Explains how token limits and context windows cause AI coding agents to fail, and offers techniques to keep them stable during long tasks.
A critique of Andrej Karpathy's AGI timeline, arguing that AI systems, not just LLMs, will replace knowledge workers sooner than his definition suggests.
A developer reflects on the shift from classic programming debates to pervasive AI discussions, exploring its practical use, ethical concerns, and impact on the developer community.
Critiques the anti-AI movement's purely negative stance, arguing it undermines credibility and suggests more constructive criticism.
An experiment testing the limits of autonomous AI code generation for a Spring Boot app, revealing current limitations and the need for human oversight.
A Thoughtworks engineer argues that developers must still care about code quality and testing, even with advanced AI coding assistants.
A developer explores the limitations of AI coding assistants like Cursor and ChatGPT, highlighting their 'bias towards helpfulness' compared to human feedback.
