Mindwise

@denk_tweets @beehiiv Thank you Tyler for the new MCP to Claude Code. Can't wait to test it. What else should I ask for? ;-)

@mindwise @beehiiv coming soon, hang tight

in the past week alone, we shipped: On-Demand Ads — premium sponsorships, available on your schedule. No more waiting. Automations v4 — more triggers, built-in testing, smarter analytics, end-to-end visibility. Recurring Email Series — automate your newsletter on a set cadence. Set it once, done. Free Digital Products — create $0 lead magnets instantly. No Stripe required. full speed ahead.. lot more coming 😈

@claudeai By the end of the video, I'm just thinking: "Are you f-ing kidding me? Wow!"

You can now enable Claude to use your computer to complete tasks. It opens your apps, navigates your browser, fills in spreadsheets—anything you'd do sitting at your desk. Research preview in Claude Cowork and Claude Code, macOS only.

@OneManSaas @claudeai Agreed. I setup an entire system on notion where “claude Imac” can speak to “claude macbook”. Eventually moved away from it and login remotely for imac projects. But “they” still share notes when i want to sync our process. I’m sure there is a better way but it works. :-)

@claudeai Local storage is great until you're switching between three different machines daily. The "everything stays on your computer" approach breaks down when your work doesn't stay in one place.

Projects are now available in Cowork. Keep your tasks and context in one place, focused on one area of work. Files and instructions stay on your computer. Import existing projects in one click, or start fresh.

@denk_tweets @beehiiv I'm happy to test a beta! Ty!

@grok @osrt91_x_social Getting API errors with Opus but switching to Sonnet 4.6 is fine. But I'm a little nervous. Sonnet be like ...

@osrt91_x_social Hacı, evet Claude Opus 4.6'da elevated error patlamış az önce, status.claude.com'a göre 19:47'de tespit edip 20:02'de fix atmışlar, şimdi monitoring. Senin için de çöktüyse 5 dk bekle düzelir (özellikle free tier'i vuruyor). Grok'la devam edelim mi yoksa? 😎

Claude opus 5 mi geliyor ne?

@andreastzav @bcherny Voice for input but text is faster from Claude. Might be better in some cases though.

@bcherny Voice mode is much slower than typing - for me at least

Update: this is now rolled out to 100% of users

@Heyrohanislam Claude

In 2026, Claude is my operating system. After 300+ hrs, I built the full blueprint: → Claude Projects + Code + Cowork → n8n MCP + SEO MCPs → Opus 4.6 + Skills Blueprint Agencies charge $5K–$10K for this. Free for you. If you want it: Like + comment “Claude” I’ll DM you the details.

@trq212 @bcherny Amazing. I've been waiting for this. Ty.

Today we're launching local scheduled tasks in Claude Code desktop. Create a schedule for tasks that you want to run regularly. They'll run as long as your computer is awake.

@NotionHQ I connect Claude Code to Notion for a huge amount of work per day. It has been tremendous! The only problem: Claude's Notion MCP requires Claude to restart a lot. Is that a Notion thing or a Claude thing? Or does anyone have a fix? TY! (Notion AI agents is on my ttd list!)

Not every task needs the same model. A quick summary doesn't need the same horsepower as a deep research question — and it shouldn't cost the same either. Now, you can now easily compare models for your Custom Agent on speed, intelligence, and cost 🫡

@AlexFinn If you are not running Llms locally, you don't really need this much power, so you?

Apple just won the AI war They announced the MacBook Pro M5 Max What would have cost $40,000 to do with Nvidia chips, now costs $3,000 with a laptop • 4x faster AI speeds • Up to 128gb of unified memory • Frontier intelligence on the go The biggest complaint about Apple before was their AI speeds You get insane memory to run big models, but the inference was super slow Not anymore Apple played the long game by not spending trillions on AI researchers. They decided to just focus on building the best AI computers possible That strategy worked. It's over.

@aryanXmahajan Your post right here would make my Claude say I've hit my token limit for this conversation. Okay kidding but it sure feels like that. Projects, Skills, no trick that I can find stops token limits hitting at any time. Shame.

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

@tomcrawshaw01 I don't know how you do it. I load a claude skill or project with a few .md files, maybe some code, and the conversation runs out of tokens stupidly fast. Maybe a .csv file with 50 rows of data. It's pretty worthless. I've rewritten my project "bibles" way down. nothing helps.

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

3/ ... placeholders and 6 other errors. It was basically garbage. When through 6 tries with ChatGPT. Finally gave up. Claude Code and Claude Skills seem only to be for programmers, of which I'm not. Too bad. I'm disappointed.

2/ ... to a google sheet. It's own built-in connection to my google drive is all setup - yet it returns old data. It claims the data is "cached" ... but I don't believe it. Finally turned to ChatGPT who rewrote everything. It said Claude's skill.md was mostly ...

@Claude_Skills @claudeai Claude skills just doesn't work for me. First, Claude had literally no idea how to set it up. I got it documentation and it failed repeatedly, including struggling to get the headers correct. All I'm trying to do is have claude reliably connect ...

@aryanXmahajan Factory

Nano banana + n8n + Claude = AI Ad Factory This system pumps out TikTok/FB/IG static ads on autopilot using Google's new image model... - No writers. - No strategists. - No $15K+ monthly content teams. Just endless, high-converting content at scale. Perfect for e-comm operators & creative agencies. Here's how it works: → Upload business context into intelligence engine → n8n pulls audience psychology & brand voice patterns → Claude generates content variations across platforms → Auto-formats for LinkedIn, Twitter, newsletters, YouTube → Applies psychological triggers & engagement hooks → Logs performance data back to system for optimization Built with Google's Nano Banana image model. Runs 24/7 without supervision. Perfect voice consistency every time. Want the complete system? Like + comment "FACTORY" + repost, and I'll DM it to you. (must be following)

@david_is_boring @samruddhi_mokal It is an illusion. Unstable or doesn't connect at all.

@samruddhi_mokal This is such an extreme exaggeration. I hate this. Click bait type post. The claude canva. mCP is not a game changer.

Claude + Canva MCP just changed the design game forever. I can now create, edit, and manage unlimited Canva designs using plain English commands through Claude. No more clicking through menus. No more design bottlenecks. Just natural conversations that become professional visuals instantly. Here's what this integration does: → Generate designs from simple descriptions using AI → Search your entire design library with natural language → Export designs in any format automatically → Import designs from URLs without manual uploads → Get design content and pages through conversation → Create folders and organize assets by talking to Claude → Comment on designs and manage collaboration → Upload assets from URLs with voice commands → Move items between folders through chat → Check export status and formats automatically Perfect for agencies managing hundreds of designs, content creators with tight deadlines, and marketers drowning in design requests. While others spend 30 minutes navigating Canva's interface, you'll create, edit, and export professional designs in 30 seconds through simple conversations. Want the complete setup? Comment "CANVA" + RT + Like I'll DM you the full MCP integration guide (Must be following so I can DM) Skip this and keep wasting hours in design software.

@samruddhi_mokal Claude will not connect to Canva nor Notion for me. It says it is connected to my Google calendar but when it can't read it, it lies and gives a fake schedule then eventually admits it. How can I possibly trust it with my gmail? Anyone else having these problems?

Checking out Agent Opus. Pretty cool shortcut to creating your own AI agents. opus.pro/agent?ref_id=A…