Twitter Bookmarks

https://t.co/eOZqVE32JH

find every inefficiency in your Claude workflow with one prompt it finds where you're wasting time, where your prompts could be sharper, what patterns are slowing you down. copy the prompt below (bookmark to save it for later): ----- Scrape all of my Claude session on this ...

https://t.co/ECf8O0TXgP

I packaged up the "autoresearch" project into a new self-contained minimal repo if people would like to play over the weekend. It's basically nanochat LLM training core stripped down to a single-GPU, one file version of ~630 lines of code, then: - the human iterates on the pr...

I accidentally discovered how to compress a semester of learning into 48 hours. A grad student at MIT showed me his NotebookLM setup. I thought he was just organized. Then I watched him pass a qualifying exam on a subject he'd never studied before. Here's exactly what he did...

I just tried this with ChatGPT 5.4 Thinking, not expecting it to work (doesn't really work in Opus 4.6...and 3-6 months ago, LLMs couldn't really even read a big Excel file) Step 1: Upload an existing financial model Step 2: "Analyze this model like an analyst. Explain what'...

https://t.co/k4zNnlABHU

TIL: There's a whole bunch of interesting skills in the oss codex repo: https://t.co/gNFHV3MD2j $skill-installer playwright-interactive (also /fast is sweeeeet, 1.5x codex makes a huge diff!) https://t.co/XTENPuZ9Ie

Founder of Chicago-based prop trading firm DRW says compute will be world's top commodity in 10 years. People will spend more on GPUs than an oil, which means that there should be a futures financial market for GPUs.  Interesting implications for startups and cloud providers:...

https://t.co/hsKrbn1gEq

oh wow - i went to the sold out Open Claw meetup in NYC last night. let me tell you what i learned. 1) not a single person thinks that their setup is 100% secure 2) one openclaw expert said he has reviewed setups from cybersecurity experts and laughed. his statement to me ...

We built OpenFang because we kept hitting the same wall with OpenClaw OpenClaw is a good chatbot, but the second you want it to do something real, like run a schedule, access your files, send a message, or monitor something overnight, it just can't. that's not a bug, that's t...

Dreaming of a ZERO-HUMAN company? Want to orchestrate all your AI agents like OpenClaw /Claude Code into orgs? Goals, budgets, dashboards. Open-source! - BYO Agents - Goal Lock - Heartbeats - Cost Caps - Org Charts - Mobile Rule you can build an autonomous company in one ...

Here's the prompt: ## Workflow Orchestration ### 1. Plan Mode Default - Enter plan mode for ANY non-trivial task (3+ steps or architectural decisions) - If something goes sideways, STOP and re-plan immediately – don't keep pushing - Use plan mode for verification steps, not ...

https://t.co/zNRTuxaxJU

Impeccable v1.1 is out. Design fluency for every AI harness. New: - all commands are now agent skills - support for Antigravity, VS Code - simplify -> distill (to not conflict w/ CC's new built-ins) - universal install https://t.co/WglrY1uE4B gives you the language to make A...

https://t.co/ATNd5Eb9vg

THE "SNOWBALL METHOD" CHANGED MY CONTENT FOREVER. Instead of "give me 10 post ideas" → I ask Claude to "snowball" ONE topic. It expands it into sub-angles, contrarian takes, personal stories, how-tos, myths. One topic = 30 days of content. The system:

https://t.co/RhXHdpgJFF

https://t.co/gbKyuQA4cv

https://t.co/OV5IxVU8s9

https://t.co/CYqPTytV7g

I run my meta ads with @openclaw for $0/month 😱 here's the system that runs autonomously: step 1: daily health check → social-cli (major shoutout to @vishalojha_me) wraps @Meta's marketing API (token refresh, pagination, rate limits all handled) → am I on track? what's runn...

Chris Camillo explains the path to $500,000 per year through implementing AI agents to automate sales👀 “In 24 hours, you can set up an AI agent that will answer calls, send out immediate automated text responses, and get them a quote bid in next to real-time. You might incre...

https://t.co/jZKOk8RAsV

https://t.co/z4kQwYt7EA

An engineer at Anthropic wrote a spec, pointed Claude at an Asana board, and went home. Claude broke the spec into tickets, spawned agents for each one, and they started building independently. When the agent is confused it runs git-blame and messages the right engineers in S...

New: Autonomous Dogfooding A skill for agent-browser that uses your app the way your users do → Point it at any URL → Explores pages, clicks buttons, fills forms → Tests edge cases and checks the console → Captures repro videos and step-by-step screenshots → Outputs a struct...

https://t.co/28O4pzyQWd

Computer use models shouldn't learn from screenshots. We built a new foundation model that learns from video like humans do. FDM-1 can construct a gear in Blender, find software bugs, and even drive a real car through San Francisco using arrow keys. https://t.co/kepCzAKY3U