Ray Fernando
@RayFernando1337 • 39,584 subscribers
12 years at Apple. Now building apps for a million people. Getting to 10% body fat. New on the App Store: SayRay 👉 https://t.co/YkfXIH9sJC
Shorts
Videos
I spent 12+ years building Apple products, and one thing has me looking at a Windows laptop. It's CUDA, the thing most AI tools run on. The Surface Laptop Ultra with NVIDIA RTX Spark puts 128 gigs of memory and CUDA in a bag I can carry, and the magnetic charger holds on so well I can lift the laptop with it. On paper it's a yes. I'm living on it for a week before I decide if I switch. .Microsoft Surface and .NVIDIA sent me this unit to test.
Ray Fernando124,321 görüntüleme • 5 gün önce
Why I stopped wearing my Apple Watch as an Ex-Apple Engineer
Ray Fernando1,259,520 görüntüleme • 10 ay önce
Cracked students build world's first (and fastest) deep research tool built specifically for learning.
Ray Fernando696,975 görüntüleme • 1 yıl önce
I feel burned out having to manage context for my agents/harnesses/runtimes. And what "grinds my gears" is the fact that Astra will burn through my usage simply due to loading a plethora of skills. I spent time to make sure the previous models like Sol are able to meet my production bar... As of today, it feels like I have to throw that out or manage that between two model types. I thought we had AI to help us with this? Shouldn't this be the job of the model provider especially if I use their harness? But Ray, you just have to...(do new undocumented thing) and it'll just work. BRUHHHHHH you drop models/updates every few weeks and keep changing this. Now repeat for the last 6 months... Cursor Projects just dropped their beta and I'm starting to see where the puck is going with a workflow like this. I can design what happens from PRs, bug fixes, testing, and the entire SW Dev lifecycle without living in a terminal or managing skill files. This is going to save me lots of time as my project evolves and I don't have to spend much time maintaining skill files or handing off things between agents. I can switch models and ship software like a professional. Here is my first look at Cursor Projects and I'm very bullish on where this is going. Timestamps 00:00 This Thing Called Projects 00:44 Grok Bot Went Crazy Viral 01:53 Grok Bot Forgets Sometimes 02:55 The Project Page 04:10 Agents, PRs, and Listening 06:02 The Exec Status Board 08:41 Files That Live on the Cursor Side 10:35 The Same Chat on My Phone 11:26 Still in Beta, Cloud First
Ray Fernando42,494 görüntüleme • 1 ay önce
OpenAI's $230 keyboard is addicting...and unfinished I paid for mine, unboxed it fresh, and got genuinely addicted to the joystick. Then it froze mid-demo. This is my honest first look at the Codex Micro (clicky version). The hardware is beautiful. The glow pulses with agent status, green for complete, red for error, blue for thinking, amber when it needs input. The joystick configuration screen is dangerously fun. But the software is early. Model selection fought me, I couldn't find a back button, and the device stopped responding partway through a Codex run. I share where I landed at the end, including whether I'd buy it again, plus the changes I'd make to the workflow if OpenAI is listening. The Codex Micro sold out fast and is already reselling way above retail, so consider this a look at what you did or didn't miss. Not sponsored. I paid for this myself, no coupon codes, no free units, no shill zone frfr. Chapters 00:00 A Dangerous and Addicting Keyboard 01:31 Unboxing the Codex Micro Keyboard 03:01 First Power On and RGB Glow 04:54 Interactive Joystick Configuration 05:51 Critique and UI Improvement Ideas 08:03 Major Software Bug and Device Freeze 09:03 Early Stages and Hardware Potential 10:08 Final Verdict and Future Plans
Ray Fernando70,192 görüntüleme • 2 ay önce
Cursor can now use Claude “computer use” to use itself. HO-LEE-FOOK 🤯🤯🤯🤯🤯🤯🤯
Ray Fernando344,027 görüntüleme • 1 yıl önce
I think this guy single handedly unlocked Deep Research with a clean UI.
Ray Fernando236,911 görüntüleme • 1 yıl önce
We aren't ready for this next generation of agentic engineers. 100k Github stars in 24 hours (claw-code), Yeachan Heo (Bellman) has 3 to 5 pro accounts and ships software from telegram and discord. Those who accuse these guys of AI slop haven't done their homework because the real story is wild and vastly mis-understood. Yeachan has a background in quant trading and developed agentic systems to help with research (and says that LLMs aren't good for trading). He uses the term "agentic runtime" and uses CS principles to treat skills like pointers in memory. oh-my-codex was used to make the clean room clone of Claude Code...in 2 hours...on a plane...over text!! He developed this orchestration layer for Codex and it is powerful. It covers the entire SWE workflow like pipelines, persistent memory/state MCP servers, and extensible hooks. They aren't burning tokens for the sake of burning. I highly encourage you to look at the oh my codex repo and start extracting some of the ideas Bellman uses to ship software.
Ray Fernando59,443 görüntüleme • 5 ay önce
Andrej Karpathy posted about the new programmable layer developers need to master: agents, subagents, prompts, contexts, memory, hooks, MCP. He said it came with no manual and everyone has to figure out how to hold it. This video is part of that manual. Hooks are one of the most underused features in Cursor and Droid, and they're what separate intentional AI-assisted development from hoping it works in production. After file edit: If the agent touches Rust code, hooks automatically regenerate TypeScript types for the frontend. If it touches TypeScript, ESLint runs with autofix. If it touches backend code, cargo clippy runs. On stop: When the agent finishes, it runs cargo check to validate the build before I even look at the output. 00:00 The problem: manually verifying AI-written code 00:31 Introducing hooks to automate tasks when files change 01:53 How hooks regenerate types for the frontend 02:24 How to set up the cursor.hooks.json file 04:44 Reviewing a more comprehensive hooks plan 05:48 Comparing FactoryDroid hooks vs Cursor hooks 06:45 Implementing the equivalent hooks in FactoryDroid 07:50 AI agent fixes a bug in the build command 08:27 How scaffolding makes the AI agent appear smarter 09:08 Demonstrating the successful hook implementation 09:53 Final insight: It's about providing guardrails, not a smarter AI
Ray Fernando60,928 görüntüleme • 9 ay önce
A lot of people are calling Hermes Agent the end of OpenClaw. BRUH! It's not... Nous Research trains actual models and they built an agent around that expertise. The local model routing is solid, but the part that matters for your business is that your conversations become fine-tuning data. You can train a model on how you actually work. 00:00 The Problem with Local AI Models 00:25 Introduction to Nous Research 01:04 Cross-Platform Agent Capabilities 01:44 Deep Local Model Integration 02:30 Routing Tasks to Different Models 03:06 Conversations as Training Data 03:50 Hermes Agent vs. OpenClaw 04:15 Future Plans and Series Overview
Ray Fernando42,398 görüntüleme • 6 ay önce
I’ve never learned so much from a launch video. Investors need to pull up and nerd out.
Ray Fernando18,103 görüntüleme • 2 ay önce
