Synthesis 1: Tracing how seven weeks form a deliberate knowledge arc from symbolic search to language models, revealing the design philosophy from classical AI to modern ML.
Week 0 opens with search algorithms: BFS for shortest paths, Minimax for adversarial play, Alpha-Beta for pruning. Two projects: Degrees (BFS) and Tic-Tac-Toe (Minimax).
07-280 is CMU's new Spring 2026 AI+ML core: 24 lectures and 12 main assignments move from heuristic search and CSPs to AlexNet, GPT-2, and AlphaZero. Its public material supports self-study, but complete recordings, Canvas checkpoints, Gradescope, and staff feedback remain unavailable.
Lecture 2 decomposes search into a problem, frontier, and priority: UCS uses paid cost, Greedy uses estimated remaining cost, and A* combines them as `f=g+h`; tree and graph search require different optimality conditions.
Lecture 4 exposes structure through variables, domains, and constraints, then upgrades DFS with backtracking, forward checking, AC-3, MRV, and LCV; the goal is to prove failure earlier.
Lectures 1–12 form one decision pipeline: define states, moves, and objectives, then use heuristics, losses, regularization, and backpropagation to control an otherwise intractable search space.
The repository has a 20-query Traditional Chinese/English golden dataset, but no document-level qrels, retrieval runs, raw latency data, or executable benchmark script. Reporting Recall@k, MRR, or nDCG as measured results would therefore be dishonest; this article defines the contract needed to run them reproducibly.
Lectures 1–4 and Project 1 connect DFS, BFS, UCS, A*, state representation, and heuristic design. The goal is not memorizing algorithms but separating what the frontier, cost, and state each control.
Algolia packages indexing, search-as-you-type, facets, and UI components as a hosted service; it ships quickly, but data synchronization, relevance, and usage costs remain your responsibility.
Elasticsearch and OpenSearch both build text analysis, BM25, aggregations, and vector search on Lucene, but licensing, governance, hybrid-search APIs, and managed ecosystems have followed separate paths since the 2021 fork.
Pagefind scans static HTML after an Astro build and ships its index with a WebAssembly search runtime; the browser fetches only the index chunks required by a query, so no search server is needed.
Typesense is a search server centered on instant, typo-tolerant keyword search. Collection schemas, field weights, facets and sorting are enough to build site search, with a choice between self-hosting and Typesense Cloud; Chinese fields need locale: zh, and domain terminology may require custom segmentation.
CS221 lays AI out along one axis, and reflex models — deep learning — sit in the lowest slot, with states, variables and logic above them. When Percy Liang took over in Autumn 2025 he replaced the slides with runnable Python and wrote 'Cut constraint satisfaction problems :(' into the source of the first lecture — yet ExploreCourses and Stanford Online both still advertise constraint satisfaction as a course topic. The project has gone from 20% of the grade in 2019 to extra credit only.
When using AI agents like Claude Code or Cursor, built-in WebFetch / WebSearch often gets blocked by Cloudflare, geo-restrictions, or rate limits. Connecting a search MCP server is the most direct fix. This post compares the options actually available in 2026.