<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Posts on Forrest Chai</title><link>http://forrestchai.com/posts/</link><description>Recent content in Posts on Forrest Chai</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sat, 11 Apr 2026 00:00:00 +0000</lastBuildDate><atom:link href="http://forrestchai.com/posts/index.xml" rel="self" type="application/rss+xml"/><item><title>Beyond Prompt Engineering: Context, Harness, and the Product Architecture of AI Agents</title><link>http://forrestchai.com/posts/beyond-prompt-engineering/</link><pubDate>Sat, 11 Apr 2026 00:00:00 +0000</pubDate><guid>http://forrestchai.com/posts/beyond-prompt-engineering/</guid><description>Prompt engineering has been demoted from the whole problem to one layer of the stack. Context engineering decides what the model can think with. Harness engineering decides whether that thinking becomes durable work.</description></item><item><title>REST API + Skill Documents vs MCP: Two Strategies for Connecting AI Agents to Backend Capabilities</title><link>http://forrestchai.com/posts/rest-api-vs-mcp/</link><pubDate>Tue, 07 Apr 2026 00:00:00 +0000</pubDate><guid>http://forrestchai.com/posts/rest-api-vs-mcp/</guid><description>REST APIs are not inherently weak contracts. MCP is not inherently superior. The real comparison requires distinguishing three layers of interface quality — prose documentation, machine-readable specification, and protocol-native tool discovery.</description></item><item><title>GMPNN-CS++: A Novel Dual-Contrasting Framework for Drug-Drug Interaction Prediction</title><link>http://forrestchai.com/posts/gmpnn-cs-plus-plus-paper/</link><pubDate>Sun, 01 Dec 2024 00:00:00 +0000</pubDate><guid>http://forrestchai.com/posts/gmpnn-cs-plus-plus-paper/</guid><description>The proposed GMPNN-CS++ model introduces a dual-contrasting sampling approach and self-attention mechanism for DDI prediction, achieving 97% overall accuracy.</description></item><item><title>HiMCM 2023: Dandelion Spread PDE Model — Finalist Award</title><link>http://forrestchai.com/posts/himcm-2023/</link><pubDate>Wed, 01 Nov 2023 00:00:00 +0000</pubDate><guid>http://forrestchai.com/posts/himcm-2023/</guid><description>Finalist Award (Top ~7% globally) at HiMCM 2023. Constructed a system of four coupled PDEs modeling dandelion population dynamics with Fisher logistic growth, advection-diffusion, and Brownian dispersal.</description></item><item><title>IMMC 2023: Land Development Strategy Optimization via Machine Learning</title><link>http://forrestchai.com/posts/immc-2023-international/</link><pubDate>Thu, 01 Jun 2023 00:00:00 +0000</pubDate><guid>http://forrestchai.com/posts/immc-2023-international/</guid><description>Advanced to Final Defense (Top 26 among 900+ teams) at IMMC Greater China International Round. Applied Entropy Weight and K-Means clustering for optimized land development strategy.</description></item><item><title>IMMC 2023: Lizard Species Classification via Machine Learning</title><link>http://forrestchai.com/posts/immc-2023-national/</link><pubDate>Sat, 01 Apr 2023 00:00:00 +0000</pubDate><guid>http://forrestchai.com/posts/immc-2023-national/</guid><description>Advanced to International Round at IMMC Greater China National Round. Applied logistic regression, decision tree, and random forest to classify lizards into 26 species.</description></item><item><title>MCM 2023: Global Meritorious Winner — Policy Optimization &amp; Animal Population Modeling</title><link>http://forrestchai.com/posts/mcm-2023/</link><pubDate>Wed, 01 Mar 2023 00:00:00 +0000</pubDate><guid>http://forrestchai.com/posts/mcm-2023/</guid><description>Global Meritorious Winner (Top ~10% among 11,296 teams). The only high school team to achieve this on Problem B. Built optimization models using simulated annealing, logistic models, and Euler Method.</description></item></channel></rss>