THIS AI BUILT A FULL BLOCK SURVIVAL GAME IN SWIFT FROM ZERO 45000 lines of code 82 files zero dependencies a hand written metal renderer with ssao volumetric god rays and soft shadows every sound and track synthesized live from oscillators no audio files at all 879 blocks 1188 items 63 biomes 100 entity types with a star pathfinding three dimensions redstone enchanting villages raids and all three bosses running at 200 plus fps on an m series macbook fully open source on github and you can build it yourself bookmark this ↓

POV: waiting for the local LLM to finish generating

TWO BUTTONS AND SPEECH IS ALL IT TOOK TO BUILD THIS most people are still copy pasting from a chat window while builders like this ship full apps in days here’s the exact setup (skills subagents AGENTS.md) that makes claude operate like this for any project ↓

A 6 YEAR OLD ANDROID JUST OUTRAN WHAT TOOK A SERVER IN 2023 gemma 4 e2b running via llama.cpp and termux on a note 20 ultra, 12 tokens per second on cpu only with multi token prediction enabled no gpu, no laptop, no cloud subscription MTP draft assistant gives a free 20-30% speed boost on top, works on any phone with 8GB RAM in my local llm playbook i wrote that mobile inference was coming and this is exactly what that looks like the floor just dropped out from under every excuse not to run local ai bookmark this ↓

OLD AUTOMATIONS HAVE ONE THING. A TRIGGER. Do X every Y minutes. Familiar. Useful. Limited. A loop has two things. A trigger that starts it and a goal that stops it. The agent runs, checks its own output, decides whether it passed, and if not, writes the next prompt itself and runs again. You stop being the person who decides whether to rerun. The loop decides. In this article you have 3 loops that replace 3 old automations. Completely seamless and hands off. The files are available to build in your own environment today. Bookmark it and give it a read today!

MUHAMMET YILMAZ SET UP ONE LOOP AND IT POSTED 388 TIMES WITHOUT HIM same content but different captions and different music every time, regenerated automatically across instagram, tiktok and youtube while he just watched most people are still doing all of this by hand and wondering why they can’t keep up save the full breakdown before you waste another week on manual posting ↓

HE BUILT A SAAS THAT RUNS ITSELF AND NEVER ASKED FOR PERMISSION one cron job runs his entire saas while he sleeps, posts to instagram and tiktok 24/7 and never stops this is the loop everyone keeps talking about and you still don’t have one save the full breakdown before you waste another hour doing it manually ↓

Boris Cherny, creator of Claude Code: “I have loops that are running, that are prompting, and kinda figuring out how to do my job anymore.” So while you’re still writing every prompt by hand, the guy who built Claude Code has agents that run, prompt themselves and figure out the work without him. Watch him explain it, then save the full setup below

THIS IS WHAT A REAL AI AGENT LOOKS LIKE IN THE WILD not a chatbot sitting in a browser waiting for your next prompt to do anything a robot with a goal and real tools and a loop that keeps running until the job is done most people still think ai agents are just better chatbots but this thing has been actively trying to sell something for 5 minutes straight without a single human telling it what to do next that’s the difference between a system that answers and a system that actually works bookmark the article below if you want to understand how this loop works ↓

POV: giving Claude Fable 5 full access

12,782 CONNECTIONS IN ONE VAULT that’s not a note-taking app anymore, it’s a cognitive engine every node in this graph is one idea and every edge is a link someone had to think hard enough to draw @cyrilXBT’s masterclass explains exactly how a vault gets here, atomic notes, the two-link rule, maps of content, claude connected via filesystem mcp bookmark and read it ↓

William Steuk, Member of Technical Staff at Anthropic: “When your agent outgrows its prompt you don’t make it bigger, you decompose it into focused pieces that actually work” So while you’re still trying to build one giant assistant that does everything an Anthropic engineer just showed how to spin up 5 focused agents in one afternoon covering code review, testing, documentation and daily dev tasks and that’s exactly where the industry is heading Watch it then read the full breakdown below ↓

Maya Nielan, member of Anthropic’s Technical Team: “We stopped guessing why agents waste tokens and we measured it” So while you’re scaling up compute and switching models the person who runs agentic evals at Anthropic already found the fix and it’s not a new model or a complex trick, just cleaner tool output and better context that cut token use by 66% Watch her explain it then save the full guide below👇

267 TOKENS PER SECOND ON A SINGLE RTX 5080 this is ollama running llama 3.2 1b and it’s not even a large model but the speed is the whole point two years ago getting 30 tokens per second on consumer hardware felt like a win and now a single gpu is doing nearly 10x that the gap between local and cloud is closing faster than anyone expected and the article below breaks down exactly which tools and hardware get you there in 2026 ↓

OLLAMA RUNNING ON A 10 YEAR OLD PHONE FROM 2015 this is not a modern flagship and not a raspberry pi and not some custom edge device this is a sony xperia from 2015 with linux deploy and ollama just running on it like it’s nothing in 2026 the hardware bar for local AI is so low it’s basically on the floor spoiler: it’s less than you think ↓

ANTHROPIC JUST MADE AI AGENTS TALK TO ROBOTS this guy connects claude to a physical robot via ROS and the robot figures out on its own how to move and find objects in a room and anthropic just dropped managed agents that handle sessions, credentials and debugging loops automatically so building stuff like this went from days of infrastructure work to 30 minutes the gap between “AI chatbot” and “AI that acts in the physical world” is closing faster than most people realize and we’re still in the early innings if this blows your mind even a little bookmark it and drop a like👇