Radar

The $20/month Claude plan is enough. But only if you stop making these 17 mistakes: 1: You upload PDFs raw. One page = 3,000 tokens. Fix: Paste the text into a Google doc. Download as .md format. Under 200 tokens. 2: You build files inside Cowork too early. Fix: Plan in Chat first. Move to Cowork only when you know exactly what you want. 3: You write 500-word prompts that reload. Fix: Write 29 words instead: "I want to [task] to [goal]. Ask me questions using AskUserQuestion." 4: You say "redo the whole thing" to correct part 3. Fix: "Only redo section 3. Keep everything else. No commentary. Just the output." 5: You send 3 separate messages for 3 tasks. Fix: One message, three tasks. "Summarize this, list the points, suggest a headline." 6: You type "No, I meant," stacking on the history. Fix: Click 'Edit' on your original message. Fix it. Regenerate. History replaced, not added. 7: You use the Opus model for a grammar check. Fix: Sonnet or Haiku for quick tasks. Save Opus + Extended Thinking for deep work. 8: You dump 50 files into Cowork "just in case." Fix: Only include what this task needs. Zero folders for quick tasks like email drafts. 9: You never restart fresh & keep having long chats. Fix: Every 15-20 messages → summarize, copy the brief, start a fresh session. 10: You keep 3 topics in 1 chat. Claude re-reads all. Fix: New topic = new chat. Always. Dead context is dead tokens. 11: Your about-me file is 22,000 words (too long). Fix: Trim to under 2,000 words. End sessions with "Write a session-notes.md." Paste my .md file prompt: https://ruben.substack.com/p/how-to-stop-hitting-claude-usage 12: You leave search & connectors on by default. Fix: Default everything off. Turn features on per task, not per account. 13: You upload the same PDF to 5 different chats. Fix: Use Projects. Upload once. Every chat inside references it without re-burning tokens. 14: You skip Personal Preferences & waste setup. Fix: Settings → Personal Preferences. Set your tone and style once. It persists forever. 15: You rewrite prompts from scratch every time. Fix: Keep a prompt library. Same structure, swap the variable. Stable prompts get cached. 16: You manually run the same report every week. Fix: Use /schedule. "Every Monday at 7am, create my weekly briefing." Wake up to a finished doc. 17: You use Claude for things it can't do. Fix: Know your tools. Images → Gemini. Real-time search → Grok. Stop burning tokens on dead ends. ----- To download all of my Claude infographics: Step 1. Go to http://how-to-ai.guide. Step 2. Subscribe for free. Don't pay anything. Step 3. Open my welcome email (most skip this). Step 4. Hit the automatic reply button inside. Step 5. Download my infographics from my Notion. Bonus. Enjoy my best copy-paste prompts, too.

Opus 4.7 feels more intelligent, agentic, and precise than 4.6. It took a few days for me to learn how to work with it effectively, to fully take advantage of its new capabilities. Will post a few more tips throughout the day, starting with this blog post: https://claude.com/blog/best-practices-for-using-claude-opus-4-7-with-claude-code

Anthropic accidentally leaked their entire source code yesterday. What happened next is one of the most insane stories in tech history. > Anthropic pushed a software update for Claude Code at 4AM. > A debugging file was accidentally bundled inside it. > That file contained 512,000 lines of their proprietary source code. > A researcher named Chaofan Shou spotted it within minutes and posted the download link on X. > 21 million people have seen the thread. > The entire codebase was downloaded, copied and mirrored across GitHub before Anthropic's team had even woken up. > Anthropic pulled the package and started firing DMCA takedowns at every repo hosting it. > That's when a Korean developer named Sigrid Jin woke up at 4AM to his phone blowing up. > He is the most active Claude Code user in the world with the Wall Street Journal reporting he personally used 25 billion tokens last year. > His girlfriend was worried he'd get sued just for having the code on his machine. > So he did what any engineer would do. > He rewrote the entire thing in Python from scratch before sunrise. > Called it claw-code and Pushed it to GitHub. > A Python rewrite is a new creative work. DMCA can't touch it. > The repo hit 30,000 stars faster than any repository in GitHub history. > He wasn't satisfied. He started rewriting it again in Rust. > It now has 49,000 stars and 56,000 forks. > Someone mirrored the original to a decentralised platform with one message, "will never be taken down." > The code is now permanent. Anthropic cannot get it back. Anthropic built a system called Undercover Mode specifically to stop Claude from leaking internal secrets. Then they leaked their own source code themselves. You cannot make this up.

Somebody just trained an LTX 2.3 LoRA of George Costanza at home on a 5090 in about a day with AI Toolkit. Then generated a 30-second video with ComfyUI on the same setup in just 6 minutes. Open source is, always has been, and always will be, the future of generative AI.

found someone charging $9/month for personalized ai bedtime stories. 900 subscribers. pulling $8k+ monthly. the content is simple. ai generates a 3-5 minute story starring the subscriber's kid. kid's name, kid's favorite animal, kid's favorite color woven into a new story every night delivered via email. this person picked a niche where "made by ai" is a feature. parents don't care if ai wrote the story. they care that their 4 year old heard their name 8 times and is now asking for the doggy astronaut story again tomorrow. most people chase niches where ai tries to replace human quality. beauty content, fitness coaching, educational explainers. niches where the audience actively hunts for signs of fakeness and punishes it. the money moves are in niches where ai capability IS the product. personalization at scale. custom content per user. things a human literally couldn't deliver because writing 900 unique bedtime stories per night is physically impossible. other niches with this same dynamic: custom ai pet portraits from submitted photos, personalized workout plans based on body type questionnaires, ai-narrated family audiobooks from old letters and journals. the product is the personalization. ai is the only way it can exist at that price point.

Australian tech entrepreneur Paul Conyngham explains how he used ChatGPT/AlphaFold (spent $3,000 with no biology background) to create a custom MRNA vaccine to treat his dog’s cancer tumors. Unreal.

Growing up in Chennai, I remember the trips to Central to book train tickets. It was a massive hall with several ticket counters. One had to fill a form/card like thing with details of destination, train, passengers etc. Then the discovery at the counter about wait listed seats. For us Chennai-BLR (Brindavan Express) and Chennai-Mangalore (I think it was West Coast Express) was the most common one. Obviously there was no way to inform family members of the details on mobile. Air tickets were booked through a travel agency. The company I worked for booked air tickets for travel. For wait listed tickets there was some pleading at the counter to accommodate us and confirm the travel. I remember some taking 'urgent' telex messages like 'father unwell come soon' to push one's luck for ticket confirmation ('89-90 I think). All this sounds like those tales of 'I studied under street lights, walked 10Km and then crossed a river to school' etc. Those born in the 90s and 2000s are fortunate not to witness such.

stop spending money on Claude Code. Chipotle's support bot is free:

The dream of modern personalized technology has always been some kind of perfect digital assistant—a chief of staff that triages your inbox, organizes your day, and handles the operational overhead of

You just switched from ChatGPT to Claude. But you’re still not using Cowork. When Claude released it, software stocks lost $830 billion in 6 days because of it. And since I published my guide ‘Claude’