Software Engineer - YouTuber - AI Enthusiast

Dubai, UAE
Joined August 2018
Speed is a creator's biggest competitive advantage. Moving fast wins deals other creators lose to slow email chains.
95
Honestly, this is a pretty useful update if you’re already building on Google Cloud
We’ve added a new way to access Claude on Google Cloud. You can now use the full Claude API from your Google Cloud account, including Claude Managed Agents, code execution, Opus 5.5 fast mode, and new features as they launch.
2
195
Here’s a complete Cursor 3.0 course from beginner to advanced. I’ll show you how to set up a project, prompt effectively, use Plan and Debug modes, work with multiple agents, review changes, and choose the right models. Then we’ll move into cloud agents, rules, skills, MCP servers, plugins, side chats, and automations. Timestamps: 00:00 | Cursor 3.0 Course 00:51 | What is Cursor? 02:10 | Cursor Setup/Download 02:50 | Pricing 03:43 | Major NEW Changes 05:40 | Cursor UI Walkthrough 08:00 | New Project Setup 09:10 | Prompting Best Practices 10:10 | Wispr Flow 12:46 | Plan Mode 15:16 | Agent Use/Build 18:23 | Model Selection 21:00 | Reviewing Code 26:56 | Cursor Browser + Design Mode 29:10 | Parallel Agents & Subagents 35:50 | Cloud Agents - Environment Setup 42:25 | Precise Edits, Quick Edit, and Tab 45:22 | Rules & Skills 48:18 | MCP & Plugins 49:51 | Sidechats 51:06 | Automations
1
6
316
A full Claude Cowork tutorial on building an AI assistant that can take repetitive work off your plate 👇
If you’re not sure what Claude Cowork is for, this video will clear it up. We’ll look at how it compares to Claude Chat and Claude Code, how it works with your files and browser, and where projects, skills, connectors, and scheduled tasks fit in. By the end, you’ll know when Cowork makes sense and how to use it for real workflows. Timestamps: 00:00 | What is Claude Cowork 00:25 | Requirements 01:45 | How to Use Cowork 02:55 | Cowork/Chat/Code 05:20 | Simple Demo 08:05 | Cowork Sessions/Project 10:25 | Browser Use 16:30 | Skill Building 19:54 | Scheduling Tasks 22:34 | Connectors
1
2
13
621
If an agency only steps in when a contract hits the inbox, it is waiting until the very last step of the process to provide value. Real management gets involved upstream, in the content itself.
5
460
Why your local LLM can still be slow even when the whole model fits in memory
5
1
11
1,168
Imagine if they’d called it Clawdbot 😄
We’re opening a research preview of Claude Duet, a new app where Claude works as a proactive agent. It comes to you with what needs your attention, completes tasks you ask of it, keeps working when you step away, and checks with you before it acts on your behalf.
3
483
I gave up gaming for 6 months in college to find out if my YouTube channel was a real business. I needed to know if I was actually building something, or just wasting four years pretending.
3
5
503
I wanted to leave university with more than an idea I'd never tried. I could've spent years saying, "I think this could work." I wanted to know.
1
1
34
If you have a genuine doubt about whether an idea can work, go all the way in and find out. But if you are going to half-ass it, do not bother. Half-effort just leaves you with an unfinished project and months of wasted time.
1
35
Most creators have no idea how dirty talent agency contracts actually get until they try to read the fine print. When we look through standard agreements from traditional agencies, the same three traps show up constantly: 1. They lock you out of your own inbox. The agency sets up a business email under your name, but refuses to give you the password. You never see what sponsors reach out, what rates get quoted, or what deals die behind the scenes. 2. They quietly steer your sponsors to other clients. A brand emails wanting to book you specifically. The agency goes behind your back, tells the brand you are "unavailable," and pitches a larger creator on their roster instead so they can take a bigger cut. 3. The perpetuity tax. If you leave, they demand a 20% cut for the rest of your life on any brand you worked with while signed, even if you built that relationship five years before you ever met them. When we started Kernel, we built the entire model around doing the exact opposite: - Every creator has direct login access to their inbox. - When we reply to an inbound brand, we reply under our own name as your agent, so you see every quote in real time. - If a brand reaches out for you, that deal stays with you. Period. - If you leave, we only take a fee on active contract renewals we negotiated. Everything else is yours. Talent management should protect your time, not trap your business.
1
3
350
Finding the bug is one thing. Tons of small business sites haven’t touched their PHP in years and nobody’s around to update them. That’s the real long tail.
OpenAI models helped researchers—operating as part of our Patch the Planet initiative—discover critical security flaws in PHP, an open-source programming language used to run an estimated 70% of websites. Over the past two months, we led a coalition of maintainers, researchers, and security providers to prepare fixes and protections ahead of disclosure. This duration was necessary because the fix was quite intricate and required a major change to the PHP engine. Every site using PHP can now safely upgrade their version to stay secure, in addition to applying mitigations from various security vendors. Due to the severity of these flaws and PHP’s widespread use, we consider this bug to be one of the most impactful vulnerabilities in recent memory. It also marks a new phase, where AI can find security bugs with internet-scale impact. This is an example of the Defender’s Window in action: to our knowledge, frontier AI was able to find this vulnerability ahead of attackers, giving defenders time to prepare. openai.com/index/coordinated…
Readers added context they thought people might want to know
Wiz Research wasn't the first one to discover the exploit. An independent researcher first discovered it: x.com/calif_io/statu…
3
506
Here’s how to use Claude Code to build an AI app that works with real data. We’ll take 40,000+ Hacker News job posts, use AI to extract skills, salary, seniority, and remote policy, then turn all of that into a deployed web app you can query in plain English. Let me show you the full process from raw data to a live URL. Timestamps: 00:00 | Overview/Demo 01:07 | The Plan 02:26 | Plan Mode - Claude 04:41 | Connecting to Databricks 07:31 | Adding AI Skills 08:00 | Handling The Data 09:22 | AI Analysis 11:20 | Building the App 12:28 | Deploying the App
3
2
15
1,215
Grok Bot can now build pages for you!
Grok Bot can now build reports, memos, and dashboards. Ask Bot for a page, then edit it together or have Bot keep it up to date.
1
1
4
449