J.R. Clubb 🐉

@luisgarau_ It's still not you? It's Slop. Stop. Just post the selfie, not the creepy clone.

Pasé de la imagen 1 a la imagen 2 con este prompt: (Úsalo para cambiar tu vieja foto de perfil) 1. Hazte un selfie con buena iluminación 2. Abre Gemini y activa Nano Banana 2 3. Carga tu selfie y usa este prompt: "Toma la imagen que te adjunto como referencia facial exacta y crea un retrato editorial hiperrealista estilo estudio profesional. – Iluminación de estudio suave con key light lateral y light fill tenue. – Claroscuro lateral sutil para separar del fondo. – Fondo negro uniforme sin textura. – Plano medio (cabeza y hombros), mirada directa. – Piel natural con detalle realista, sin efecto plástico. – Corrección de color neutra. – Nitidez alta en los ojos. – Profundidad de campo corta. – Estilo fotografía de retrato contemporánea. – Óptica equivalente a 85 mm. – Alta resolución. – Proporción 4:5. Prompt negativo (importante): – No caricatura. – No estilo pintura. – No piel falsa. – No deformaciones. – No brillo artificial. – No fondos visibles. – No sonrisa exagerada." 4. Ajusta hasta obtener la luz deseada Pruébalo y vuelve para enseñarme los resultados. ¿Te atreves a compartir en los comentarios la imagen que has conseguido?

@truechatdata @Suryanshti777 Stop with the AI, bro.

@Suryanshti777 That jump from PDF to structured knowledge base is where these workflows get practical. The useful part is being able to trace each extracted idea back to the source page later, otherwise the knowledge base turns into a very confident black box.

This is insanse🤯...this might kill how you read books forever. Someone built a script that reads entire PDFs for you… and turns them into a structured knowledge base. Not summaries. Actual extracted knowledge. Drop any book → run once → get: • key ideas extracted page-by-page • noise skipped (TOC, index, fluff) • clean Markdown summaries • a growing, reusable knowledge base This isn’t “AI summarization” It’s progressive understanding The system reads like this: page → extract insights → update memory → refine → repeat Until the whole book becomes organized intelligence The craziest part? You can stop anytime… and resume later No lost context. No starting over. This is the shift: From “reading books” To compounding knowledge automatically If you’re still reading PDFs manually in 2026… you’re already behind. Bookmark this. Retweet before everyone starts building their own AI reading pipelines.

@jackfsweeney @podcastnotes @hubermanlab Expensive.

@podcastnotes @hubermanlab we made an app for this! coherencebreath.com

Rick Rubin has low heart rate variability. So he looked up everything that raises it, picked one technique, and started doing it every day. It worked. The technique: coherence breathing. 10 to 20 minutes a day, at least once, sometimes twice. Now he and @hubermanlab do it together on camera so you can follow along:

@ClaudeDevs @EricBuess Use up your usage using /usage

We’re adding more visibility into where your Claude Code usage goes. Run /usage to see a breakdown of what's driving it: parallel sessions, subagents, cache misses, long context, plus tips to optimize each.

@Shpigford Same

i turned off my 🦞 the past week of trying to force it to work with other models was a massive drain and i was able to replicate the vast majority of impactful functionality with a mix of claude cowork + code.

@benspringwater Raycast does this

I moved my daily punch list to FloatyDo this morning and am a HUGE fan so far. The extreme constraint is refreshing and imo they nailed the tradeoffs and details. My favorite todo list method has always been a single blank sheet of printer paper for the day's list and FloatyDo comes closest to instantiating that on the desktop. Clarity of space.

@thewriterme Nope he just had a presser backing Trump on using nukes in Iran tonight

First: Conservative Republicans need to run for local offices. Second: I don’t give a rats ass about Tucker or Candace. Third: This may be every reason in the world to put your money and vote behind Rubio. Time will tell. 💥

@gtconway3d Isn’t JD Vance worse?

We are going to see an accelerating tide of these admissions and conversions as the coming weeks and months pass. And the job of those of us who have opposed Trump for years is to resist saying "I told you so," or "you knew better," or "who needs you," but rather to say "thank you for seeing the light," and to ask people who previously supported Trump to help us stand up now for the impeachment and removal of that terrible man so that we rid ourselves of him sooner, rather than later. The survival of our nation as a constitutional republic depends in no small part on such grace.

@kevinrose Obsidian

co-work feature request, let me select google drive/dropbox/etc. as a place to "work" on files. -- that way I can create on the fly vs relying dispatch (my laptop to be open/on)

@buccocapital Substack

I’ve been enjoying writing a bit more long form. What’s the best place to do that? Just need simple. Is it Substack? Is there an argument for something else?

@boringmarketer I haven’t used for weeks now

anyone feel themselves using openclaw a bit less lately? personally I feel like it’s memory is not great and it’s tool use even with skills is not close to claude code I like it for quick on the go things but it’s not a workhorse for me by any means at this point

every video: ai slop every comment: bot every recipe: life story every podcast: 3 hours every app: subscription every article: paywalled every site: cookie popup every thread: engagement bait every newsletter: "quick note before we start" the internet: cooked

@signulll @EricJorgenson 🤮

very excited to dive into this this week. thanks for copy @EricJorgenson.

CHATGPT NEXT PLEASEEEE

Nothing you made with Sora mattered. Nothing made with any AI prompt will ever matter. Instead, invest in yourself by learning real creative skills.

@oykun @obsdmd @claudeai The best! So good with Claude code /commands

reconsidering going back to @obsdmd since i've started heavily using @claudeai cowork to run my businesses and life. just pulled my old obsidian vault gave access to claude seeing what's in there anyone using obsidian with claude?

@kentdebruin Yeah, hopefully it all goes the way of Sora/Dodo

AI written shit is so fucked, you let me read all this shit and it's some generated bullshit, fuck off man.

@dSebastien Probably something that looks for the gaps in your notes/thinking and helps/encourages you to fill in the gaps through prompts/questions.

What is the one thing you wish AI could do with your notes that it cannot yet? I am designing new skills for my Obsidian vault and I am curious what workflows people dream about. For me, it is a skill that traces how my thinking on a topic evolved over months, across daily notes and permanent notes. Like a time-lapse of my own mind.

@emollick No one wants the slop

My most popular Sora video was “an Elaborate regency romance where everyone is wearing a live duck for a hat (each duck is also wearing a hat), a llama plays a flute, prestige drama” I am not sure why OpenAI has decided their compute has more valuable uses. Really a mystery.

@soraofficialapp Good riddance.

We’re saying goodbye to the Sora app. To everyone who created with Sora, shared it, and built community around it: thank you. What you made with Sora mattered, and we know this news is disappointing. We’ll share more soon, including timelines for the app and API and details on preserving your work. – The Sora Team