Rohit Parab

I thought people were exaggerating. Then I burned $100+ of extra Claude usage in 1 hour. What happened: agentic coding with Claude in Chrome enabled. 10-20x multiplier on already expensive operations. A survival guide until the fix ships: Claude Code (terminal): → npx @anthropic-ai/claude-code (bypasses the Bun cache bug) → Avoid --resume (breaks cache) → /compact to compress context mid-session → /effort medium for routine work, /effort low for simple tasks → --model sonnet for exploration. Opus for final passes only → /mcp — disable servers you're not actively using VS Code / Cursor: → Same engine. Same bugs. Same fixes. Cowork (desktop): → Default to Sonnet. Not every task needs Opus. → Auto-selects effort → Start a fresh session if context bloats Dispatch (mobile): → No model picker in UI → Delete session, start new one if it spirals → You can ask it to dispatch sessions with specific models The biggest lever most people miss: stop using Claude in Chrome for scraping. Dev-browser gives you DOM snapshots instead of screenshots. Text is 10-100x cheaper than pixels. Anthropic knows. Fix is coming. Until then — /compact, /effort medium, and kill your unused MCPs.

"I don't think many tech companies execute M&A well." Palo Alto Networks CEO @nikesharora breaks down his strategy for successful M&A: "Purchase price is an irrelevant artifact. If it's going to work, it's going to work phenomenally well, or you're going to screw it up. It's not what you paid, it's what you're able to do with it." "You could say that Instagram was expensive, or YouTube was expensive, or DoubleClick was expensive. They all worked perfectly. AOL Time Warner is a different story. So it boils down to how you execute past the price you pay for it." "In tech, when you buy a company, you buy a team, you buy an existing product, and you buy a roadmap for the future. The question is: can you deliver on that roadmap? Can you accelerate that roadmap? Does it work?" "We sign a term sheet, and we ask the founders to sit with our team and redesign the product roadmap so we like it and they like it. And if they don't agree with our expectations and we don't agree with theirs, we don't buy the company." "We make them in charge. My teams have to work for them, which makes them really unhappy. And not many of them like it. But I'm like, look, these guys went out there, raised money, kicked your ass in your category, and you want them to work for you? That makes no sense to me. You're going to work for them. Learn from them." "So our job is to enable these people. We look at them and say, whatever your business plan was when you were a small private company, find me a business plan that's twice as assertive and bold as the one you had then." "We've built a phenomenal system to take them to market. I have 3,000 people in the field... 3,000 people go out there and see 10,000 customers. So that's where the secret sauce kicks in." "We've bought 34 companies so far. I think our hit rate on things that have worked is over 70%."

@tobi Who knew early singularity could be this fun? :) I just confirmed that the improvements autoresearch found over the last 2 days of (~650) experiments on depth 12 model transfer well to depth 24 so nanochat is about to get a new leaderboard entry for “time to GPT-2” too. Works 🤷‍♂️