Ray Fernando's banner

Ray Fernando

@RayFernando1337 • 38,348 subscribers

12y ex-Apple • Building live with AI • Current Mission: 10% Body Fat

Shorts

Finally! Visual editor for your Tailwind and Next.js code. Going to try this out on my stream.

Finally! Visual editor for your Tailwind and Next.js code. Going to try this out on my stream.

138,004 просмотров

Next.js & Tailwind are all you need.

Next.js & Tailwind are all you need.

24,045 просмотров

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

Why I stopped wearing my Apple Watch as an Ex-Apple Engineer

Why I stopped wearing my Apple Watch as an Ex-Apple Engineer

1,259,200 просмотров • 8 месяцев назад

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

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

69,254 просмотров • 27 дней назад

These kids cooked a full planning system on Groq to have Richard Feynman teach you in your style. They have 17k users. Investors need to talk to these guys asap.

These kids cooked a full planning system on Groq to have Richard Feynman teach you in your style. They have 17k users. Investors need to talk to these guys asap.

1,082,438 просмотров • 1 год назад

This guy is a pro vibe coder. Ryo Lu

This guy is a pro vibe coder. Ryo Lu

383,186 просмотров • 7 месяцев назад

Cracked students build world's first (and fastest) deep research tool built specifically for learning.

Cracked students build world's first (and fastest) deep research tool built specifically for learning.

696,871 просмотров • 1 год назад

Cursor can now use Claude “computer use” to use itself. HO-LEE-FOOK 🤯🤯🤯🤯🤯🤯🤯

Cursor can now use Claude “computer use” to use itself. HO-LEE-FOOK 🤯🤯🤯🤯🤯🤯🤯

343,996 просмотров • 1 год назад

Coding Challenge: Make a dashboard from the screenshot 👉🏽 RAWDOG (no v0, no Cursor, no shadcn/ui) 👉🏽 No Previews 👉🏽 15 mins Let cook 🔥Next.js conf Vercel

Coding Challenge: Make a dashboard from the screenshot 👉🏽 RAWDOG (no v0, no Cursor, no shadcn/ui) 👉🏽 No Previews 👉🏽 15 mins Let cook 🔥Next.js conf Vercel

317,177 просмотров • 1 год назад

I think this guy single handedly unlocked Deep Research with a clean UI.

I think this guy single handedly unlocked Deep Research with a clean UI.

236,821 просмотров • 1 год назад

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.

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.

59,092 просмотров • 4 месяцев назад

The frontier of human knowledge isn’t locked behind corporate walls anymore. It’s sitting across the table from you.

The frontier of human knowledge isn’t locked behind corporate walls anymore. It’s sitting across the table from you.

64,638 просмотров • 8 месяцев назад

Claude researched sprite-making best practices. Gemini 3 Pro generated the actual pixel art. 13 cents per character. I can't draw at all but now I have full sprite sheets for my multiplayer soccer game.

Claude researched sprite-making best practices. Gemini 3 Pro generated the actual pixel art. 13 cents per character. I can't draw at all but now I have full sprite sheets for my multiplayer soccer game.

58,416 просмотров • 7 месяцев назад

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

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

42,398 просмотров • 5 месяцев назад

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

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

60,928 просмотров • 8 месяцев назад

GPT-5.2 Low just beat Opus 4.5 on a real code review. The cheapest reasoning setting caught issues the expensive model missed.

GPT-5.2 Low just beat Opus 4.5 on a real code review. The cheapest reasoning setting caught issues the expensive model missed.

48,096 просмотров • 7 месяцев назад

Everyone's spinning up 50 agents in parallel. The engineer who built Droid Missions told me the opposite: if you can't produce something large and correct with one, adding more just makes it worse. Parallelization is for gathering live info, not building systems.

Everyone's spinning up 50 agents in parallel. The engineer who built Droid Missions told me the opposite: if you can't produce something large and correct with one, adding more just makes it worse. Parallelization is for gathering live info, not building systems.

24,555 просмотров • 5 месяцев назад

Bring your own agents! Repo Prompt rides on the Claude Code and Codex subscriptions you already have, dispatches them in parallel, and shows you every prompt it sends. I have a feeling a lot of folks are going to be talking about this very very soon. 00:00 Introduction to RepoPrompt App 00:57 RepoPrompt Setup Wizard Walkthrough 03:34 Live App Refactoring Demonstration 05:03 The Scout Agent Workflow 08:38 Concurrent AI Engineer Agents 10:24 Core Benefits and Final Thoughts

Bring your own agents! Repo Prompt rides on the Claude Code and Codex subscriptions you already have, dispatches them in parallel, and shows you every prompt it sends. I have a feeling a lot of folks are going to be talking about this very very soon. 00:00 Introduction to RepoPrompt App 00:57 RepoPrompt Setup Wizard Walkthrough 03:34 Live App Refactoring Demonstration 05:03 The Scout Agent Workflow 08:38 Concurrent AI Engineer Agents 10:24 Core Benefits and Final Thoughts

18,248 просмотров • 4 месяцев назад

GLM 5.2 Easy Setup with Baseten + Droid harness. 00:00 Fastest GLM 5.2 Setup Goal 00:32 Getting a Baseten API Key 01:09 Automated Droid AI Configuration 02:23 Testing the GLM 5.2 Integration 03:07 Alternative Setups and Limitations 04:14 Bonus: Setup for Other IDEs

GLM 5.2 Easy Setup with Baseten + Droid harness. 00:00 Fastest GLM 5.2 Setup Goal 00:32 Getting a Baseten API Key 01:09 Automated Droid AI Configuration 02:23 Testing the GLM 5.2 Integration 03:07 Alternative Setups and Limitations 04:14 Bonus: Setup for Other IDEs

10,580 просмотров • 2 месяцев назад