Christopher Dean

Instead of watching an hour of Netflix, watch this 2 hour hour Stanford lecture will teach you more about how LLMs like ChatGPT and Claude are built than most people working at top AI companies learn in their entire careers.

🚨 Deploy Hermes On The Abacus AI Super Computer You can now choose Claw or Hermes and deploy it on our cloud super computer - Bring you own Claude or Codex keys - Build on secure and scalable AI - Deploy in seconds Always on AI agents that you can simply message from Telegram or Whatsapp to do things

🚨 Anthropic just showed a 27-minute workshop on how to actually do prompts for Claude. Taught by the people who built it. Free. No registration. No paywall. I've seen $300 courses that don't cover what they teach in the first 8 minutes. Watch it and bookmark it now.

Andrej Karpathy built a wiki to think with AI. I built something that thinks back. Claude Code + Obsidian equals an AI that actually knows you. Your goals. Your context. Your history. Not a chatbot you explain yourself to every session. A second brain that remembers everything permanently. Build it once. It compounds forever. Bookmark it for later and start this weekend.

more and more work is moving into coding agents, I don't live in my editor anymore but you gotta keep an eye on these little goblins, they write bad code. so we built a diff viewer in opencode! available now

With the Cursor SDK, you can build your own agents with Composer 2.5. It's now available in Python and TypeScript. This long weekend, Composer usage is 90% off in the SDK. We're excited to see what you build!

Kimi K2.6 = replaced an entire dev team. Works while you sleep. One person. Parallel agents. 90% profit margin. Zero employees. $80,000 a month solo. Most agency owners spend their first $80K on salaries, benefits, and management overhead before they make a single dollar of profit. This builder spent it on API costs and kept the rest. The math is not complicated. A dev team costs $30,000 to $60,000 a month in salaries. Parallel AI agents cost a few hundred dollars a month in inference. Same output. Fraction of the cost. Zero management overhead. Zero HR. Zero office politics. 4 to 6 hours saved every single day. The people still building agencies the old way are not losing to better agencies. They are losing to one person with the right AI stack who can undercut their pricing by 60% and still run at 90% margin. That is not a productivity upgrade. That is a structural economic advantage that compounds every month. The builders who figure this out in 2026 will be the ones everyone else is trying to reverse engineer in 2027. Read this and Bookmark it now.

🚨 Boris Cherny, the creator of Claude Code at Anthropic, just explained why most people aren't getting real results from Claude in this podcast he breaks down exactly how most people never actually set up Claude: - the 14% you lose to CLAUDE.md before typing a word - the features that change how Claude thinks before you type a word - the settings 95% of users have never opened - the workflows hiding behind one toggle if you've been using Claude for more than a month and never left the chat window, you have at least 30 untouched features. probably 38 instead of another show tonight, watch this make sure to bookmark it before it gets lost in your feed

INSTEAD OF WATCHING NETFLIX TONIGHT. Spend 2 hour with this. Claude AI FULL COURSE that teaches you how to BUILD and AUTOMATE anything. The people who watch this tonight will wake up tomorrow with a new skill. Watch it and Bookmark it now.

Boris Cherny, the creator of Claude Code at Anthropic, just explained why most people aren't getting real results from Claude in this podcast he breaks down exactly how most people never actually set up Claude: - the 14% you lose to CLAUDE.md before typing a word - the features that change how Claude thinks before you type a word - the settings 95% of users have never opened - the workflows hiding behind one toggle if you've been using Claude for more than a month and never left the chat window, you have at least 30 untouched features. probably 38 instead of another show tonight, watch this make sure to bookmark it before it gets lost in your feed

2️⃣ Appshots bring context from your screen straight into the Codex app.

3️⃣ Goal mode is now available in the Codex app, IDE extension, and CLI. Goal mode makes Codex more hands-off, letting you set a goal that it can work towards for hours or even days.

4️⃣ Advanced annotation mode lets you directly adjust the way web pages look while leaving feedback, making it even easier to work together with Codex.

Instead of watching an hour of Netflix, watch this 2 hour hour Stanford lecture will teach you more about how LLMs like ChatGPT and Claude are built than most people working at top AI companies learn in their entire careers.