Codez

@w1nklerr Damn, NVDA keeps shipping crazy stuff. Real chads.

Nobody is talking about what this Nvidia laptop actually means for creators Jensen Huang walked on stage and held up the RTX Spark like it was nothing special. Full Blackwell GPU. 1 petaflop of AI performance inside a laptop. It renders, edits and runs local AI models faster than most desktop setups people have at home. You pay zero monthly fees because everything runs locally on the device. Creators who switch stop paying $300 a month in tools immediately. Video editors are already charging $150 an hour using the AI workflows this chip makes possible. At 8 hours a day that is $3,600 a week from a single laptop. Most people are still waiting 3 hours for a render this thing finishes in 10 minutes. The reaction in this clip says everything. Follow if you want to know what actually matters before everyone else figures it out.

@noisyb0y1 Obsidian looks crazy good. Will use it to power my Claude

THIS CHINESE DEVELOPER'S OBSIDIAN BRAIN MAPS EVERY CLIENT CONVERSATION - ZERO EMPLOYEES, $40,000/MONTH, CATCHES PROBLEMS BEFORE CLIENTS DO every node on screen is a conversation - green for happy clients, yellow for neutral, red for problems that need attention - the brain sees the emotional state of the entire business in real time this is not a CRM, not a dashboard, not a spreadsheet - it's a living map of every client interaction that fires connections and surfaces patterns no human account manager would ever catch when a cluster starts turning yellow the brain flags it before the client sends the complaint - when a green cluster grows it identifies what's working and replicates it across every other account automatically he replaced a $15,000/month account management team with one Obsidian brain that never sleeps, never misses a message and never needs a performance review no employees, no contractors, no standups, no payroll - just one developer, one brain and one delivery system doing the work of 10 people $40,000/month - solo - from a system that gets smarter every single conversation

@0xchromium Damn, bro, this looks really useful. Thanks for the share, bro.

She dropped her old content into a folder and Claude turned it into a month of posts old articles, newsletters, captions, emails, blog posts you forgot you wrote give Claude Cowork access to that folder and write it one prompt > every week it turns your old writing into a thread, a post, and an email > not taking from the internet, building from what you already wrote > schedule it once and it runs without you 60 pieces a week from writing you already did once workflow 2 of 6 in the article below

@defileo Wow, this is an amazing finding. Thanks for sharing, bro. Bookmarking it for myself.

🚨 One of the fastest growing GitHub repos in history just hit 66k stars. Free GPT-4o, Claude, Kimi, Gemini, DeepSeek all under one roof, that's $2,400 back in your pocket every year. One install, no paywall, no key, 66,000+ devs already know, you're still paying.

@Lummox_eth Amazing watch brother. Yeah Dynamic workflows totally changing the game !

9 OUT OF 10 CLAUDE CODE USERS WRITE 50 PROMPTS MANUALLY WHEN 1 DYNAMIC WORKFLOW DOES EVERYTHING. Claude writes its own JavaScript harness, spawns subagents with isolated context windows, and assigns different models per agent automatically. Three failure modes it solves. Agentic laziness where Claude stops at partial progress. Self-preferential bias where Claude favors its own output when verifying it. Goal drift where original constraints disappear after turn 47. 6 patterns cover every use case. Fan-out for parallel work across hundreds of files. Adversarial verification where a separate agent checks work without knowing who produced it. Tournament for ranking 1,000 items through pairwise comparison instead of absolute scoring. Three controls prevent token explosions. Explicit token budgets in the prompt.

@thejayden Thanks you Jay !

Everything you need to master Claude! Bookmark

Watch full episode at WorkOS YouTube channel: youtu.be/RkQQ7WEor7w?si…

Claude Code creator: "I don't prompt Claude anymore. I write loops - and the loops do the work. My job is to write loops." in 30 minutes Boris reveals his actual daily Claude Code setup. Claude Code + loops + dynamic workflow Worth more than a $500 vibe-coding course

@0xMoysei thanks Moysei, love your guides too. Keep pushing them

@0xCodez so cool guide

@eng_khairallah1 damn, 300 agents, for what you need that much brother ?

@Flandermaxx yeah, true, but you can use /loops for any type of your routine

@0xCodez this approach to agents is honestly such a developer move

@ridark_eth thank bro, btw are you using /loops yourself ?

@0xCodez 30 minutes of interesting listening

@YotamBlu Yeah. This is an amazing pod, worth watch brother !

@0xCodez loops are the interval training of coding. once you hit that threshold where the ai starts doing the heavy lifting and you're just directing the effort, everything changes. gonna watch boris's breakdown because that's exactly where i'm trying to get with goosenet.

@asukahaox Are you using dynamic workflow in your daily coding now ?

@0xCodez すごい！クロードコードとループを駆使したダイナミックワークフロー、その効果はおそらく＄500のバイブコーディングコースより高いんですね！

@Nikitont are you using /loops in your daily routine bro ?

@0xCodez I'll listen, thanks.

@0xRravix 100% agree on this bro !

@0xCodez Do you agree with me that Claude Cod is the best there is?

@0xMorlex Amazing share bro ! thanks for your support

Andrej Karpathy keeps repeating one idea: the gap stopped being talent. it's leverage anthropic just showed the Claude Code version of that idea: you don't need one smarter agent. you need an org of agents a real engineering pod researcher, builder, reviewer, QA, strategist costs $20,000+/m as a solo builder you can't justify that, so you do all five jobs yourself and call it discipline here's what most people miss: you don't need a team of people. you need their roles. and a role is just system instructions, context, tools, and a clear job. that's exactly what Dynamic Workflows are 6 patterns, one Claude Code setup: > classifier: figures out what kind of task this is > fan-out agents: split 50 files, bugs, docs, or claims into parallel work > verifier: checks the result without self-bias > filter: kills weak ideas before they reach you > tournament judge: picks winners through pairwise comparison > loop agent: keeps going until the goal is actually done the old move was asking Claude to do the work. the new move is asking Claude to design the machine that does the work most people are still prompting like employees. the move is being the org. watch Karpathy’s talk, then save the 14-step Claude Code setup below

@LunarResearcher you are dropping a real alpha bro ! thanks for the share

My dad showed up at my apartment. Unannounced. No text. No call. Just rang the bell at 11am on a Tuesday. I opened the door. "What's wrong?" "Nothing. I just wanted to see what you do all day." He walked in. Looked around. Saw the laptop, the second monitor, the notebooks. "Sit down. Show me." So I did. One wallet I was tracking turned $480 into $6,900 in 19 days. Another moved $5.3M in volume. One more had a 74% winrate across 214 trades. Sharpe 2.31. I didn't touch it once. He didn't say anything. "That's from a script running on a $5 VPS in Germany." "Germany?" "Cheap server. Bot doesn't care where it lives." Then I showed him the repos. All free. All public. First: github.com/warproxxx/poly… 86M+ trades on Polymarket. Every outcome since day one. Free to download. Second: github.com/warproxxx/poly… Market making bot. Both sides of the book. Google Sheets execution. Third: github.com/pselamy/patter… ML + heuristics. I fed 14,000 wallets into Claude. One prompt. 4 minutes. Found 47 traders with 70%+ winrate. Bot mirrors them with 60-second delay. He leaned back on the couch. "Show me again." I did. Three times. Then: "I'm 64. I still don't understand half of it. But I want in." I said okay. He transferred $2,000 before he left. Profile: @weatherman825?r=lunarlunar#1V6eGgd" target="_blank" rel="nofollow noopener">polymarket.com/@weatherman825… Dads don't ask permission. They just show up.

@shtanga0x @MicroStrategy @saylor amazing research bro !

Between May 26–31, @MicroStrategy sold 32 BTC at an average price of $77,135. Today Bitcoin is trading at $66,800. They probably should’ve sold a lot more than 32. That said, the timing was chef’s kiss. @Saylor knows his thrill - sold right at the local highs, just before the -10% crash. Masterful. We used to have “weekly buy announcements” from MicroStrategy and corresponding @Polymarket events. Time to launch the weekly sell market?