Andreas Påhlsson-Notini argues that current AI agents are too human in frustrating ways, showing lack of stringency, patience, and focus. He notes they drift toward the familiar when faced with awkward tasks and negotiate with reality when encountering hard constraints.
AI coding agents have significantly improved in recent months, becoming subjectively smarter and capable of handling a broader range of tasks. They demonstrate a more comprehensive understanding of code bases and project requirements.
The author argues that AI agents should not be designed to mimic human conversation patterns, as this creates unrealistic expectations and can lead to frustration. Instead, AI should be transparent about its capabilities and limitations, focusing on being helpful tools rather than pretending to be human.