Tag
An analysis of the current state of AI memory systems, arguing that the focus has shifted from storing more data to defining how memory should behave—covering governance, observability, lifecycle management, and interoperability.
This article argues that filesystems, due to their long history and extensive inclusion in LLM training data, offer a natural and intuitive primitive for AI agent memory, outperforming traditional databases and APIs for exploratory reasoning and persistent context.
The 2026 State of Web Dev AI survey with over 7,000 respondents reveals that AI-generated code has doubled to 56% on average, Claude is the most paid-for model, and developers are spending more on AI tools, amid growing concerns about an AI bubble.
Practitioner Rory Sawyer reflects on a decade of applying program analysis to bridge the gap between code and human intent, emphasizing static analysis as a communication tool for correctness beyond execution.