AI prompt engineering in 2025: What works and what doesn’t | Sander Schulhoff

Gives concrete prompting techniques and the argument that prompt injection cannot be fully fixed, which shapes how much authority you should hand to agents.

• prompt injection — An attack that hides instructions in content an AI will read — a webpage, email, or document — tricking it into following the attacker instead of the user.

• videoOpenAI’s head of platform engineering on the next 12-24 months of AI | Sherwin Wu
• videoThe AI-native startup: 5 products, 7-figure revenue, 100% AI-written code. | Dan Shipper (Every)
• videoAnthropic's CPO on what comes next | Mike Krieger (co-founder of Instagram)
• videoThe rise of Cursor: The $300M ARR AI tool that engineers can’t stop using | Michael Truell

• podcastThe coming AI security crisis (and what to do about it) | Sander SchulhoffLenny Rachitsky
• videoThe prompting playbookClaude
• videoState-Of-The-Art Prompting For AI AgentsY Combinator

Checking sign-in…

Loading comments…