A GERMAN DEVELOPER REPLACED HIS ENTIRE DEV TEAM WITH KIMI K2.6, VISUALIZED EVERYTHING IN OBSIDIAN AND NOW MAKES $80,000/MONTH SOLO 1 trillion parameters, 32 billion activated per token and a SWE-Bench score of 65.8 - Kimi K2.6 reads the entire client codebase, understands the https://t.co/Tcl0QXK7FB https://t.co/0EyEclXOu3
X bookmarks
Review queue · sorted by recency · last sync 1h ago
+ 2 unused
+ Add a badge
★ 5.4@noisyb0y1en2d ago ★ 10.8@NousResearch✓en4d ago The @xai team has published a full setup guide on how to use the xurl skill, which allows your Hermes Agent to read and write to X on your behalf — posting, searching, pulling bookmarks, managing lists, and more — all through natural language. https://t.co/6AwkzKChha https://t.co/cvkwuvdDnK
★ 16.9@0xMovezen4d ago Spotify's Chief Architect just showed how they ship 4,5K deployments /day with Claude at Anthropic stage 27-minutes. free. By #1 music app dev "More than 99% of our engineers use AI coding tools. Adoption took off after Opus 4.5" Worth more than any $500 vibe-coding course. https://t.co/5g697TGtDu https://t.co/R8PWTIDKXt
★ 10.3@DamiDefien6d ago Life after discovering MIT put a world class AI education online for free. This is what happens when you actually feed all 12 into Claude. A completely rebuilt research system. https://t.co/xHL5QPIZKa https://t.co/rs1fEOUoHr
★ 1.5@0xDepressionnzxx2026-05-17 https://t.co/EKKW7dS4zk
★ 0.0@sairahul1zxx2026-05-17 https://t.co/voJe5fY8Q3
★ 10.9@Zephyr_hgen2026-05-15 ANDREJ KARPATHY: "the internet is terrible. A huge amount of slop and garbage from all the corners of the internet." Type 1: you ask generic Claude generic questions, you get back generic internet-trained answers. Type 2: you brief Claude with your business, your voice, your https://t.co/bQSdtJEbph https://t.co/QhT62IcuGM
★ 1.1@eng_khairallah1zxx2026-05-15 https://t.co/byOzZfUvFh
★ -0.1@Zephyr_hgzxx2026-05-14 https://t.co/MfsQZ7VYTv
★ 1.9@akshay_pachaarzxx2026-05-13 https://t.co/Exoyd8tB0d
★ 5.6@DeRonin_en2026-05-12 Andrej Karpathy: "90% of your AI coding bill is paying for context you didn't need to send" Here are 10 things senior AI engineers stopped wasting tokens on: 1. Auto-context loading 50 files for a 30-line fix: $1.20/turn for tokens you'll never read. 80% input waste, every https://t.co/RobBDHo2ZQ https://t.co/G9Ox6xMTxZ
★ 9.3@cgtwtsen2026-05-10 Andrej Karpathy: “10x engineers are normal. real agentic engineers are 100x” Context engineering is becoming the foundation of agentic software. Tool routing, memory systems, evals, and orchestrator-subagent workflows are the new stack. Bookmark it and watch it. https://t.co/mx3dKd8bdq https://t.co/oObBvRDczE
★ 8.7@Mnilaxen2026-05-10 Karpathy threw a grenade at every senior engineer who still treats LLMs as a toy. his actual words: the worst thing an expert can do right now is reject them. most experts read it as a threat, but it's advice. his framing: > the gap between "AI tools are bad" and "AI tools https://t.co/r7T4cWnYbQ https://t.co/HqCTygknPK
★ 5.4@leopardraceren2026-05-09 ANDREJ KARPATHY IS THE GODFATHER OF MODERN AI He doesn’t use Notion. He doesn’t use Roam. He doesn’t use Obsidian plugins. He built his own second brain from scratch. I copied him exactly. The result: → 378 notes → 1,854 nodes → 3,856 edges → One custom 3D knowledge galaxy https://t.co/rBJHSXpIsL https://t.co/RhHioFahmj
★ 11.0@trq212en2026-05-08 HTML is the new markdown. I've stopped writing markdown files for almost everything and switched to using Claude Code to generate HTML for me. This is why. https://t.co/T97m0lIDx1
★ 12.0@system_monarchen2026-05-04 System Design Round at Anthropic: You are running an LLM in production that costs $0.40 per query. At 100,000 queries a day that is $40,000 a day. You check your logs and find 60,000 of those queries are users asking slight variations of the same 200 questions. Your model is
★ 9.0@bbssppllvven2026-04-30 Agents make ugly UIs because they've never seen good design. We've been fixing that, 2,000 DESIGN.md files from the world's best products, structured for a model to read and learn. Colors, type, spacing, layouts and more. Free. https://t.co/mJaKNHba0O https://t.co/GkbyV1HMRQ
★ 4.4@_smontlouisfr2026-04-29 Je vous conseille de bouffer du matt pocock matin midi et soir. Je pense legit que c'est le meilleur architecte IA actuel. Ses skills sont excellents, ses vidéos sont excellentes tout ce qu'il fait est EXCELLENT. ZERO SLOP dans mes projets mes repos sont cleeaannnnnnn
★ 1.2@sharbelzxx2026-04-28 https://t.co/RzJaPFrOKp
★ 9.5@JulianGoldieSEOen2026-04-27 Hermes doesn’t have to anymore. Here’s the workflow: → OMI records your day → Obsidian stores memory vault → Hermes reads vault locally → Context sync happens automatically → Works across agent ecosystems That’s real long-term memory infrastructure. Save this video, https://t.co/BnLA4l6y6y
★ 6.0@steipeteen2026-04-25 Built clawsweeper, which runs 50 codex in parallel around the clock, scans issues/prs deep and closes what is already implemented or what makes no sense. Closed around 4000 issues today, a few thousand are in the pipeline. (rate limits are rough) https://t.co/AiNNDcvGke
★ 12.0@kirillk_web3en2026-04-24 > use Claude Code for months > Claude makes wrong assumptions every session > overwrites code I didn't ask to touch > adds 500 lines when 50 would do > find the CLAUDE.md file on GitHub trending > 82,000 stars. one file. > paste it into my project > first task > wait. it asked https://t.co/HVEQReFB6T https://t.co/mDIaku59Pr
★ 4.6@k1ralliken2026-04-24 > be Kimi > 2023 Beijing - invisible to the rest of the world > your founder left Google Brain to build you > everyone said he was too late > launch with 128k context. OpenAI is stuck at 4k > developers switch overnight > scale to 1 million tokens. nobody is close > 36 million https://t.co/pJACHJQRO6 https://t.co/EBfnYDohbx
★ 15.0@kirillk_web3en2026-04-24 A SINGLE CLAUDE.md FILE JUST HIT #1 ON GITHUB TRENDING. 82,100 stars. 7.8k forks. zero dependencies. Bookmark this before you forget. And your Claude will start working differently. 4 principles. one file. Karpathy's LLM coding habits. distilled. > think before coding. > https://t.co/3NVb5S5xbc https://t.co/byUHaq1vBB
★ 1.4@cyrilXBTzxx2026-04-23 https://t.co/lkRFCBt82J
★ 10.7@Kimi_Moonshot✓en2026-04-23 Meet Kimi K2.6 Agent Swarm 👋 Highlights: 🔹 Swarms, elevated - 300 parallel sub-agents × 4,000 steps per run (up from 100 / 1,500 in K2.5). 🔹 Outputs are real files, not chat - one run delivers 100+ files, 100,000-word literature reviews, or 20,000-row datasets. https://t.co/IZ2KljFdez
★ 1.1@SilenceCaPrompten2026-04-22 Repo Github : https://t.co/9gsRZXmDxh
★ 1.4@aiedge_zxx2026-04-22 https://t.co/bDaKwfM4GJ