Field Notes · School-based AI

Model watch

What separates the large language models, reasoning models, open and closed weights, agents and the risks that come with them

Model watch11 September 2026About 8 min

Comparing 15 LLM Providers in 2026: Prices, Context Windows, and the One Decision a School Actually Makes

One set of school usage assumptions applied to September 2026 official pricing from OpenAI, Anthropic, Google, xAI, Meta, Mistral and Cursor Composer, plus DeepSeek, Qwen, Kimi, GLM, MiniMax, Doubao, Hunyuan and ERNIE. Capability gaps are narrowing while price gaps widen, which means the real decision is not which model to use but who absorbs the volatility and what a generational change costs.

Keep reading

Model watch11 September 2026About 7 min

Choosing Among China's LLMs: DeepSeek, Qwen, Kimi, GLM and Four More, From a Hong Kong School's Side of the Table

The same "DeepSeek" means two entirely different privacy positions depending on whether you download the weights or call the API. This piece lays out the price, context window, licence and hardware floor for DeepSeek, Qwen, Kimi, GLM, MiniMax, Doubao, Hunyuan and ERNIE, then sorts school work into the routes a Hong Kong school can defend under the Personal Data (Privacy) Ordinance.

Keep reading

Model watch11 September 2026About 7 min

Tool Calling, MCP and AI Agents: Deciding Which Step a School Will Not Hand Over

An AI agent is not a chatbot with better answers. It is a system that has been granted permission to act — it files a request, calls your school's data, and takes another step based on what comes back. This article follows one tool call end to end, explains what the MCP standard actually changes for a school, how per-call tool billing adds up, and the three risks that agency amplifies.

Keep reading

Model watch11 September 2026About 6 min

Choosing Among Four US LLM Providers: OpenAI, Anthropic, xAI and Google for Schools

In September 2026 the gap between OpenAI GPT-6 Astra and Google Gemini 3.8 Flash flagship input pricing is 13x, yet panel heads often cannot tell the summaries apart. Rather than a spec dump, this piece starts from real Hong Kong school tasks and walks through price, context, Chinese handling, access paths and billing traps.

Keep reading

Model watch11 September 2026About 6 min

School AI Safety in Practice: Hallucination, Prompt Injection and Platform Guardrails

A language model can cite a curriculum guideline number in perfect format that does not exist — a structural property, not one vendor's bug. Starting from everyday Hong Kong school scenes, this piece maps OWASP top risks and the NIST framework to hallucination consequences, what injection looks like, and the guardrails and audit arrangements a school platform must have.

Keep reading

Model watch11 September 2026About 6 min

Open Weights or Closed API? Real School Maths on Self-Hosting, and When Privacy Flips the Answer

Many schools assume a machine running an open model must beat cloud pricing. Run real usage through September 2026 published rates and the annual API bill is often too small for hardware to catch. This piece works both sides honestly, lists open models that actually fit a server room, and names the data-policy moments that tip the balance toward on-premises deployment.

Keep reading

Model watch11 September 2026About 6 min

Reasoning Models in Schools: Chain-of-Thought, Adaptive Thinking, and What Changes for Marking and STEM

Models in 2024 rushed to answer; models in 2026 reason internally first and decide their own thinking depth. This article explains chain-of-thought, reasoning effort and adaptive thinking in staffroom language, compares the four vendors' effort controls, and sets out what has genuinely changed for marking, maths and science — and what has not.

Keep reading

Model watch

Comparing 15 LLM Providers in 2026: Prices, Context Windows, and the One Decision a School Actually Makes

Choosing Among China's LLMs: DeepSeek, Qwen, Kimi, GLM and Four More, From a Hong Kong School's Side of the Table

Tool Calling, MCP and AI Agents: Deciding Which Step a School Will Not Hand Over

Choosing Among Four US LLM Providers: OpenAI, Anthropic, xAI and Google for Schools

School AI Safety in Practice: Hallucination, Prompt Injection and Platform Guardrails

Open Weights or Closed API? Real School Maths on Self-Hosting, and When Privacy Flips the Answer

Reasoning Models in Schools: Chain-of-Thought, Adaptive Thinking, and What Changes for Marking and STEM

Subscribe to Field Notes