8 RAG architectures all AI Engineers should know:

There is no better place on the internet to learn about Context Engineering than this repo. It's literally a course with a learning path. It gathers the best resources and covers the theory + code for anything related to context, RAG, memory, and agentic systems and more.

New hyper-efficient addition to our amazing Gemma open models: Gemma 3 270M packs a real punch for its tiny size! It’s super compact and power efficient, so you can easily run your own task-specific fine-tuned systems on edge devices. Enjoy building with it!

Let's build an MCP server (100% local):

Meet SFR-DeepResearch (SFR-DR) 🤖: our RL-trained autonomous agents that can reason, search, and code their way through deep research tasks. 🚀SFR-DR-20B achieves 28.7% on Humanity's Last Exam (text-only) using only web search 🔍, browsing 🌐, and Python interpreter 🐍,

When I started LLMs-from-scratch I just hoped it might help a few people learn. Just saw the GitHub the repo has now been forked 10k times! More than the stars, the best part is seeing thousands of people actually use and build on the code ☺️

Ilya Sutskever explains why AI will do 100% the work that human can do within few years. "Slowly but surely, or maybe not so slowly, AI will keep getting better. The day will come when AI will do all of our, all the things that we can do, not just some of them, but all of them.

this is the most important chart on the new gpt-5-codex model We are just beginning to exploit the potential of good routing and variable thinking: Easy responses are now >15x faster, but for the hard stuff, 5-codex now thinks 102% more than 5. Same model, same paradigm, but

GPT-5-Codex is 10x faster for the easiest queries, and will think 2x longer for the hardest queries that benefit most from more compute.

Harshad Saykhedkar Asfi In this context, GEPA works as a prompt optimizer, so the end result is a prompt (or multiple prompts for a multi-agent system, one for each component). However, one aspect that does not get highlighted enough is that GEPA is a text evolution engine: Given a target metric, GEPA

China's Alibaba just dropped an opensource 30B agentic LLM that outperforms Claude 4 Sonnet, DeepSeek v3.1, Kimi k2 on a range of agentic search benchmarks. Only ~3B parameters are activated per token. 100% Opensource.

Announcing “K-Dense”, a multi-agent AI scientist that has already made a new discovery in aging research 🧵 Ashwin Gopinath & @BioStateAI tinyurl.com/3dmraa5k

"Mathematics for Computer Science" — MIT This book of 1048 pages is now FREE. A MUST for all Beginners. To Get it: 1. Follow me (so that i can DM you 2. Repost 3. Comment "MIT"

Thinking, Searching, and Acting A reflection on reasoning models. It's easy to fixate on the "thinking" that gave reasoning models their name, but just over a year out from o1-preview's release by OpenAI, the core primitives that make up models today has expanded. Searching and

RL is not enough. It only reaches its potential when combined with other ideas. The most famous example is AlphaZero. RL was combined with self-play which created an implicit task curriculum that evolved through training. This is very different from many RL datasets for LLMs

Vibe coding with AI Studio is so addictive! I built an AI Hair Stylist Agent that: > find the best haircut by looking my face > generates the after images using nano banana > lets me edit it live with the live API > find nearby salons using google maps Built in just 5 mins!

I'm so proud!! The open-source trillion parameters reasoning model <3 > SOTA on HLE (44.9%) and BrowseComp (60.2%)

Our first release is Gemini 3 Pro, which is rolling out globally starting today. It significantly outperforms 2.5 Pro across the board: 🥇 Tops LMArena and WebDev lmarena.ai leaderboards 🧠 PhD-level reasoning on Humanity’s Last Exam 📋 Leads long-horizon planning on Vending-Bench 2

Gemini 3 Pro is the new leader in AI. Google has the leading language model for the first time, with Gemini 3 Pro debuting +3 points above GPT-5.1 in our Artificial Analysis Intelligence Index Google DeepMind gave us pre-release access to Gemini 3 Pro Preview. The model

The secret behind Gemini 3? Simple: Improving pre-training & post-training 🤯 Pre-training: Contra the popular belief that scaling is over—which we discussed in our NeurIPS '25 talk with Ilya Sutskever and Quoc Le—the team delivered a drastic jump. The delta between 2.5 and 3.0 is