Dami-Defi
@DamiDefi • 98,373 subscribers
AI. Former marketing lead at global Top 100 company. Crypto since 2018. Sharing strategies that actually work. All posts are NFA | DYOR. @Bitget Partner.
Shorts
Videos
MARK CUBAN JUST NAMED THE PLAYBOOK: "Get into Claude, learn all the agentic stuff, then go after small businesses because they won't know how to do it." One sentence. The skill. The tool. The customer. People who figured this out early didn't wait for someone to hire them. They learned Claude, built AI systems that handled real business tasks, and sold those systems to companies that couldn't build them themselves. The opportunity is sitting in plain sight. Here’s the skill stack, step by step ↓
Dami-Defi75,637 Aufrufe • vor 4 Tagen
THIS IS WILD 🚨 ELON MUSK JUST DROPPED A WARNING PEOPLE SHOULD PAY ATTENTION TO: "You have at most 10 years left to make money by selling your work." His argument? AI could soon handle most economically useful tasks, making the old model of exchanging hours for a paycheck far less valuable. For roughly 200 years, the formula has been simple: Work your hours → collect a salary. That model may be entering its final chapter. And the shift toward AI-driven income could create one of the biggest transfers of wealth in modern history. I wrote a guide on how people are using Astra to build new income streams ↓ The real question: Are you still monetizing your time? Or are you learning to make AI work for you?
Dami-Defi16,686 Aufrufe • vor 2 Tagen
Jamie Dimon, CEO of JPMorgan, stood on a stage next to Dario Amodei on May 5 2026 and described building a full Treasury dashboard with Claude Code in 20 minutes over a weekend. Asset swaps. Bid-ask spreads. Investment grade analysis. Production-ready output. On his own. Anthropic launched the same tools to the public the same day. Here is exactly how to set them up and what they actually produce.
Dami-Defi292,181 Aufrufe • vor 2 Monaten
Claude Code cannot read 300 files at once. So someone built a system that lets it control NotebookLM from the terminal instead. The results are wild. Here is the full workflow nobody is talking about: The Setup → Claude Code connects to NotebookLM via a command line interface → Claude searches YouTube, finds relevant videos, uploads them as sources automatically → NotebookLM processes up to 300 sources simultaneously and returns cited, grounded answers → Everything syncs back into your Obsidian vault with passage-level citations you can click to verify Why This Changes Research Forever → No more 20 browser tabs you never close → No more copy-pasting outputs into random notes → No more hallucinated answers with no sources to back them up → 60% of citations verified as strong matches in accuracy audits - answers are grounded in real data What Claude Can Do From the Terminal → Search YouTube for relevant videos on any topic and rank by relevance → Create a new NotebookLM notebook and add 20 sources in parallel automatically → Ask questions and export cited answers directly into Obsidian with wikilinks → Set custom personas per notebook - concise, no filler, no preamble → Generate audio overviews and save them as MP3 files into your vault → Build mind maps, flashcard decks, and research dashboards from your sources → Search arXiv for academic papers and feed them directly into NotebookLM → Upload competitor blog posts, podcast episodes, PDFs, and your own vault notes The Obsidian Output → Every answer arrives with clickable citations that link to the exact passage in the source video or article → Graph view shows connections between all 20 sources and the topics they share → Q&A log tracks every question asked and the grounded response received → Source dashboard shows citation frequency, topics extracted, and which questions each source answered Use Cases Worth Building Today → Academic research with arXiv papers, full citation traceability → Competitor analysis from their YouTube channels and blog posts → Company knowledge base for onboarding, new employees ask NotebookLM instead of interrupting teammates → Podcast research, feed 4-hour Lex Fridman episodes and ask what's new in AI this week → Personal second brain, 300 daily notes uploaded and queryable in one notebook Before this system existed you needed 20 tabs, hours of manual reading, and no guarantee the answers were real. Now you type one prompt in the terminal and Claude does all of it for you. The research stack of 2026 is not a browser. It is a terminal connected to everything
Dami-Defi252,693 Aufrufe • vor 3 Monaten
5,000 notes in Obsidian and none of them producing anything Most notes never get used. Not because the information was not valuable. Because every note-taking system optimises for capturing and ignores using entirely. Someone built a five-workflow Obsidian system designed from the opposite end. The contribution rate compounds from the first processed note. Here is the full build nobody is talking about. AI IS TURNING OBSIDIAN INTO A KNOWLEDGE ENGINE. Not because it captures better. Because it retrieves better. The average person has valuable insights buried in thousands of notes they never revisit. Claude changes that. It finds forgotten connections. Surfaces relevant context. Builds decision briefs. Generates writing from accumulated knowledge. The result: Less searching. More thinking. The future of note-taking isn't saving information. It's activating it.
Dami-Defi70,601 Aufrufe • vor 3 Monaten
Most people start Obsidian the wrong way. They import 10,000 notes. Build 50 folders. Install 20 plugins. Then quit a week later. If I had to restart Obsidian today, I’d do the opposite: • Start with 5 meaningful notes • Create ZERO folders • Ignore plugins completely • Focus only on connecting ideas That’s the real unlock. Obsidian isn’t a notes app. It’s a personal internet for your mind. The magic happens when you use one simple prompt: “This reminds me of…” A quote links to a book. A book links to a song. A song links to a memory. A memory links to an insight. That’s how real thinking compounds. The goal isn’t collecting information. It’s building connections your brain can return to later. AI can summarize notes. But only YOU can create meaningful links between ideas. That’s where the leverage is. Follow Dami-Defi for more AI alpha.
Dami-Defi71,024 Aufrufe • vor 3 Monaten
Life after realising you've been wasting money monthly on five tools that do not talk to each other That is five locked rooms. This is what happens when you actually move everything into Obsidian and let Claude reason across all of it. A completely rebuilt research system. Realising you have been paying $30 a month for five tools that do not talk to each other while one Claude subscription does all of it in a single vault.
Dami-Defi42,343 Aufrufe • vor 3 Monaten
YOUR AI IS FORGETTING EVERYTHING YOU TAUGHT IT YESTERDAY. That is why most outputs still feel generic. The people getting real leverage in 2026 fixed this with one setup: Obsidian + Claude Code. Obsidian stores your thinking. Claude Code reads the patterns. Your notes become permanent context the agent can access anytime: Daily thoughts. Projects. Ideas. Contradictions. Questions you keep returning to. Then the real unlock: Custom slash commands. `/context` loads your recent thinking instantly. `/emerge` finds hidden ideas across your notes. `/challenge` tests your beliefs against your past writing. `/trace` maps how your thinking evolved over time. One critical rule: The AI never writes to the vault. You write. The agent reads. That is what keeps the system valuable. At first it feels like note-taking. Eventually it feels like a second brain.
Dami-Defi41,299 Aufrufe • vor 3 Monaten
I had done the research that told me not to enter the trade. I entered it anyway. Not because I had not read the research. Because I had not read it immediately before entering. Six months of journal entries and one Claude analysis to find that. Here is the full setup.
Dami-Defi29,191 Aufrufe • vor 2 Monaten
EVERYONE HAS BEEN TALKING ABOUT AI AGENTS. BUT THE REAL UNLOCK ISN'T BETTER PROMPTS: IT'S BETTER LOOPS. Everyone is chasing the perfect prompt. The top AI engineers are chasing something else: loops. Instead of chatting back and forth with AI, they give it one goal and let it continuously improve its own work until the objective is met. Here's the framework: • Define the goal once • AI discovers the work required • Specialized agents tackle tasks in parallel • A verification agent checks the results • If the goal isn't met: loop again. If it is: deliver. The key ingredient is memory. Each cycle remembers what was completed, what failed, and what still needs work, so every iteration gets smarter instead of starting from scratch. There are two approaches: • Open loops: Maximum autonomy, but higher token costs as AI explores freely. • Closed loops: Clear boundaries, defined success metrics, lower costs, and far more practical for everyday workflows. Don't ask AI to complete a task. Build a system where AI can plan, execute, verify, remember, and repeat until the task is actually finished. Prompt engineering got us here. Loop engineering is what takes AI from assistant to autonomous teammate.
Dami-Defi13,354 Aufrufe • vor 2 Monaten
You need to try Hermes RIGHT NOW. OpenClaw was the breakthrough. Hermes feels like the evolution. Here’s why AI power users are quietly switching: • Hermes learns from you over time • It creates its own reusable skills • Memory stays curated instead of bloated • Agents improve every 10 turns automatically • It actually feels stable on day 30 The wildest part: Hermes agents build workflows from your behavior. One user asked their agent to configure Twingate once. The agent: → learned the process → created a reusable skill → stored it for future tasks → improved its own workflow automatically That’s not prompt engineering anymore. That’s agent evolution. Meanwhile most people are still babysitting broken OpenClaw setups and manually importing marketplace skills. Hermes took a different path: Less clutter. Less tweaking. More autonomy. And it’s working. It already flipped OpenClaw in OpenRouter token usage and became one of the fastest-growing AI repos on GitHub. The bigger shift: We’re entering the era where the model matters less than the harness around it. GPT-5.5, Grok, Qwen: They’re already powerful enough. The real edge now is: • memory systems • self-improvement loops • skill creation • agent orchestration Hermes understands that. Most people still think AI agents are glorified chatbots. The people using Hermes are building AI teammates.
Dami-Defi17,062 Aufrufe • vor 3 Monaten
Most teams deploying AI agents test whether the model produces the right output. Nobody is testing whether it has the right permissions, the right audit trails, and the right escalation paths when something goes wrong. The ones who run this free 45-inspection diagnostic before shipping will know exactly where their governance layer is missing before it surfaces as an incident, a lawsuit, or a regulator's question. The gap is getting obvious fast.
Dami-Defi14,813 Aufrufe • vor 3 Monaten
THIS META ENGINEER SPENT 6 MONTHS IN CLAUDE CODE... AND HIS BIGGEST BOTTLENECK ISN'T WRITING CODE ANYMORE. It's reviewing AI-generated code. Key takeaways: • Start every feature in **Plan Mode**, not Edit Mode. • A clean `CLAUDE.md` is your AI's operating manual. Keep it concise. • Validation loops > better prompts. Give Claude ways to verify and fix its own work. • Fresh context beats bloated context every time. • Run multiple Claude instances in parallel instead of waiting on one. • Let Claude manage its own rules, skills, commands, and workflows. • MCPs are powerful, but only install what you actually need. • The best AI engineers aren't faster typists. They're better context engineers. The biggest shift: You're no longer programming the computer. You're programming the AI that writes the software. If you're serious about AI coding in 2026, this is one of the most practical breakdowns you'll watch. It goes far beyond prompts and shows how elite engineers actually structure their workflow. Video cred: John Kim (Youtube)
Dami-Defi11,779 Aufrufe • vor 2 Monaten
The CEO of Anthropic just said we are 1 to 3 years away from AGI. On camera. With 90% confidence. Almost nobody watched it. INSTEAD OF ARGUING ABOUT AI TAKING JOBS. Spend 2 hours watching the CEO of Anthropic explain exactly when and how it happens. The AI compute arms race just got a reality check nobody expected. Dario Amodei, CEO of Anthropic just did the math out loud: → Revenue growing 10x per year means $100B by end of 2026 and $1T by end of 2027 → At that trajectory you could theoretically buy $5T in compute over 5 years → But if revenue comes in at even $800B instead of $1T, bankruptcy. No exceptions → And if growth slows from 10x to just 5x per year, the entire model collapses by one year This is the most honest thing anyone in AI has said publicly in years. The companies building AI infrastructure are making trillion-dollar bets on growth curves that have never existed before in history. One year off. One multiplier wrong. The whole thing unravels. The AI compute boom is real. The risk underneath it is equally real. The question is not whether AI is the future. It is whether anyone can survive long enough to get there
Dami-Defi16,105 Aufrufe • vor 4 Monaten
$ONDO RWA tokenization numbers are absolutely insane right now! → Tokenized market cap just crossed $4.43B - adding $2B+ in a single month → +236% growth in tokenized market cap over 8 months → Tokenized equities holders up +276% in just 20 weeks, now at 44,930 holders → Number of tokenized companies up +149.5% in 4 months → Weekly lending supply hit a new ATH of $65.07M this week Are you paying attention yet?
Dami-Defi14,411 Aufrufe • vor 3 Monaten