Simon Willison profile photo

AI educator

Simon Willison

Simon Willison on LLMs

Consistently useful notes, demos, model comparisons, and warnings about practical LLM use without product marketing gloss.

Start with: Read the recent model-roundup posts, then try the llm command-line tool with two or three different providers.

Videos from Simon Willison

The last six months in LLMs in five minutes video thumbnail ►

The last six months in LLMs in five minutes

Educator video

Simon Willison · llm tools, local models, ai engineering

Open Challenges for AI Engineering video thumbnail ►

Open Challenges for AI Engineering

Educator video

Simon Willison · ai engineering, llm tools, developer tools

Open Questions for AI Engineering video thumbnail ►

Open Questions for AI Engineering

Educator video

Simon Willison · ai engineering, llm tools, agents

AI tools for software engineers without the hype video thumbnail ►

AI tools for software engineers without the hype

Educator video

Simon Willison · coding, llm tools, developer tools

Using LLMs for Python Development video thumbnail ►

Using LLMs for Python Development

Educator video

Simon Willison · python, coding, llm tools

Skills

Guides, skills, and tools from Simon Willison

Model analysis

Simon Willison on GPT-6 Astra

Intermediate to advanced

You want a concise independent read of GPT-6 Astra's launch claims, benchmark caveats, long-context results, pricing, and early comparison with Claude Fable 5.1 and GPT-5.6 Sol.

Blog

Simon Willison on LLMs

Beginner to advanced

Use this when you want Simon Willison's material for llm tools and related AI skills.

Learner questions

Who should learn from Simon Willison?

Developers, technical generalists should start here when they need llm tools, prompting, ai safety, local models, and model selection. The strongest fit is a learner who wants material in these formats: blog, open source tools.

What should I do first?

Read the recent model-roundup posts, then try the llm command-line tool with two or three different providers. After that, open one related resource below and write down the exact workflow, concept, or implementation pattern you want to apply.

What problem does this help with?

Consistently useful notes, demos, model comparisons, and warnings about practical LLM use without product marketing gloss. Use this profile when you are comparing educators by topic, level, format, and practical usefulness rather than browsing random AI content.

How do I compare this with other educators?

Compare the skill coverage, the starting recommendation, the educator's own resources, and any videos when available. If you need llm tools, search the directory for that skill and shortlist three profiles before committing to a course, book, or playlist.

Similar videos from other educators

These are not by Simon Willison. They are included only as optional adjacent material after this educator's own videos and resources.

AI Just Crossed the Terrifying Line - Now What? video thumbnail ►

AI Just Crossed the Terrifying Line - Now What?

Similar video from another educator

Kurzgesagt – In a Nutshell · 2026, ai safety, agent security, reward hacking

Don't Use Claude, Use This 320B Local Coding AI Instead video thumbnail ►

Don't Use Claude, Use This 320B Local Coding AI Instead

Similar video from another educator

The Stack · 2026, iquest-q1, local models, coding agents

Build Your Own Agentic Harness in Python - Full Tutorial video thumbnail ►

Build Your Own Agentic Harness in Python - Full Tutorial

Similar video from another educator

Tech With Tim · 2026, Python, agent harnesses, tool calling

OpenAI Security: Controlling Models is Now ‘Hell’ video thumbnail ►

OpenAI Security: Controlling Models is Now ‘Hell’

Similar video from another educator

AI Explained · 2026, ai safety, model control, recursive self-improvement

AI News: Dots, GPT-6.1 Sol, Sonnet 5.5, Gemini 4, and everything you need to know video thumbnail ►

AI News: Dots, GPT-6.1 Sol, Sonnet 5.5, Gemini 4, and everything you need to know

Similar video from another educator

Matt Wolfe · 2026, ai news, openai, gemini

12GB Model, 8 Hours, One 3D Game: OrcaSAQ2 27B Tested video thumbnail ►

12GB Model, 8 Hours, One 3D Game: OrcaSAQ2 27B Tested

Similar video from another educator

Fahd Mirza · 2026, local models, qwen3.8, hermes agent

More related resources

Resource Kind Level Use when
ChatGPT Prompt Engineering for Developers
DeepLearning.AI
Short course Beginner You want a short, structured intro to prompting for software tasks.
Learn Prompting
Sander Schulhoff
Guide Beginner to intermediate You need a broad prompt engineering reference.
Prompt Engineering Guide
DAIR.AI
Guide Beginner to advanced You want examples of prompting techniques and patterns.
The AI Engineer Roadmap
Matt Pocock
Free tutorial Beginner to intermediate You want a guided path through core AI concepts, model selection, the AI engineering mindset, evals, and techniques for improving LLM-powered apps.
Google's AI Principles
Google
Responsible AI principles Beginner Use this as Google's primary statement of the principles it applies to AI development and deployment, alongside the playbook's recommendation to build a framework for trust.
Develop AI-Powered Prototypes in Google AI Studio
Google Cloud
Skill badge course Beginner Use this 45-minute hands-on course to practice prompting, multimodal image and video analysis, and rapid application prototyping in Google AI Studio.
Claude Sonnet 5.5 explained
Anthropic
Model migration explainer Intermediate to advanced Anthropic released Claude Sonnet 5.5 on September 28, 2026. Use this guide to understand the efficiency claims, breaking API changes, and a safe migration test from Sonnet 5.
Ember-1 explained
Fireworks AI
Reasoning-efficient coding model explainer Intermediate to advanced Fireworks released Ember-1 on September 23, 2026 as a Kimi K3-based model trained to use fewer reasoning tokens. Use this explainer to evaluate the quality, cost, latency, and context-growth claims on your own agent workload.
Grok 4.7 explained
SpaceXAI
Frontier coding model launch explainer Intermediate to advanced SpaceXAI released Grok 4.7 on September 21, 2026 for coding, agentic tasks, and knowledge work. Use this guide to compare its task reliability and total cost with your current model.
Union Alpha revealed as Pareto 26.9
Unbiased
Multi-model routing launch explainer Intermediate to advanced Union Alpha was revealed as Unbiased's Pareto 26.9 on September 17, 2026: a hosted system that routes work across several models and returns one checked answer.
Qwen3.8-Omni-Flash explained
Qwen
Omnimodal model launch explainer Intermediate Qwen3.8-Omni-Flash launched September 18, 2026 for long audio and video analysis, text answers, web search, and tool-calling workflows.
GPT-Live-1 in the API
OpenAI
Voice agent model launch Intermediate You want OpenAI's September 10, 2026 launch of GPT-Live-1 in the API for full-duplex voice agents, including its $0.05-per-minute front-end pricing and guidance on pairing it with a backend model and agent harness.