Beja

We built a Claude Code plugin that teaches you to code while you vibecode. No courses. No tutorials. No prior experience. Just build your project, CodeSensei explains what's happening in real-time, quizzes you, and tracks your progress with a belt system (White → Black) Free. Open source. 🥋 github.com/DojoCodingLabs…

Analizamos 300,000+ votos en Tomatometro.com El hallazgo más incómodo: @ClaudiaDobles y @aramosc comparten el 80% de sus votantes. No están sumando contra el continuismo. Se están devorando entre ellos. 🧵 Les explico qué encontramos (y por qué importa):

@sam_starkman @AlexFinn Answer is git worktrees

@AlexFinn How does Claude Code handle parallel edits to the same repo when you use multiple terminals?

Sunday evening. 5:30pm. 3 Claude Code terminals. 5 cloud agents. All building an autonomous agent platform that will take care of half my work for me. If you're not spending your entire weekends building please unfollow me.

“I think programming as we know it is dead, and that's a good thing. I think creation, as we haven't known for a great many years, is more alive than ever.” Railway Founder is spot on, creativity is the last leverage humans have… for now

Posted on LinkedIn about Claude Code and Opus 4.5… got bombarded with the same old “AI is for POCs” talking point Normies are cooked

Not sure how sustainable @AnthropicAI 's $200 Max Plan is. Last 7 days I have consumed close to $1k in tokens, without a single limit blocker. Are we in the golden age?

@Mho_23 GUIDE

nanobanana pro, gemini 3, sora 2 these tools let you create AI video ads for literally anything physical products, digital products, info, saas, consumer apps this video cost me $0.15 to make i put together the full guide on how to do this: >best prompting frameworks >how to combine nano banana pro + gemini 3 + sora 2 for insane results >how to show multiple screens/angles of your app in one video like, rt + reply 'GUIDE' and i'll send it to you (must follow so i can dm)

Blockchain Jungle 2025 was incredible for Dojo Coding Our booth stood out, our community showed up, and we made serious moves in the LATAM Web3 space. Here's what went down 🧵

@MiDatoPay @cavosxyz @StarknetFndn @crecimientoar @ilustracianas Felicidades chicos! Fue un gusto conocerlos

🚀 We’re excited to share some amazing news! MidatoPay won 3rd place at the Starknet Hackathon, among 1,400+ projects worldwide 🌍 Huge thanks to @cavosxyz @StarknetFndn @crecimientoar for the support and trust throughout the process. Design by @ilustracianas midatopay team

@aryanXmahajan Go fully custom with Claude Code

i've been running my entire business from Claude Projects for 4 months and just hit a fundamental architecture problem THIS IS ONLY A PROBLEM IF YOU'RE MOVING AT BLITZ SPEED if your identity and business are relatively stable this won't apply to you i use Claude Projects for everything - strategy work, content engines, proposals, SOPs, client delivery, the whole operation runs through it the setup works because i have context-engineered files sitting in the project that know everything about my business, my ICP, my positioning, my current deals, my content strategy, all of it this is incredibly powerful because it gives EVERY NEW chat i open an excellent starting point relative to context and completely bypasses me having to re-explain myself over and over again but here's where it breaks — my business_profile file says i have 35K LinkedIn followers, but i'm at 40K now - the CURRENT chat i'm in knows this because i mentioned it, but what about the next chat i open tomorrow? i'm working with outdated memory which defeats the entire point now you might say "just update the file bruv" but here's what you don't understand - when you're moving at velocity EVERYTHING changes constantly my ICP shifted this month, my positioning evolved three times, my deal sizes jumped 10x in eight weeks, my content strategy pivoted twice, my authority level changed completely if i have to manually update five or six context files every week to keep them current i'm spending hours on AI maintenance instead of actually building, the tool meant to REDUCE friction is now CREATING friction but it gets worse Claude recently launched MEMORY which is supposed to "eliminate the need to re-explain context and keep complex work moving forward" - supposed to solve this exact problem except there's a CORE ARCHITECTURE FLAW in how it actually works here's the priority hierarchy: 1. Project Knowledge files (static, manually updated) 2. Automatic Memory (dynamic, invisible) 3. Current conversation context see the problem? #1 OVERRIDES #2 even when #2 is more current so even if Claude's automatic memory knows my follower count is 40K now, the static file that says 35K takes priority and every new chat loads the outdated info first the system is inherently flawed and working AGAINST blitz scalers because it assumes your identity is relatively stable, your business evolves slowly, you want consistent context, and manual updates are acceptable overhead this is optimized for the 90th percentile user - someone in the same role for 2-3 years with stable company context, predictable workflows, monthly updates are fine NOT for operators whose positioning changes monthly, deal sizes jump 10x in weeks, strategies pivot rapidly, manual updates are friction they can't afford, and daily context shifts are the norm and the INCENTIVE STRUCTURE for managing chats is completely broken too your options are: keep old chats to preserve memory summaries but have a cluttered workspace, or delete old chats to stay clean but lose context entirely - you're punished either way here's the paradox in two scenarios: if you DON'T update files manually - your files say outdated info, reality has moved forward, every new chat loads stale context, you correct it manually every time, friction is HIGH if you DO update files manually - you're editing files weekly, updating your ICP monthly, keeping methodology current as you evolve, maintenance overhead becomes UNSUSTAINABLE at velocity so the files that are meant to REDUCE friction end up CREATING friction for fast movers because static storage can't keep up with dynamic reality this is a genuine architectural limitation what high-velocity operators actually need is temporal awareness where the system knows context from different time periods and old info doesn't override new info, self-correcting architecture where one correction propagates everywhere without manual file editing, velocity matching where the system adapts to your rate of change, transparent control where you can see and edit what's stored, and context compression without information loss where old chats can be deleted but key facts persist none of this exists in Claude's current architecture i don't have a solution to this, i'm just documenting what i'm seeing because if you're operating at velocity you've probably hit this too, and if you haven't hit it yet you will the faster you move the harder you'll hit it and right now there's no clean way around it just thought this was worth sharing

The @tether WDK was just released and it's looking promising. To celebrate, we are teaming up with @avax, @AvaxTeam1 and @BChainJungle to organize a Hackathon for payment apps. Blockchain Jungle is a massive tech conference with over 6k people coming together in Costa Rica.

@tomcrawshaw01 SKILL

Writing viral posts will never be a struggle again... I packaged every context file, example, and framework that got me 4.5M+ impressions into one Claude skill. Just upload it to your project and Claude instantly references: - 20+ tweets with 100K+ views each - Proven hook formulas - Writing principles that actually work - Real feedback on what converts (and what flops) Most people prompt Claude with zero context and wonder why their posts sound generic. They're basically asking it to write blind. This skill changes that completely. You upload it once to your Claude account and it becomes part of Claude's memory. Now when you say "write a post about X," Claude pulls from battle-tested patterns. - It knows which hooks are overused and market-fatigued. - It understands how to structure posts for maximum engagement. - It references actual examples that crushed it. The skill teaches Claude to write posts that actually convert, and it never runs out of fresh angles. Claude gets better the more you use it together, because you can keep adding to the skill over time. This is the new way to add context to AI. No more copy-pasting examples into every chat. No more re-explaining your style from scratch. Follow + comment "SKILL" and I'll DM you the file

@cavosxyz @Starknet Aegis is the way 🙌🏼

Bring more users to @Starknet

De las personas más "ethereum aligned" que he conocido y un enorme factor en mi introducción al mundo Web3. Que grande @AndyGuzmanEth, muchas felicidades mae! Huge win para ethereum, el futuro de la privacidad y para el ecosistema en Costa Rica. 🇨🇷

@ethereumfndn @barinov @AndyGuzmanEth Well deserved!

We are excited to welcome @barinov to lead Privacy @ the Ethereum Foundation, and @AndyGuzmanEth as the new lead of the PSE team. Privacy is normal.

@Fricoben @thenetworkstate You’ll crush

Today I take a plane to @thenetworkstate to build the ultimate AI SEO Agent MRR sits at 198$ after we voluntarily divided it by 5 (for our repositioning) Feels scared and excited to start everything from scratch again :)

@0xVato Grande crack

Aca nos rifamos con los real builders!! 😎🫡

At @Dojo_Coding we don’t just market to CT, we go where builders actually are. Region-specific marketing campaigns let us reach talent at scale and bring new developers into web3. Distribution is king. Always has been. 70% of spots filled in 48h, before this tweet was made.

All eyes are on Argentina for crypto talent this Q4. 🇦🇷 That’s why we’re teaming up with @StarknetFndn to launch a program designed to turn builders into founders. Bootcamp. Hackathon. Co-working. Road to a Startup House during DevConnect. 90 days → Founder. Free. 500 spots.