Smarter retrieval strategies that outperform dense graphs — with hybrid pipelines and lower cost

I’m hanging out in Sydney with my esteemed co-author and co-conspirator Gene Kim today; we flew in to conduct Vibe Coding workshops and…

Check out HubSpot's FREE AI Decoded Pocket Guide: https://clickhubspot.com/d21e13 In today's video, I'll be breaking down what made DeepSeek V3.2 such an important paper, how is DeepSeek-V3.2-Speciale so good, how DeepSeek has created this model, and explaining DeepSeek's new secret weapon: DeepSeek Sparse Attention (DSA). My Newsletter https://mail.bycloud.ai/ my project: find, discover & explain AI research semantically https://findmypapers.ai/ My Patreon https://www.patreon.com/c/bycloud DeepSeek-V3.2 [Paper] https://arxiv.org/abs/2512.02556 [V3.2 Huggingface] https://huggingface.co/deepseek-ai/DeepSeek-V3.2 [V3.2 Speciale Huggingface] https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Speciale DeepSeek-V3.2-exp [Paper] https://github.com/deepseek-ai/DeepSeek-V3.2-Exp/blob/main/DeepSeek_V3_2.pdf [Huggingface] https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp DeepSeek-V3.1-Terminus [Paper] https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Terminus [Huggingface] https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Terminus Try out my new fav place to learn how to code https://scrimba.com/?via=bycloudAI This video is supported by the kind Patrons & YouTube Members: 🙏Spam Maj, Alex, Chris LeDoux, DX Research Group, Poof N' Inu, Deagan, Robert Zawiasa, Ryszard Warzocha, Tobe2d, Louis Muk, Akkusativ, Kevin Tai, Mark Buckler, NO U, Tony Jimenez, Ângelo Fonseca, jiye, Anushka, Asad Dhamani, Binnie Yiu, Calvin Yan, Clayton Ford, Diego Silva, Etrotta, Gonzalo Fidalgo, Handenon, Hector, Jake Disco very, Michael Brenner, Nilly K, OlegWock, Daddy Wen, Shuhong Chen, Sid_Cipher, Stefan Lorenz, Sup, tantan assawade, Thipok Tham, Thomas Di Martino, Thomas Lin, Richárd Nagyfi, Paperboy, mika, Leo, Berhane-Meskel, Kadhai Pesalam, mayssam, Bill Mangrum, nyaa, Toru Mon, Lame Plane [Discord] https://discord.gg/NhJZGtH [Twitter] https://twitter.com/bycloudai [Patreon] https://www.patreon.com/bycloud [Business Inquiries] bycloud@smoothmedia.co [Profile & Banner Art] https://twitter.com/pygm7 [Video Editor] @Booga04 [Ko-fi] https://ko-fi.com/bycloudai

This is a public facing version of an internal onboarding guide at Cursor provided to GTM + non engineering hires. This guide walks through getting started from scratch to a built out, deployed project.

superwhisper-prompts. GitHub Gist: instantly share code, notes, and snippets.

Contribute to mackid1993/superwhisper-dictation-prompts development by creating an account on GitHub.

SuperWhisper Trainer is an interactive training system that helps you create custom vocabulary and replacement rules for SuperWhisper - verygoodplugins/superwhisper-trainer

The one constant that I have observed in my professional life is that people underestimate the need to move fast. Of course, doing good work takes time. I once spent six months writing a URL parser. But the fact that it took so long is not a feature, it is not a positive, it is … Continue reading Why speed matters

Transform your voice into text instantly with WhisperClip - completely FREE forever! Privacy-first voice-to-text software for macOS featuring 100% local AI processing. No internet required, no subscriptions, no ads, no hidden costs. Your voice data never leaves your computer. Open source and reviewable.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

This application displays the evolution of benchmark scores for large language models over time. It shows the top scores achieved by models on various benchmarks and provides insights into the prog...

An empirical study analyzing over 100 trillion tokens of real-world LLM interactions across tasks, geographies, and time.

This article is for vibe coders and developers seeking private, fast, and affordable AI coding solutions.

Check out HubSpot's AI Decoded Guide: https://clickhubspot.com/c7a843 A tiny 27M parameter “recursive” model is suddenly rivaling frontier LLMs on the ARC AGI benchmark, challenging & revealing how iterative thought, not size, is also capable of solving hard logical tasks. Papers [HRM] https://arxiv.org/abs/2506.21734 [TRM] https://arxiv.org/abs/2510.04871 My Newsletter https://mail.bycloud.ai/ my project: find, discover & explain AI research semantically https://findmypapers.ai/ My Patreon https://www.patreon.com/c/bycloud Try out my new fav place to learn how to code https://scrimba.com/?via=bycloudAI This video is supported by the kind Patrons & YouTube Members: 🙏Spam Maj, Alex, Chris LeDoux, DX Research Group, Poof N' Inu, Deagan, Robert Zawiasa, Ryszard Warzocha, Tobe2d, Louis Muk, Akkusativ, Kevin Tai, Mark Buckler, NO U, Tony Jimenez, Ângelo Fonseca, jiye, Anushka, Asad Dhamani, Binnie Yiu, Calvin Yan, Clayton Ford, Diego Silva, Etrotta, Gonzalo Fidalgo, Handenon, Hector, Jake Disco very, Michael Brenner, Nilly K, OlegWock, Daddy Wen, Shuhong Chen, Sid_Cipher, Stefan Lorenz, Sup, tantan assawade, Thipok Tham, Thomas Di Martino, Thomas Lin, Richárd Nagyfi, Paperboy, mika, Leo, Berhane-Meskel, Kadhai Pesalam, mayssam, Bill Mangrum, nyaa, Toru Mon [Discord] https://discord.gg/NhJZGtH [Twitter] https://twitter.com/bycloudai [Patreon] https://www.patreon.com/bycloud [Business Inquiries] bycloud@smoothmedia.co [Profile & Banner Art] https://twitter.com/pygm7 [Video Editor] Abhay [Bitcoin (BTC)] 3JFMJQVGXNA2HJE5V9qCwLiqy6wHY9Vhdx [Ethereum (ETH)] 0x3d784F55E0bE5f35c1566B2E014598C0f354f190 [Litecoin (LTC)] MGHnqALjyU2W6NuJSSW9fTWV4dcHfwHZd7 [Bitcoin Cash (BCH)] 1LkyGfzHxnSfqMF8tN7ZGDwUTyBB6vcii9 [Solana (SOL)] 6XyMCEdVhtxJQRjMKgUJaySL8cGoBPzzA2NPDMPfVkKN [Ko-fi] https://ko-fi.com/bycloudai

Update: This post received a large amount of attention on Hacker News — see the discussion thread.

Anti-AI sentiment might or might not be rational, but it certainly relies on a lot of bad arguments.

`CLAUDE.md` is a high-leverage configuration point for Claude Code. Learning how to write a good `CLAUDE.md` (or `AGENTS.md`) is a key skill for agent-enabled software engineering.

For more information about Stanford’s Artificial Intelligence professional and graduate programs, visit: https://stanford.io/ai November 11, 2025 This lecture covers agents, prompts, and RAG. To learn more about enrolling in this course, visit: https://online.stanford.edu/courses/cs230-deep-learning Please follow along with the course schedule and syllabus: https://cs230.stanford.edu/syllabus/ More lectures will be published regularly. Andrew Ng Founder of DeepLearning.AI Adjunct Professor, Stanford University’s Computer Science Department Kian Katanforoosh CEO and Founder of Workera Adjunct Lecturer, Stanford University’s Computer Science Department

A friend made me aware of a reading list from A16Z containg recommendations for books, weighted towards science fiction since that’s mostly what people there read.

Artificial intelligence can already replace 11.7% of the U.S. labor market, across finance, health care and professional services, according to MIT's study.

Positron unifies exploration and production work in one free, AI-assisted environment, empowering the full spectrum of data science in Python and R.

Contribute to microsoft/fara development by creating an account on GitHub.

Qwen Image models through MPS. Contribute to ivanfioravanti/qwen-image-mps development by creating an account on GitHub.

Here's a delightful project by Tom Gally, inspired by my pelican SVG benchmark. He asked Claude to help create more prompts of the form Generate an SVG of [A] [doing] …

Our new flagship Olmo 3 model family empowers the open source community with not only state-of-the-art open models, but the entire model flow and full traceability back to training data.