Insights

An AI that rewrites the student's essay teaches nothing. The skilled move is rubric-based feedback that diagnoses without doing the work — preserving the struggle where the learning actually lives.

A hallucinating tutor is worse than no tutor — it teaches errors with authority. Grounding a tutor in real tools (a math engine, references, a code runner) is a safety requirement, not a nice-to-have.

The durable win from an AI tutor isn't the physics answer — it's teaching the learner how to plan, self-test, and manage anxiety. Metacognition, not content, is what compounds.

Most ed-tech fads died. Spaced repetition — testing yourself at widening intervals against the forgetting curve — didn't. Here's why it's the highest-leverage thing to wire an AI tutor into, and the skills that do it.

Bloom's 2-sigma problem — that one-on-one tutoring beats classroom instruction by about two standard deviations — was a scaling impossibility for 40 years. Personalized AI tutors are the first plausible answer, with real caveats.

How a solo builder plus an AI agent ship on-brand UIs fast using a DESIGN.md from the registry. The leverage that closes the design gap without a designer.

Every model launch ships with bar charts where the new model wins. Here's a reusable checklist for sanity-checking those numbers — using Grok 4.5's July 2026 launch as the worked example.

Grok 4.5 ranks #4 on the independent Intelligence Index at a price >60% below Opus 4.8 and GPT-5.5. Here's what that price-per-intelligence unlocks for high-volume skill and agent workloads.

xAI reports Grok 4.5 using ~4x fewer output tokens than Opus 4.8 on SWE-Bench Pro. For long agentic loops where output dominates the bill, that can matter more than winning the benchmark.

'On par with GPT-5.5/Codex at lower cost' sounds decisive — until you notice it's a harness score, not a model score. What that means when you pick a coding backend for a skill.

Grok's DeepSearch is an iterative RAG loop with live X integration. Treated as an agent primitive, it changes what a research skill can answer. Here's how it compares to Claude tool-use plus web search.

Stop hardcoding one model. Build a router that sends cheap high-volume work to Grok 4.5, hard long-horizon work to Fable 5, and the balanced middle to Opus 4.8 — with a decision table you can copy.