Tendril
Loading…
New · guided experience
A curated walkthrough of the library — ordered lessons, a 15-question quiz between each, and 3 next-steps so you stay in flow. Earn XP, badges, and a streak as you go.
Library · 6440 lessons · Advanced view
Search below, or pick a shelf. Kids and teens get age-tier shelves; College+ and Career+ organize the same library around life stage and situation.
Lessons handpicked for the Advanced shelf.
Agents are only as useful as their tools. Tour the big three — filesystem, browser, code execution — plus the emerging MCP ecosystem, with examples of what each unlocks.
Ollama turns 'I want to run an LLM locally' into a one-line install and a two-word command. Here's the stack, the key commands, and the models worth pulling first.
A circuit is a small sub-network inside a big model that implements one specific behavior. Finding circuits is how researchers prove how a model does what it does.
A transformer processes a token through many layers before outputting a prediction. The logit lens shows you what the model would predict if it stopped at each layer along the way.
Fresh Advanced lessons added to the library.
AI writes Java for you faster than your teacher can say 'Scanner'. Using it without cheating yourself out of the class is the real skill.
A lot of civics class is pretending you read the news. AI makes it possible to actually understand a bill, a court case, or a political ad in under ten minutes.
On October 30, 2023, President Biden issued the most detailed executive order on AI ever signed. In January 2025, President Trump rescinded it. The policy churn matters.
In 2024, California almost passed the first US state law targeting frontier AI safety. Governor Newsom vetoed it. The fight reshaped the AI policy landscape.
Browse everything
Subject tracks
Tap a tile to filter the library — or pick “Surprise me” below for a randomized starter set.
Agents are only as useful as their tools. Tour the big three — filesystem, browser, code execution — plus the emerging MCP ecosystem, with examples of what each unlocks.
Ollama turns 'I want to run an LLM locally' into a one-line install and a two-word command. Here's the stack, the key commands, and the models worth pulling first.
A circuit is a small sub-network inside a big model that implements one specific behavior. Finding circuits is how researchers prove how a model does what it does.
A transformer processes a token through many layers before outputting a prediction. The logit lens shows you what the model would predict if it stopped at each layer along the way.
AI does not read letters. It reads tokens, which live as vectors in a space of meaning. Learn how text becomes numbers you can do math on.
Every new model claims a new high score. Before you trust a leaderboard, learn what benchmarks actually measure — and what they miss.
AI did not start in 2022. It has decades of wrong turns and breakthroughs. Knowing the history helps you spot hype from real progress.
Physics needs intuition. PhET simulations plus AI explanations give you that intuition faster than any textbook.
Google's NotebookLM lets you upload textbooks, lectures, and notes, then chat with them. This is the most underrated study tool of 2026.
A paper without code is often a paper without truth. Papers With Code links claims to runnable proof. Where Claims Meet Code Papers With Code is a community-maintained site that pairs AI papers with their open-source implementations and benchmark results.
Benchmarks are how AI progress gets measured. Understanding them is the first step in reading any AI claim.
Automatic metrics miss a lot. Humans catch what metrics cannot. Here is how to run a simple human eval.
If the same paragraph appears a million times in your training data, your model will memorize it. Deduplication quietly makes AI better.
The raw web is 99 percent garbage. Filtering it down to the 1 percent worth training on is one of the highest-leverage steps in modern AI.
The imitation game became famous, but most AI researchers now think it measures the wrong thing.
A 2013 paper from Google showed that words could live as points in space, with analogies as arithmetic.
In 2024, a new class of models traded fast answers for slow, deliberate thinking, and benchmarks jumped.
Two frontier models, same subscription price, very different personalities. Pick by vibe, not by benchmark — here is how to figure out which one clicks for you.
Everyone brags about million-token windows. Here is what you can actually do with one when you learn how Gemini 2.5 Pro handles long documents.
Every LLM hallucinates. Perplexity's Sonar family solves it by grounding answers in live web results with citations. Here is when to use Sonar instead of Claude or GPT.
ElevenLabs voices are indistinguishable from humans. That is a feature and a fraud vector. Here is the production checklist before you clone anyone.
xAI's code-specialist model ships strong benchmarks. Here is how it actually feels in a real IDE.
Mistral Large 2 quietly beats the US frontier models on several non-English benchmarks. Here is why it should be your default for European languages.
Mistral Small is the right open-weights model when you need to run on a laptop, a phone, or an on-prem CPU box.
Codestral Mamba ditches transformers for a state-space model. The result: linear-time long-context coding at a fraction of the attention cost.
DeepSeek V3.5 is the open-weights model that keeps punching above its weight class on coding benchmarks at a fraction of the cost.
Qwen 3 Coder is the open-weights coding specialist from Alibaba. Strong benchmarks, good IDE ergonomics, and cheap to run.
Moonshot's Kimi K2 specializes in long documents and retrieval-heavy workflows. Here is when it beats a generalist.
All three claim to be the best. Pick tasks you actually care about, run the same prompt across all three, and you'll build your own benchmark.
The agent market matured fast. Here's the field map — frontier labs, frameworks, browsers, local stacks, benchmarks — so you can pick the right tool without shopping by hype.
Underneath every agent framework is the same primitive — the model returns a structured tool call, you execute it, you feed the result back. Master this loop and every framework looks familiar.
Model Context Protocol is the most important open standard in agents. One protocol, 1,200+ servers, and your agent can plug into almost any system. Here's how it actually works.
One smart agent is fine. Two agents checking each other's work is better. Master the canonical orchestration patterns: planner/executor, judge/worker, debate, and swarm.
LangGraph became the production favorite in 2026 for good reasons — explicit state, checkpointing, first-class MCP. Build a real agent end-to-end and learn why.
Claude Code isn't just a coding assistant — it's a general agent runtime with MCP, subagents, hooks, and skills. Treat it that way and you get a free, powerful platform.
Computer Use lets Claude see your screen and use it — mouse, keyboard, apps. The capability is real, the gotchas are real. A hands-on look at what works in 2026.