You can't whisper at an AI agent (opens in new tab)
--- title: 'You can''t whisper at an AI agent' summary: 'What a dozen steering experiments taught us about how LLM-based agents actually behave in the wild.' authors: - 'James Beswick' - 'Peter Epsteen' date: '2026-05-14' topics: - 'AI' - 'Best Practices' - 'Developer Productivity' type: 'Blog' --- There's a comforting mental model that many of us carried into the age of AI agents, that they'd behave like diligent junior engineers. All you have to do is hand them a codebase, point them at th...
Read the original article