

[Google @Google]

We’re rolling out the biggest upgrade to Chrome in its history with all-new AI features, including:
✨ Gemini in Chrome
🔎 Search with AI Mode right from the address bar
🔐 One-click updates for compromised passwords, plus more safety features
And more → https://t.co/x6UGeOFcjI

[Dev it! @Dev_it_with_me]

That's definitely something new!

Chain of Thought made LLMs much more useful; it could do the same for video generation.

Ray 3 seems like a fresh start!

[Chubby♨️ @kimmonismus]

I did not see that coming: Chain of Thought in AI Video generation!

LumaAI introduced Ray 3

- HDR Generation
- Fidelity "state of the art realism, physics, character consistency, and far superior instruction following"
- SOTA Physics & Controls

And much more. Some examples: