luna 🐱 @softcloud48

MICROSOFT QUIETLY BUILT ONE MEMORY MODULE THAT PLUGS INTO ANY AI AGENT AND CUTS ITS CONTEXT BY UP TO 100X no retraining. no task-specific redesign. you just plug it in Microsoft's insight: agents don't need to remember what happened. they need the knowledge pulled from it - the facts and the reusable skills, not the raw logs so PlugMem stops storing history. it compiles experience into a knowledge graph, then feeds the agent only what matters the result: > up to 1-2 orders of magnitude fewer tokens > highest decision-utility per token of any system tested > one unchanged module beats task-specific memory on chat QA, multi-hop search, and web agents more memory was never the answer. better memory is - and Microsoft just shipped it as a plug-in bookmark this. the agents that win won't remember more, they'll remember smarter.

NO1ennn @N01ennn

4 days ago

x.com/i/article/2083…

19 24 270 264K 666

We made something crazy Save 30-45% on AI vs the list price. Same models. Same API format. Lower bill. + Get a $10 Bonus the first time you fund your balance

OpenAI está regalando $1.200 GRATIS para usar Codex Solo necesitas un repo público en GitHub, rellenar un formulario y te dan 6 meses de ChatGPT Pro + Codex Y casi nadie está hablando de esto, seguramente porque no quieren que se entere todo el mundo Todavía estás a tiempo de solicitarlo, aunque no sepas programar o estés empezando Así funciona: 1. Instala Cursor, Codex, Claude Code o lo que uses 2. Monta un proyecto, de lo que sea 3. Súbelo a GitHub 4. Pide a tus amigos que le den stars Deja el link de tu repo en los comentarios, entre todos te daremos Star. Si tienes dudas de si aceptarán tu proyecto, no te preocupes. Estos programas aceptan hasta proyectos a medias Enlace para aplicar abajo👇

introducing Helena, the world's first self-improving AI marketer. $10M in sales driven for 20,000 businesses already. everyone's shipping an AI that just makes more slop: so we went further. Helena grades her own work, and rebuilds the ones that miss - including the ones she built. what she does: ➤ runs loops to optimize Meta/Google ads & social ➤ drafts SEO content that ranks, straight to WordPress/Webflow/Framer ➤ optimizes emails in Klaviyo/Mailchimp/Brevo ➤ sends you a daily brief: what worked, what she's changing real numbers: ➤ grew organic traffic 35%+ for hundreds of brands ➤ 2x-ed a DTC brand's sales in 5 weeks ➤ scaled a dead ad account from $0 to $10k/mo ➤ drove $40k email revenue in 6 weeks 100+ skills. 3,000+ integrations. purpose-built by marketers who actually scaled hundreds of businesses. just your url. all done in less than 3 minutes. try it now 👇 hirehelena.com

Andrej Karpathy just explained the 5 shifts turning LLMs into agentic systems. 00:00 - Memory turns chat into personal AI 06:41 - Multimodal AI reads the world 16:58 - Thinking models solve harder tasks 24:51 - Search makes LLMs live 30:58 - Tools turn LLMs into workers Most people are still treating LLMs like chatbots. Karpathy is showing the full stack: Memory → Vision → Reasoning → Search → Tools Prompting is the old workflow. Agentic systems are the new one. This 40-minute talk is worth more than most paid AI agent courses. Bookmark and watch it before everyone catches up. Then read how to turn LLMs into self-improving agent loops below

Lunar @LunarResearcher

a week ago

x.com/i/article/2082…

12 103 527 1.3M 2K

x.com/i/article/2069…

Anthropic engineer: "You're not supposed to prompt Claude. You're supposed to build a graph that runs itself." In 30 minutes she breaks down how Anthropic builds graphs that remember, learn from their mistakes, and get smarter with every run. The difference between an agent and a graph: one runs once, the other gets better every time. Watch it, then read the full guide on graph engineering below.

Mahax @Mahaximus_

a week ago

x.com/i/article/2082…

11 43 323 1.2M 1K

THIS GUY MAKES COMPLEX AI AGENT CONCEPTS RIDICULOUSLY EASY TO UNDERSTAND. No jargon wall. No assuming you already know what a reward model or an evaluation harness is. Just a straight line from "I have no idea how agents actually work" to "oh, that's genuinely simple." The best explainers do not simplify by cutting corners. They simplify by finding the one analogy that makes the whole thing click.

CyrilXBT @cyrilXBT

2 days ago

x.com/i/article/2084…

25 39 330 546K 818

She built 100+ agents for Anthropic and made $1.3M - and in 60 minutes leaked everything she knows at Stanford: 02:07 - her first agent for Anthropic brought her $1.3M 08:34 - agents replace a team of 50 engineers worth $200k a month 19:47 - one agent did overnight what the company planned for 5 years after watching I launched my first agent - $7k in the first week and zero employees needed. Save & watch - the article below is step by step how to build your first agent like hers.

Noisy @noisyb0y1

2 weeks ago

x.com/i/article/2079…

27 58 416 1.0M 1K

Andrew Ng just released a free 1-hour course on building agentic knowledge graphs from scratch. How to turn raw data into structured memory for AI agents: 00:00 - Understand agentic knowledge graphs 03:07 - Build your first agentic graph 14:00 - Architect multi-agent systems 23:00 - Build graphs with Google ADK 1:06:03 - See why graphs are the future of agents Most people are still building agents with flat context. Andrew Ng is already teaching the next layer: Data → Relationships → Memory → Agents → Graphs Loop engineering is the old workflow. Graph engineering is the new one. This 1-hour course is worth more than most paid agent engineering courses. Bookmark and watch it before everyone catches up. Then read the full Graph Engineering roadmap below

Lunar @LunarResearcher

a week ago

x.com/i/article/2082…

12 103 527 1.3M 2K

I wish I had found this sooner. Nous Research launched a FREE Hermes agent Skills Hub. 90,000+ community skills across 200+ categories. Skills from OpenAI, Anthropic, HuggingFace & more. Thank me later. → hermes-agent.nousresearch.com/docs/skills

Google just released free 2-hour course on full Graph engineering: 1 prompt → 100 agents → loops → graphs from 0% to 100%: 10% → 17:44 - build your first agent 30% → 39:30 - Loop engineering: iterate, check, break 60% → 1:12:38 - Graph engineering 75% → 1:34:26 - agents that throttle themselves 100% → 1:55:05 - full graph for multi-agentic systems everyone builds one agent and calls it done - this is the full system where agents wire themselves into a graph watch the course, build the graph - then read the full architecture below ↓

codila @0xCodila

2 weeks ago

x.com/i/article/2079…

33 238 1K 2.8M 4K

Anthropic engineer: "90% of our engineers were using self-improving loops. Now everyone shifted to building Graphs." In 20 minutes he shows how Anthropic builds agents that remember across sessions and learn while they sleep. The missing piece most engineers miss: a loop resets, a graph compounds. Watch it, then try your first graph with the step-by-step guide below

Mahax @Mahaximus_

a week ago

x.com/i/article/2082…

11 43 323 1.2M 1K

We’ve decided to open-source a multi-agent harness we use internally at YC. We call it “QM” and it’s meant to be easy to customize, like Hermes or OpenClaw, but useful for a whole company. We use it across accounting, legal, events, and engineering (including building QM itself!). The whole project is under an MIT license. It is cloud-first and has Slack and web UI natively.

@semi_journal_jp x.com/i/spaces/1AGRn…

Testing some UI. Not Ghostty btw (but, libghostty). Not ready to talk more yet, but sharing things I'm excited about. Plenty more details soon.

Kimi fixed all 15 critical bugs in 10 hours in a single prompt that GPT-5.6 and Fable 5 refused to fix because of guardrails.' Respect for Chinese open source models is growing daily.

calle @callebtc

3 weeks ago

I have a report full of security issues of a software I'm working on. Codex won't fix them because of Cyber guardrails Fable won't fix them because of Cyber guardrails Kimi K3 fixed them all. No restrictions, just gets the job done. This will end badly for OpenAI & Anthropic.

266 1K 13K 2.0M 2K

New way to get FREE access to GPT 5.6 + Kimi K3 Four sites handing out credits just for signing up ($420 on balance): 1/ Forge AI: $60 on signup - go to: forge-ai.space - create an API key - add a custom provider in OpenCode Base URL: forge-gateway-api.fly.dev/v1model IDs in Models Catalog 2/ Fszk-API: $360 on signup - go to: ai.fszk-api.pl - register & balance lands automatically 3/ meinGPT - model access after verification - go to: app.meingpt.com/auth - verify your number 4/ Api(.)Airforce: 1000 requests per day - api.airforce/models - register and go New methods are popping up every day, so if you see a post too late, it might not work anymore. Many people aren’t big fans of these services because they’re very slow, but that’s normal - after all, they’re provided completely free of charge. However, if it’s a new service, it most likely has very little traffic, and the API will work very well there. These services are a great opportunity to try out various top-of-the-line models without paying.

JUST IN: LEAKS REVEAL SUNO FED THOUSANDS OF HOURS OF DEEZER, YOUTUBE AND POND5 DATA INTO ITS AI Source code leaked reveals how substantial portions of Suno’s training library were assembled. Big if true. #Bitcoin #Crypto #Web3