FerTech 🇨🇭

Want to play with local light AI via Chrome browser? Download this extension and download the 3GB local model when prompted, thats it. chromewebstore.google.com/detail/transfo…

JAJAJAJAJA NO HABÍA VISTO ESTO 😭😭

Imagine being able to be free to create, without any pressure to earn money...thats the point.

Cambió el pop para siempre

Over water swing on a cruise ship

@clothasub Una de las mejores escenas de Los Simpsons 😃

Otra genialidad de mi generación X… #TheSimpsons

Hi @MicrosoftTeams can you please urgently update the total number of users which can be members of a chat group? We cant add more colleagues to this regional group. Thank you!!! cc: @satyanadella

I asked Claude Opus 4.7 to analyze these tips: Mixed bag. The infographic gets the direction right but oversimplifies in a way that contradicts Anthropic's actual published guidance in two places. Here's what holds up and what doesn't, grounded in the current docs. What's correct The "no context" critique of Write me a LinkedIn post about AI is solid. Anthropic's prompt engineering guide repeatedly emphasizes that vague prompts force the model to guess everything, while specific prompts that name the audience, constraints, and definition of success eliminate guesswork. Same applies to the "make it punchier / more professional" loop — that's just deferred specification. The middle-panel idea, uploading ABOUT ME.md + ANTI AI WRITING STYLE.md + COPYWRITING.md, is the strongest claim in the whole infographic and the one most aligned with where Anthropic is actually pointing. It maps directly onto what Anthropic now calls context engineering, framed in their September 2025 engineering post: "finding the smallest possible set of high-signal tokens that maximize the likelihood of some desired outcome". The anti-style file (what you'd never say) is a legitimate negative-example technique. This is also exactly what Claude Projects, Skills, and the Memory feature exist for, which is why your fernando-writing-style skill and servicenow-product-surface-design-v1 skill work the way they do. The "stopped prompting, started operating" frame is also directionally right, though the infographic implicitly sells Cowork as the destination. The actual destination is durable context-aware setups: Skills + Projects + Memory + MCP connectors. You're already living in that world. What's wrong or oversold The dismissal of persona prompts (Act as a world-class copywriter…) is the worst part of the infographic and contradicts Anthropic's published guidance. Anthropic's documentation explicitly emphasizes that assigning a role at the beginning sets the stage for consistent, filtered responses, and in their internal contract review example, Claude without a role missed problems that the lawyer-persona Claude caught. Anthropic recommends separating persona from task: system prompt carries the role, user prompt carries the work. The actual failure mode isn't "persona prompts are bad" — it's "stacking adjectives without giving Claude info about you and your audience doesn't add signal." Those are different claims. The infographic conflates them. The "ask me clarifying questions first" recipe is pitched as a universal upgrade. It isn't. It's a coping mechanism for users who haven't done the upfront thinking. Anthropic's actual guidance leans the other way: system prompts and user prompts should be "extremely clear and use simple, direct language", with the failure modes being either over-prescriptive brittle logic OR vague high-level guidance that "falsely assumes shared context." Asking Claude to interview you can be useful for genuinely fuzzy creative work, but for any task where you already know the constraints, it just adds turns and dilutes the context window. For your style of working, where you already prefer judgment over clarification, this advice is almost the inverse of what's optimal. There's also a subtler issue: the infographic frames every problem as a Claude problem ("Claude has no idea who you are," "Claude keeps guessing"). The honest framing is that LLMs reflect what you give them. Anthropic's own framing is about treating context as a precious, finite resource — finding the smallest set of high-signal tokens for the outcome you want. That's a thinking discipline, not a prompt trick. Net recommendation Keep panel 5 (persistent context files) and panel 6 (operate, don't prompt). Throw out the persona dismissal. Replace "ask me clarifying questions" with "specify upfront, fall back to clarifying only when the brief is genuinely unclear." That gives you a version that matches both Anthropic's published practice and your own working style. For your stack specifically, you've already implemented the genuinely useful parts: Skills as durable context, an explicit voice file, brand standards, design references. The next leverage isn't more prompting tricks — it's cleaner separation between Skills (capabilities), Projects (account-scoped context), and Memory (cross-conversation continuity), which is what the Anthropic context engineering post is actually pointing at. Sources for verification: Prompting best practices, Effective context engineering for AI agents.

Prompting is dead. Here's what to actually do instead (in one image): 1. Download the Claude desktop app (free). 2. Create a folder names "Claude Cowork". 3. Create 3 subfolders: about-me, output, templates 4. In about-me, create 3 .md files: about-me, anti-ai-writing-style, my-company. 5. Fill them with your tone, rules & non-negotiables. 6. Download my files (for free) here how-to-ai.guide 7. Don't pay anything. Reply to the welcome email. 8. Open Notion link → .md files folder → download. 9. Go to Claude app → Cowork. Select your folder. 10. Go to Settings → Cowork → Global Instructions. 11. Type: "Always read about-me first." 12. Now write 1-line prompt. It already knows you. By the way, here's the red flags to know you're still prompting like it's 2025: 1. Your prompts are 500 words. Cowork needs 5. 2. You re-upload the files. They auto-load now. 3. "Act as a copywriter…" Stop. Claude needs files. 4. You created Projects. Cowork is one folder 5. No anti-AI file. So Claude sounds like Claude. 6. You re-explain your tone. Put it in a .md once. 7. Your outputs sound generic. Lack of context. 8. You blame Claude. The problem is missing files. 9. You copy prompts. They don't know your voice. 10. You think "prompting" is a skill. It's already over. 11. You never tried Cowork. The biggest feature. 12. You're still in chat. The top 1% are operating. 13. You never read this: ruben.substack.com/p/youre-just-a… People still type 500-word prompts in 2026. You want to help your network upgrade? ♻️ Repost this so they finally try Cowork.

@RoundtableSpace *just* you have been blocked for deceiving people with your posts and messaging. bye.

ANTHROPIC JUST RELEASED THE OFFICIAL PLAYBOOK FOR BUILDING A COMPANY WITH CLAUDE CODE. CEO: 1 human. Employees: AI agents. Operations: fully automatic. The zero-headcount company is no longer a joke.

@JulianGoldieSEO So now you are also Amelia, Julian?

Hermes Desktop Just Changed Everything Hermes just became way easier to use. No terminal, no complicated setup, no command-line stress. The new Hermes desktop app gives you a visual way to run a powerful AI agent. Here’s what it does: → Installs Hermes automatically. → Lets you choose OpenRouter, Anthropic, OpenAI, or local models. → Saves every chat session. → Creates separate profiles for different workflows. → Stores persistent memory. → Gives you access to 68 built-in tools. → Supports MCP connections. The biggest unlock? Hermes can learn skills from tasks and improve the more you use it.

@J_Galt_I_Am @ABC Ah, so only affects average Americans then...

@ABC Ain’t no way. People stored food until it decomposed and built up gas and then took the lid off while looking directly at it. Poses no risk if your iq is above room temp.

Thermos, the popular food and beverage insulated container company, is voluntarily recalling more than 8 million jars and bottles for injury risk after several people "suffered permanent vision loss." abcnews.link/e3XbmbO

@mrfacundo Demasiado Argentino que se la cree y encima son malas personas cuando se van de la Argentina. Tal cual.

el español tiró factos

One of the most simple and amazing things to try in Argentina 🇦🇷

May the fourth be with you

How to duplicate yourself into Claude in a weekend: (even if you've never written a prompt before) 1. Download the desktop app. ☑ Go to claude .com/download ☑ Set Opus 4.7 as default ☑ Turn ON Extended Thinking 2. Open Cowork mode. ☑ Cowork = where your voice lives ☑ Click the top left tab ☑ Create your "Voice" folder inside 3. Install Wispr Flow (it's free). ☑ Turns your voice → text ☑ Voice = faster and more honest ☑ Typing kills the truth. 4. Run the interview. ☑ Paste Prompt 1 from ruben.substack.com/p/youre-just-a…. ☑ 100 questions, 7 categories ☑ Push past every vague answer 5. Compress the dump. ☑ Paste prompt 2 from ruben.substack.com/p/youre-just-a…. ☑ 20K words → 4K tokens ☑ Save as [your_name] .md 6. Test it in a blank chat. ☑ Open a fresh Claude chat ☑ Run a prompt only you would write ☑ If it sounds like you → ship it 7. Drop it into Cowork. ☑ Move [your_name] .md into your folder ☑ Claude now reads it on every turn ☑ Every draft = your voice, automatically 8. Port it everywhere. ☑ Upload to ChatGPT, Grok, Gemini ☑ Same file = same voice in every AI ☑ Hand it to your team or ghostwriter 9. Edit it forever. ☑ Install Obsidian (free) ☑ Open Cowork as a vault ☑ Update as your taste shifts Full guide + prompts at ruben.substack.com/p/youre-just-a…. (save this to clone yourself into any AI)

I am obsessed with this Japanese man using AI video to put himself into movies (he's on IG at @ai_am_furufuru)

Hi @ottomatorAI bolt.diy under your leadership was moving. now under Bolt themselves is completely stalled. No new releases in 1 year. Are you guys working in anything similar?

Que ARTE coones.....