Dani Acosta

We just built the best AI Chef! 🚀 Scan ingredients, suggests a meal. If you have leftovers, it turns into dinner ✨ Everything is instant with image recognition 🧠 There are no long blogs, no ads, no scroll required to find the instructions 1 Month Free Code: “DANI2026”

@HodlReaper 316TB to store markdown? What are you storing bro? 😎

Claude + Obsidian + n8n + 316 TB storage built a private second brain that ships AI projects at $3,400 a month. Most people rent cloud space and pray the bills stay low. Data leaks. Models throttle. Projects slow. This stack runs everything local. → Obsidian vault grows without limits. Every note, dataset, fine-tune, client archive links in one graph. → Claude reads the full vault instantly through Projects and MCP. No token caps. No privacy risk. → n8n automates the pipelines. New data drops → auto-ingest → Claude summarizes and links. Nightly fine-tune jobs fire. Client deliverables generate on demand. → One ORICO enclosure starts at 60 TB. Add drives. 180 TB. 300 TB. Final setup hits 316 TB. HDDs for archives. SSDs for active models. Laptop-level speed in a desktop box. Plug, power, done. Month 1: Vault hits 120 GB. First local agent runs end-to-end. Month 2: Private dataset training. Sold one custom workflow for $1,200. No cloud fees. Month 3: Recurring retainers. $3,400. System trains, tests, and deploys while you review. Before: Scattered cloud tabs. Monthly bills. Slow inference. After: 316 TB under your desk. Full control. Zero latency. Projects compound. The second brain does not beg for API keys. It owns the data and prints the income. If this was useful - follow.

Meet Lucy 2.5, our most advanced Live AI model yet. Lucy edits videos in realtime, now with more capabilities and greater control. See how it's being used across streaming, e-commerce, advertising, and more 🧵

I spent 100 hours building with Hermes Agent made every mistake so you don't have to everything I learned, compiled into 46 minutes

I talk to engineers at other companies every day and hear the same thing: one person is 10x'ing their output with Claude but the rest of the org hasn't caught up. Watching teams adopt AI, I keep seeing the same 4 steps. I mapped them out here: Steps of AI Adoption claude.ai/code/artifact/…

I built an app that runs Claude Code, Codex, Cursor, Grok, Antigravity, OpenCode, and Pi side by side in my Mac notch. Agent finishes → notch pops. Needs approval → notch pops. One click back to that exact session. no more switching between apps.

@steipete Please dont let @LangChain join the conversation 😭

Are we still talking loops or did we shift to graphs yet?

wtf is a graph. Loops made Agent behavior programmable. Graphs make agent orgs programmable. Dynamic Agent Org is where the graph rewrites itself while the work is happening.

We just hit a weird milestone: our model became more reliable than your average home WiFi. Just like everybody else, we thought cloud inference was the obvious choice. Yet 2 days into the ACT-2 eval, our mind completely changed. If our hero @ArpitKalla didn’t cook, this video wouldn’t exist 🧵

A guy bought a $1,500 Samsung TV 3 years ago. He watched Netflix. He watched YouTube. He thought the picture looked fine. He assumed that's just what a TV looks like. His friend, a home theater installer who calibrates TVs for a living, walked into his apartment and looked at the screen for 5 seconds. "You're watching everything in demo mode. The motion smoothing is on. The eco dimmer is cutting your brightness by 40%. Your TV is taking a screenshot of your screen every 30 seconds and selling your viewing data to advertisers. And you're watching a $1,500 panel in the same picture mode Best Buy uses under fluorescent lights to make TVs pop on a showroom wall." He changed 9 settings in 12 minutes. The picture looked like a different television. The soap opera effect disappeared. The colors became natural. The TV stopped spying on him. Here's every setting he changed 🧵

ANTHROPIC AND OPENAI BOTH MISSED THIS. Someone just open-sourced one SDK that gives AI agents a mouse, keyboard, and screen across macOS, Linux, and Windows. It's called CUA. Same code drives a local VM or a cloud sandbox regardless of the OS. Your agent sees the screen, clicks, types, and runs shell commands like a real user. > Benchmark against OSWorld and ScreenSpot > Export trajectories for model training > Near-native performance on Apple Silicon No separate SDK per OS. No infrastructure headache. 100% Free. Open Source.

Synara v0.5.5 is out 🪽 🚀 Antigravity is now a first-class provider, replacing legacy Gemini CLI: models, reasoning controls, streaming, tools, plans, approvals, usage, auth, sessions, cancellation, and restart recovery 🔀 Pull Requests got faster and cleaner with shared caching, coalesced results, unified popovers, and smoother project-wide updates 📝 PR and Git diffs now use Synara’s own file headers and visual chrome instead of Pierre’s default styling 🧵 live turns now settle with the provider session, so working indicators, task cards, and file-change strips can’t stay stuck forever ⚡ chat reconciliation and event projection do less repeated work, keeping busy transcripts and sidebar updates more responsive 📁 dropped files and folders with spaces, parentheses, or encoded characters now become correct mentions in chat and Kanban 🛡️ WebSocket requests now always resolve or reject across timeouts, closes, send failures, and reconnects 🎛️ Cursor discovery failures stay isolated, preserving usable model choices instead of blanking the picker ✨ cleaner provider pickers, stable theme updates, refreshed Antigravity branding, and a broad session reliability pass

@superdoteng Love your product! But claude code keeps breaking rendering (codex is ok) not sure why, superset works just fine

Meet the new notification queue. Juggle as many chats as you can handle across Claude Code, Codex, OpenCode, Pi, and any other model or harness. This is part one of our plan to make a fleet of agents feel like one workflow.

Why do even our best AI models need tens of thousands of examples to learn skills that a human picks up in a handful of tries? Solving this problem is one of the great open challenges in modern AI. World models, which give AI an internal simulation of its environment, are one of the most promising paths forward. In this episode of Decoded, YC's @agupta and @FrancoisChauba1 discuss the intuition and math behind world models, new research, and current applications in self-driving, robotics, and more. 01:45 — What would perfect efficiency look like? 05:10 — World models in the human brain 09:20 — Control theory & the drone example 14:30 — When physics breaks down 17:45 — Chess, Go & the action space problem 24:10 — Why AlphaGo can't scale 28:00 — Monte Carlo tree search explained 34:00 — Self-Driving: state space is infinite 40:30 — Model-Free vs. Model-Based RL 44:00 — Why robotics is the hardest case 48:20 — World models that actually work 54:10 — JEPA & latent space tricks 59:00 — Open problems remaining 1:04:30 — Does this pass the squint test?

Most UI sounds still feel cheap because they’re just MP3s. built synthesised tactile feedback that generates on the fly. crisp clicks, satisfying toggles, proper error tones. 2kb. zero files. zero dependencies. cuelume-site.pages.dev

Hoy Meta comunicó oficialmente que su MCP ya está disponible para cualquiera que quiera desarrollar. La idea es que puedas hablarle con lenguaje natural a la plataforma y puedas: - crear/editar campañas, ad sets y ads - hacer reporting detallado - gestionar catálogos y feeds - correr A/B tests - revisar logs de actividad El valor deja de estar en hacer clicks en la plataforma y pasa a entender qué preguntas tiene sentido hacerse.

👀

Kimi K3 is CRAZY at frontend used about 3 vague prompts to create this site in Kimi Code

Some patterns we're seeing across our engineering clients that tell you where AI adoption is actually heading: 1. Companies are done spending blind on AI. A few months ago, most were approving unlimited API budgets for OpenAI and Anthropic with no tracking on where the tokens went. Today they're asking us to build governance layers and monitor every dollar. One client had three teams running up five-figure token bills before a single production agent shipped. Now they want dashboards that show exactly what's AI-generated, what it costs, and whether it's actually faster than adding headcount. That means more diagnostic work for us and meaningful savings for them. 2. Companies are accepting the real timeline. A few months ago, leadership expected to go AI-native over a few workshops and a handful of tool subscriptions. Now they're calling us because the codebase is seven years old and can't absorb automation without a full foundation phase first. Their developers are using AI at 60-70% adoption, but nobody's tracking what's generated vs. human-written. QA hasn't been touched. There's no governance. Going AI-native means rethinking org charts, handoffs, and process ownership across every department. Not a software purchase. 3. Companies are walking away from the big firms. The Accentures and McKinseys are all pitching AI transformations. Our clients keep showing up saying the same thing: "We paid seven figures for a strategy deck and nothing shipped." This is why firms like ours have a market. We operate at the engineering layer while having the business sense to map a process end to end, then build the agents to automate it. A year ago we had to explain this on every first call. Now prospects open the conversation with it. In the last 90 days we've taken calls with PE firms, law firms, healthcare companies, VPN providers, construction platforms, and retail tech businesses. Some are direct competitors with each other. Nearly all came through referral. AI SaaS won't transform your company. Giving every developer a Copilot subscription and calling it a strategy won't either. The only path to real operational ROI is combining a team that learns your business processes on the ground with engineering capacity to automate every manual workflow worth automating. We built Limestone Digital around this thesis ten years ago. AI made it urgent. If you're looking to transform engineering delivery or automate business processes with production-grade agents, visit limestonedigital.com.

Having fun with Claude + Kling + GPT Image 2.0 Prompt coming soon. Claude → Animations + Dev Kling → Character animation GPT Image 2.0 → Character + Textures