https://waylandz.com This is my portfolio RSS feed https://waylandz.com/blog/shanclaw-ai-agent-harness I built ShanClaw — a Go agent runtime with tool dispatch, permissions, context management, and loop detection — before Claude Code went open source. When their architecture became public, the convergences were striking. Here is what we independently arrived at, what I learned from their caching practices, and what I think defines a production harness. Sat, 04 Apr 2026 00:00:00 GMT https://waylandz.com/blog/claude-code-tool-design-lessons An Anthropic engineer described Claude Code's evolution from simple todo lists to dependency-aware task graphs — the same patterns Shannon independently arrived at. Five lessons mapped, including where Shannon needs to catch up. Sun, 01 Mar 2026 00:00:00 GMT https://waylandz.com/blog/information-theory-and-llm Shannon laid the foundation in 1948. Seventy-eight years later, his framework still explains why Transformers work, what cross-entropy loss actually means, and why your model can never be smarter than its training data. Tue, 17 Feb 2026 00:00:00 GMT https://waylandz.com/blog/dnalyaw-quant-trading-system A deep dive into the architecture, language choices, and hard-won lessons behind building a production quantitative trading platform with Rust, Go, and Python — from nanosecond risk checks to RL-driven signal generation. Sat, 14 Feb 2026 00:00:00 GMT https://waylandz.com/blog/ai-agent-book-introduction A practical guide to building production-grade AI Agent systems. Covers single-agent design, multi-agent orchestration, MCP protocol, Computer Use, cost control, and enterprise deployment patterns. Sun, 11 Jan 2026 00:00:00 GMT https://waylandz.com/blog/transformer-book-introduction A deep dive into every component of the Transformer architecture—from Tokenization to Attention mechanisms, from forward propagation to code implementation. For developers who want to truly understand how GPT and ChatGPT work. Sun, 11 Jan 2026 00:00:00 GMT https://waylandz.com/blog/2025-review-2026-prediction Reflecting on how 2025 normalized agent workflows and reasoning models, and why 2026 feels less like a prediction and more like a state you can already opt into. Tue, 06 Jan 2026 00:00:00 GMT https://waylandz.com/blog/tensor-logic-brain-like-architecture Bridging the gap between logic and learning—how tensor equations create AI systems that think both symbolically and intuitively. Tue, 21 Oct 2025 00:00:00 GMT https://waylandz.com/blog/shannon-agentkit-alternative An architectural deep-dive into Shannon, a self-hosted multi-agent platform that addresses the three hardest problems in production AI: runaway costs, non-deterministic failures, and security vulnerabilities—through deliberate technology choices in Rust, Go, and Python. Tue, 07 Oct 2025 00:00:00 GMT https://waylandz.com/blog/ai-quant Demystifying quantitative trading for AI practitioners — what quant funds actually do, why reinforcement learning fits markets better than LLMs, and where the real barriers lie. Tue, 29 Apr 2025 00:00:00 GMT https://waylandz.com/blog/read-karpathy-rnn-post Reflecting on Andrej Karpathy’s 2015 RNN post and the surprising evolution of LLMs with transformers and fine-tuning. Tue, 25 Feb 2025 00:00:00 GMT https://waylandz.com/blog/transformer-architecture A step-by-step walkthrough of the Transformer architecture—from input embeddings and positional encoding to self-attention and the decoder-only GPT variant. Thu, 22 Feb 2024 00:00:00 GMT