I think, therefore I am; recording insights from daily life and technology.
An analysis of Xiaomi's HyperOS 4 adopting Flutter for UI and Rust for system services, weighing performance benefits against Dart VM maintenance burdens and divergence from Android's mainline optimization.
This article presents a systematic approach to building reliable AI agents by classifying faults into API, tool, context, and control-flow layers, detailing detection mechanisms like repeat-call fingerprints and watchdogs, and outlining recovery strategies including exponential backoff, model cascade degradation, tool-error virtualization, and idempotent pre-check-confirm patterns to prevent death spirals and ensure safe retries.
This article outlines six key principle categories for designing effective AI agent systems: simplicity, transparency, tool interface design, harness constraints, context engineering, evaluation, and multi-agent collaboration, emphasizing iterative evolution and cost-aware decisions.
This article reviews 'Software Architecture: The Hard Parts', highlighting eight key architectural challenges including trade-offs, data-architecture tensions, service granularity, database decomposition, distributed data access, contract design, code reuse, and error handling in distributed systems.
The article surveys classic definitions of software complexity from Ousterhout, Simon, Mitchell, Gall, Taleb, Tesler, Gurley, and Wolfram, then proposes three dimensions—structure, behavior, and evolution—for analyzing complex software systems.
This article traces Claude Code agent interactions to reveal how natural language queries are converted into search commands via agentic tool-driven loops, highlighting the impact of tool configuration and LLM reasoning quality on code location accuracy.
This article explains the historical origins of mathematical symbols used in AI papers, provides a six-step method for reading formulas (type checking, outside-in parsing, bound variables, dimensional analysis, extreme values, code translation), and includes a symbol-to-code dictionary with case studies on Gaussian, attention, and chain rule.
Learn to trace Claude Code agent interactions by setting up mitmproxy via cc-trace to intercept and inspect API requests and responses to Anthropic or DeepSeek, with step-by-step terminal commands and a web UI for viewing prompts, tool calls, and model outputs.
This article explores Android's system-level reliability designs, including the TokenBucket rate limiter for logs and metrics, the MultiRateLimiter multi-window quota engine used for Toast rate limiting, and resource counting mechanisms like broadcast receiver limits, showing how Google prevents system overload from app misuse.
This article details Android's file reliability design patterns including atomic write protocols, triple-redundancy fault tolerance, transactional file updates, RAII file descriptor management, zero-copy optimization, dynamic storage trimming strategies, and filesystem-level quota and reservation mechanisms.
