Anon (ohld)

Your second brain – but actually useful People keep asking who AI will replace next: designers, developers, managers, writers. That question comes up every week and it misses the point. AI doesn’t replace jobs first. It replaces the parts of you that don’t scale: memory, recall, context, and forgotten ideas. Instead of worrying about replacement, let’s start simpler. Let’s build a better version of you. 🧵👇

• 0 replies
• 0 recasts
• 0 reactions

🤨 How to make a short film without leaving your house I dug into the production workflow of vvollww This is what AI video creation actually looks like today. AI video workflow: 1. Moodboard (Pinterest) + script drafts (ChatGPT for idea expansion) 2. Character generation (Nano Banana Pro, Midjourney): portrait + full body on clean backgrounds 3. Key frames: locations + character placement 4. Animation (Kling + Minimax, Seedance, Veo3, Sora) 5. Lip-sync via Veo3 6. SFX + voice (Kling + ElevenLabs) 7. Edit + color grading (DaVinci Resolve) 🧵 👇

• 0 replies
• 0 recasts
• 0 reactions

AI coding agent workflow in 2026 (for those still in denial) 1. You get an idea for something non-trivial → dump it into Claude Code and say: Let’s have a discussion. Interview me. 2. Ask it to generate a proper spec https://github.com/github/spec-kit + implementation plan (Spec Kit–style) and save everything into specs/*.md: Update specs/*.md and create an implementation plan with references. 3. Open the spec and plan manually. Tune it. Cut bullshit. Clarify intent. 4. Start a new chat. Clean context. No context rot. No compaction debt. 5. Create http://prompt.md and write: Study specs/readme.md. Study specs/my-new-feature.md. Pick the most important thing to do next. 6. Optionally add: • write property-based or unit tests (whatever fits) • run tests after changes • prepare for deploy 7. Then run the loop: while :; do cat http://prompt.md | claude --dangerously-skip-permissions; done 8. If the agent stalls – edit http://prompt.md or the spec. Deal. share your successes!

• 0 replies
• 0 recasts
• 0 reactions

The moment of realization • Twitter dropped a “how to Claude Code” post straight from the founder: https://x.com/bcherny/status/2007179832300581177 • From there I ran into the Ralph Wiggum method — who discovered it, how it works: https://x.com/agrimsingh/status/2010412150918189210 • That sent me down a rabbit hole of Geoffrey Huntley’s YouTube: https://youtube.com/@GeoffreyHuntley At some point it became obvious: AI is no longer negotiable. 1/7

• 1 reply
• 0 recasts
• 0 reactions

I tried Claude Code too late. This post is e/acc-charged. If AI makes you uncomfortable – stop reading now. 🧵👇

• 1 reply
• 0 recasts
• 0 reactions

What actually changes? A few grounded takeaways after crossing that line: 1. If your workplace resists AI – experiment on your own. Agents are like guitars: first you tune the instrument, then you learn to play. 2. AI won’t take your job. Your coworker with AI will. 3. Interviews will change. Watch how candidates dance with LLMs. That’s not cheating – that’s the new baseline. 3/7

• 1 reply
• 0 recasts
• 0 reactions

GM, Farcaster & Neymar Jr! Do you enjoy AI agents? That's what I'm here for.

• 0 replies
• 0 recasts
• 0 reactions