Wal @walidshaari

介绍比Jev快50倍，在你设备上跑的laya-mlx! 只在你的设备上占用最高1G内存 Laya是一个开源的类似于Jev的,基于文本输出概率的分类系统 我将其移植到MLX,并且做了一些性能优化! 视频中就是这个模型在我的本地M3Max上玩贪吃蛇 这个模型能够以每秒决策60次的速度玩贪吃蛇！ github.com/mizorewww/laya…

Local Laya moggs Jev at @grok 4.7-built Tetris 🧩 An open-weights System One model called Laya, beat cloud-based Jev at playing Tetris by making decisions 11 times faster, running locally on a 16GB MacBook Air! Run AI models locally -> atomic.chat

雨夹雪❄️ @mizorewww

3 days ago

介绍比Jev快50倍，在你设备上跑的laya-mlx! 只在你的设备上占用最高1G内存 Laya是一个开源的类似于Jev的,基于文本输出概率的分类系统 我将其移植到MLX,并且做了一些性能优化! 视频中就是这个模型在我的本地M3Max上玩贪吃蛇 这个模型能够以每秒决策60次的速度玩贪吃蛇！ github.com/mizorewww/laya…

277 1K 14K 4.1M 18K

oh snap. finishing quick used to be a bad thing 💅

TypeSafe AI @typesafeai

2 days ago

Jev is now available to everyone. No waitlist. Start using it here: console.typesafe.ai

714 2K 23K 3.1M 12K

Over 300 original figures! An Illustrated Guide to AI Agents is now OUT on Kindle and other Ebook stores! Presses are rolling, print copies ship in a few weeks. @MaartenGr and I spent the last year and a half making the agent stack legible: memory, tools, planning, evaluation, multi-agent systems, and code agents. We're ecstatic to finally be able to share it with you! Agents are being adopted faster than they're being understood. Our bet is that a small number of concepts will outlast everything else in this field, so we spent the time identifying them and explaining them properly. Concepts and code. You build a working agent yourself along the way. Order here: Amazon: amazon.com/Illustrated-Gu… O'Reilly: oreilly.com/library/view/a…

This just gets crazier by the second. @Meta and @finkd need to address this ASAP. This is the flock-fueled future everyone is afraid of and corporations keep telling everyone it's fine. Prove it. @ kontheinside on IG

Opus or Sonnet? Maybe that’s the wrong question. Claude is becoming more than a model—it’s becoming an AI operating layer. The real edge in 2026? Not the best model. The best AI stack.

x.com/i/article/2079…

One model, four tricks: 🎬 text → video with synced sound 🖼️ first/first+last frame → video with audio 🎤 image + audio → lip-synced clip 🎥 green-screen footage + background video → auto relight & composite 🫶Thanks @MiniMax_AI for the shoutout on vLLM-Omni! Check out our recipe to get started👇 github.com/vllm-project/v…

MiniMax (official) @MiniMax_AI

4 weeks ago

The MiniMax H3 ecosystem is growing faster than ever! ☺️ Check out Awesome MiniMax H3 Integrations - an index tracking everything built around H3, from 24GB VRAM local ComfyUI setups to enterprise-scale SGLang & vLLM-Omni serving deployments. 🔥 What’s inside: - Hardware &

36 41 484 44K 383

This weight transfer engine is native to vLLM. Any Ray-based trainer can adopt it with a single WeightSource iterator. Great work here! 🔗 vllm.ai/blog/2026-08-2…

Sumanth Hegde @sumanthrh

4 weeks ago

Excited to share our work on large-scale sharded weight transfer! We’ve implemented a native sharded weight transfer engine in vLLM and SkyRL using Ray Direct Transfer (RDT) + NIXL. We’re able to achieve weight transfer for Kimi K2 (1T params) in BF16 in 7.53 seconds on 48

3 21 104 22K 77

I HAVEN'T OPENED CLAUDE AT MIDNIGHT SINCE I BUILT THIS FOLDER I used to wake up, check what broke overnight, fix it by hand -> now the receipts are already sitting there when I wake up. dated, graded, waiting on my review what's actually inside the folder that took over the night shift: • the contract > CONTRACT.md - the shift rules, committed > contract.local.md - my personal overrides, gitignored • the harness (.claude/loops/) > settings.json - spend caps and timeouts, set once > schedule.yml - when the next shift fires > rubrics/ - code.md, writing.md, safety.md - the graders catching what I'd miss > pr-hunter/ - plan.md wakes it, act.sh does the work • the state > receipts/ - one folder per shift, 5,382 kept so far > trace.log - exactly what happened, no guessing > checkpoint.json - resumes where the last shift stopped • the edges > kill.sh - my panic file, never once used > .mcp.json - the tools it's allowed to touch the folder runs the night shift now. I just read the receipts in the morning

Mr. Buzzoni @polydao

2 months ago

x.com/i/article/2073…

14 79 618 1.4M 2K

this is seriously dangerous some random american student dropped $2,200 on an ipad and a mac mini, plugged them into his macbook three machines on a dorm desk and his roommates figured he was running a crypto farm he wasn’t he just wired up the automation and went to bed by sunrise it had already chewed through hundreds of leads, generated custom emails for every single one, and dumped everything into the crm without him lifting a finger the crew doing the same thing before him cost $7,000 every month he paid $2,200 one time there are 360 million companies on earth and millions still hand humans work the machine does cleaner, faster, and cheaper and maybe 100,000 people alive know how to actually set ai up like this

CyrilXBT @cyrilXBT

4 weeks ago

x.com/i/article/2091…

19 95 734 1.3M 2K

Palantir sells governments a war room that costs millions a year. So, a guy named Elie just rebuilt it, put it on GitHub, and gave it away. It's called World Monitor. Open it and you get a live 3D globe with 500+ news feeds pouring in across 15 categories, all summarized by AI as they land. > Military movements. > Economic shocks. > Natural disasters. > Cyber incidents. > Flight paths. > Shipping lanes. + 56 different map layers you can stack on top of each other. It scores 31 countries on a stress index and updates the number as things happen. It watches 29 stock exchanges, commodities, and crypto in one panel. It runs local AI through Ollama, so you can use the whole thing without a single API key. Native desktop app for Windows, macOS, and Linux. 25 languages. Works out of the box after one clone.

Build coding agents that learn from experience. In Building Adaptive AI Agents, you’ll turn an agent’s own traces into reusable skills and build a code knowledge graph that finds the right context where keyword search misses. Built in partnership with @Oracle and taught by Nacho Martínez (@jupiterwanderer) and Casius Lee. Enroll for free: hubs.la/Q04vlNYg0

I asked Kimi K3 to design a robot for deep sea research Here's what it came up with A jellyfish inspired robot with tentacles built from a hexagonal nanostructured lattice, designed to withstand extreme pressure.

this might be one of the most useful things I've read about AI coding agents all week everyone is building bigger and bigger memory systems but the real problem isn't that agents forget everything it's that every time you switch agents, the next one has to figure out what the previous one already learned this article explains why giving every coding agent the same second brain might be a much better idea

Rohit @rohit4verse

a month ago

switch from claude code to codex mid-task and lose nothing. move semantic state, never KV state x.com/i/article/2083…

43 32 262 330K 771

I canceled my $200/month Claude subscription because of this. GPT 5.6-Luna is practically free and they've figured out how to never hit the usage limits in Codex. It takes 3 minutes to set up. Here's how it's done: 1. Install this repository called “sol-advisor”. 2. Copy the “savings-prompt”. And that's it. Save it and give it to your agent right now.

Rahul @sairahul1

a month ago

realizing this is literally the cheat code to NEVER hitting your Claude/GPT usage limits ever again. The most valuable AI article of the month is right here: x.com/i/article/2090…

41 29 240 537K 639

call me crazy but the first AI agent most companies should build is an autonomous analyst. you can build one using Kimi K3. it watches your competitors while you sleep, remembers every move, and wakes your team with the launches, pricing changes, and positioning shifts they need to act on. don't bookmark this if it crosses your timeline. paste the full article into Kimi and tell it to build the first version for your market.

J.B. @VibeMarketer_

a month ago

x.com/i/article/2089…

15 69 482 960K 2K

x.com/i/article/2057…

ANTHROPIC LEAKED A SETUP WHERE A $1.2M A-YEAR TEAM FITS INTO ONE FILE FOR $4 A DAY you hire nobody - you write one file, and $106,500 of salaries in it turn into $4 of tokens. architect → 4 builders → tests → critic → docs → scout → chief → back into the file the architect runs twice a day and decides everything - the priciest model on the sheet is the smallest line on the bill at $1.05. four builders cost $1.20 a day - and a fifth builder is one more number in the file, not one more quarter of recruiting. the tester asks does it run, the critic asks should it exist at all - $1.22 together for two roles a solo dev never fills. nothing reaches you that hasn't been rejected at least once. the scout and the scribe cost 40 cents - the exact two roles that get cut from every real budget. nobody hires a documentation engineer, and everybody wishes they had one. the chief at 14 cents is the only one who writes back into the file - without it this is a list, with it the list edits itself. hiring the eleventh is a paragraph: no req, no interviews, no ramp - and firing is one command. save this and paste it into Claude Code - and you get 10 roles for the price of one coffee ↓

Sprytix @Sprytixl

a month ago

x.com/i/article/2086…

9 29 171 440K 743

ByteDance literally dropped a prompt guide for Seedance 2.5.