Your Old Prompts Are Making Claude Worse - Lance Martin, Anthropic

Outdated prompt habits and poor cache use cost money and quality. The talk gives concrete audit, caching and eval steps, including cutting cost 90% with a stronger model at lower effort.

• eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.

• videoHow to Get Frontier Coding Results at 70% Lower Cost - Nouha Dziri, Cohere
• videoYour AI Agent Is Hiding Its Mistakes From You - Ben Holmes, Warp
• videoHow Agents Cut Hour-Long Data Checks to 5 Minutes - Amol Kapoor & Clifford Ressel, Nori Agentic
• videoAI Can't Make Up a Number It Can't Look Up - Vinoo Ganesh, Kepler

• videoThe prompting playbookClaude
• videoHow to Actually Tokenmaxx and Save Millions — Alvin Pane, OutRivalAI Engineer
• videoClaude for Long-Horizon Tasks — Lance Martin, AnthropicAI Engineer

Checking sign-in…

Loading comments…