►
Local AI Is Only 4 Months Behind. I Did the Math.
Ash · 2026, local AI, open-weight models, Qwen3.8
AI directory search
Search across educators, skills, and resources.
Use this when you know the topic you need: Claude Code, MCP, evals, RAG, agents, product, coding, prompting, foundations, or model internals.
77 matches for "models"
Video matches
Watch first when you want a fast feel for the topic before opening courses, docs, or profiles.
►
►
Small Models, Big Results: Training a Finance Agent for Under $500 — Charles Dickens, Snorkel AI
AI Engineer · 2026, reinforcement learning, small models, financial agents
►
Don't Use Claude, Use This 320B Local Coding AI Instead
The Stack · 2026, iquest-q1, local models, coding agents
►
Build Your Own Agentic Harness in Python - Full Tutorial
Tech With Tim · 2026, Python, agent harnesses, tool calling
►
Recursive's $670M Bet on Self-Improving AI, Sonnet 5.5 Hits 70%, Elon Co-Leads Pentagon Push EP 299
Peter H. Diamandis · 2026, recursive self-improvement, claude sonnet 5.5, open models
►
OpenAI Security: Controlling Models is Now ‘Hell’
AI Explained · 2026, ai safety, model control, recursive self-improvement
►
12GB Model, 8 Hours, One 3D Game: OrcaSAQ2 27B Tested
Fahd Mirza · 2026, local models, qwen3.8, hermes agent
►
Code with Claude London 2026: Opening Keynote
Claude · 2026, claude code, coding agents, frontier models
►
Google's AI endgame is here... everything you missed at I/O 2026
Fireship · 2026, gemini, frontier models, multimodal ai
Educators
Jeremy Howard
fast.ai · Intermediate
One of the best practical routes into training and using real models.
Skills
Deep learning, PyTorch, Model training
Andrej Karpathy
Neural Networks: Zero to Hero · Intermediate
Excellent from-scratch explanations of neural networks and language models.
Skills
Neural networks, Backprop, LLM internals
Simon Willison
Simon Willison on LLMs · Beginner to advanced
Consistently useful notes, demos, model comparisons, and warnings about practical LLM use without product marketing gloss.
Skills
LLM tools, Prompting, AI safety, Local models, Model selection
Nathan Lambert
RLHF Book · Advanced
Good route into how models are trained after pretraining.
Skills
RLHF, Post-training, Alignment
Latent Space
Latent Space · Intermediate to advanced
Good for staying current on how AI builders think about tools and models.
Skills
AI engineering, Industry context, Model ecosystem
Cohere For AI
Cohere For AI · Advanced
Useful for people who want research context and open science around language models.
Skills
NLP research, Open models, Multilingual AI
Large Language Models for Product Managers
Polly Allen on Maven · Beginner to intermediate
Concise LLM fundamentals course for PMs who need to vet opportunities, scope projects, and rally stakeholders.
Skills
LLM fundamentals, Product scoping, Stakeholder alignment, AI prototyping
Maggie Appleton
AI and language model essays · Beginner to intermediate
Good for understanding how people experience and design with language-model interfaces.
Skills
AI UX, Language model interfaces, Conceptual models
Nils Reimers
Sentence Transformers · Intermediate
Essential education for understanding sentence embeddings and semantic search in practice.
Skills
Embeddings, Semantic search, Vector search, NLP
Phil Schmid
Hugging Face LLM tutorials · Intermediate to advanced
Hands-on guides for fine-tuning, serving, and using open-source models with Hugging Face tooling.
Skills
Open models, Fine-tuning, Deployment, Transformers
Lewis Tunstall
NLP with Transformers · Intermediate
Strong practical guide to using Transformer models for real NLP tasks.
Skills
Transformers, NLP, Open models, Fine-tuning
Brandon Rohrer
Brandon Rohrer ML explanations · Beginner to intermediate
Good plain-English explanations of ML concepts, pitfalls, and practical mental models.
Skills
ML foundations, Deep learning, Model intuition
Providers and platforms
Hugging Face
Hugging Face Learn · Beginner to advanced
One of the best free ecosystems for learning open-source AI by building with models, datasets, spaces, agents, context engineering, and MCP workflows.
Topics
Agents, Context engineering, MCP, Transformers, Post-training, Open models
Anthropic
Anthropic Academy and Claude docs · Beginner to advanced
Official material for learning Anthropic's current Claude family, model tradeoffs, Claude Code, MCP, computer use, practical prompt workflows, and team model-governance workflows without relying on third-party summaries.
Topics
Claude models, Claude Code, MCP, Computer use, AI fluency, Frontier model selection, Model governance, Release notes
TypeSafe AI
TypeSafe AI and Jev documentation · Intermediate to advanced
Official material for using Jev where software needs a bounded judgment, probability, or score rather than generated prose.
Topics
Jev, System One models, Typed decisions, Calibrated probabilities, Choice, Score, Noul, RLCD
OpenAI
OpenAI docs, Academy, and Cookbook · Beginner to advanced
Official model and implementation material for learning GPT-6 Astra and cost-sensitive GPT-5.6 choices, Codex workflows, subagents, memories, agent evals, MCP and connector patterns, retrieval, background jobs, prompt engineering, production best practices, model optimization, structured outputs, and OpenAI's Academy learning path.
Topics
GPT-6 Astra, GPT models, Reasoning models, Model selection, Agents, Subagents, RAG, Structured outputs, MCP, Evals, Memories
Stanford CS224N
Natural Language Processing with Deep Learning · Intermediate to advanced
A deep route into the NLP concepts behind embeddings, attention, and modern language models.
Topics
NLP, Transformers, Embeddings, Language models
Still useful for understanding vision models, training loops, backpropagation, and representation learning.
Topics
Computer vision, Deep learning, Model training
Replicate
Replicate docs and examples · Beginner to intermediate
Fast route to test many hosted AI models without managing infrastructure.
Topics
Model APIs, Prototyping, Image generation, LLM apps
OpenRouter
OpenRouter docs · Beginner to intermediate
Useful for learning model comparison, latest-family aliases, routing, fallback behavior, agent construction, project-specific evals, and API-compatible experimentation across proprietary and open model families.
Topics
Model routing, Model comparison, Auto Router, Agent SDK, Coding-agent harnesses, GPT models, Claude models, Gemini, Llama, Mistral, DeepSeek, Qwen, API examples, Evaluation
Fireworks AI
Fireworks AI model catalog · Intermediate to advanced
Official material for comparing serverless and dedicated model serving, training specialized models, and measuring quality, token use, cost, and task duration on production-shaped evaluations.
Topics
Ember-1, Kimi K3, Serverless inference, Dedicated deployment, Model training, Model evaluation, Reasoning efficiency
Google AI for Developers
Gemini API model docs · Beginner to advanced
Official Gemini material for learning Gemini 3.8 Flash and the current stable, preview, latest, and experimental model lineup, plus the now-GA Interactions API, Lyria music generation, prompt design, function calling, background execution, Deep Research, Computer Use, Hooks, Live API, File Search, coding-agent setup, multimodal tradeoffs, and AI Studio workflows.
Topics
Gemini 3.8 Flash, Gemini models, Multimodal AI, Long context, Model selection, AI Studio, Interactions API, Background execution, Deep Research, Computer Use, Hooks, Live API, Coding agents, Music generation, File Search, API examples
Meta Llama
Meta Model API and Llama docs · Beginner to advanced
Official path into current Llama families, prompt formats, open-weight deployment, Meta's newer hosted Model API surface, and integration decisions for both local and managed workflows.
Topics
Llama, Open models, Meta Model API, Muse Spark, Muse Code, Local models, Fine-tuning, Model deployment, Safety models
Mistral AI
Mistral models docs · Beginner to advanced
Official material for comparing current Mistral families such as Devstral, Magistral, Voxtral, OCR, and newer Small and Medium models across coding, reasoning, and multimodal use cases.
Topics
Mistral models, Open models, Model selection, Agents, Coding, Reasoning, Multimodal AI
Cohere
Cohere model docs · Beginner to advanced
Official material for learning Cohere chat, embedding, rerank, and LLM University material, especially for grounded enterprise retrieval workflows.
Topics
Command models, RAG, Embeddings, Reranking, Enterprise AI, Model selection, Course material
DeepSeek
DeepSeek API docs · Beginner to advanced
Official DeepSeek API material for learning model access, OpenAI-compatible usage, reasoning mode, pricing, and current migration details from the live models list rather than third-party screenshots.
Topics
DeepSeek, Reasoning models, Coding models, OpenAI-compatible APIs, Model selection
Official Qwen material for learning the Qwen3 family, multilingual and multimodal capabilities, local deployment paths, and function-calling behavior.
Topics
Qwen, Open models, Multilingual AI, Coding agents, Multimodal AI, Model selection
xAI
xAI Grok model docs · Beginner to advanced
Official xAI material for learning current Grok choices across chat, coding, image, video, and voice APIs, plus Build workflows, aliasing, and release-version behavior.
Topics
Grok 4.6, Grok Build, Reasoning models, Coding models, Image models, Video models, Model selection
Together AI
Together AI model catalog · Beginner to advanced
Useful for learning which open and hosted models are available through a unified inference platform.
Topics
Open models, Serverless inference, Llama, Qwen, DeepSeek, Mistral, Model hosting
Ollama
Ollama docs · Beginner to intermediate
Practical route into running and testing local models on your own machine.
Topics
Local models, LLM tools, AI engineering, Privacy
llama.cpp
llama.cpp examples · Intermediate to advanced
Core educational repo for understanding local inference, quantization, and efficient model running.
Topics
Local models, Inference, Quantization, AI engineering
Learning paths
Frontier models and model selection
Builders choosing between Claude, GPT, Gemini, Llama, Mistral, Cohere, DeepSeek, Qwen, Grok, Perplexity, and hosted open models
Learn first
- When to use Claude or GPT-class reasoning models for complex coding, analysis, and long-horizon agent work
- How Gemini, Llama, Mistral, Cohere, DeepSeek, Qwen, Grok, and Perplexity differ by modality, openness, retrieval, coding, and price
- Context windows, output limits, latency, pricing, tool support, and eval-based routing
- How to migrate safely when frontier model versions change
Good matches
Open next
Resources
►
Neural Networks: Zero to Hero
Video course · Andrej Karpathy · Intermediate
You want to understand neural networks and language models from code.
model internals, neural networks, coding
►
Practical Deep Learning for Coders
Free course · fast.ai · Intermediate
You can code and want a practical route into training models.
deep learning, pytorch, training
LLM Fundamentals
Free tutorial · Matt Pocock · Beginner
You need clear mental models for system prompts, tokens, context windows, tools, and agents before building or using AI systems seriously.
llm fundamentals, tokens, context windows, tools, agents
Promptfoo
Open-source eval and red-team framework · OpenAI / Promptfoo · Intermediate to advanced
Declarative regression tests and side-by-side comparisons of prompts, models, RAG systems, and agent configurations, especially when red teaming is also required.
evals, llm evaluation, ai quality, open-source frameworks
Microsoft Foundry evaluations
Cloud evaluation portal and SDK · Microsoft · Intermediate to advanced
Microsoft Foundry teams evaluating models, RAG systems, and single- or multi-turn agents for quality, safety, task completion, and tool use.
evals, llm evaluation, ai quality, cloud and provider evals
Amazon Bedrock Evaluations
Managed model and RAG evaluation jobs · Amazon Web Services · Intermediate to advanced
AWS teams comparing Bedrock models or assessing knowledge bases and external RAG sources with automated metrics, LLM judges, or human reviewers.
evals, llm evaluation, ai quality, cloud and provider evals
Language Model Evaluation Harness
Language-model benchmark runner · EleutherAI · Intermediate to advanced
Reproducible few-shot and zero-shot evaluation of base or instruction-tuned language models on established academic benchmarks.
evals, llm evaluation, ai quality, benchmarks and learning resources
Lighteval
Multi-backend LLM evaluation toolkit · Hugging Face · Intermediate to advanced
Teams evaluating local, distributed, or API-served models across a large multilingual task catalog while retaining sample-level results.
evals, llm evaluation, ai quality, benchmarks and learning resources
Beginner: Introduction to Generative AI
Learning path · Google Cloud · Beginner
Use this four-activity learning path for an introductory overview of generative AI, large language models, and responsible AI principles.
generative ai, large language models, responsible ai, foundations, learning path
NVIDIA Kumo Tabular explained
Tabular foundation model explainer · NVIDIA · Intermediate to advanced
NVIDIA released Kumo Tabular on September 29, 2026. Use this guide to understand its in-context prediction workflow, reproduce a baseline, and test its vendor-reported results on your own tables.
kumo tabular, tabular foundation models, classification, regression, in-context learning
Ember-1 explained
Reasoning-efficient coding model explainer · Fireworks AI · 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.
ember-1, kimi k3, reasoning models, reasoning tokens, cost optimization
Union Alpha revealed as Pareto 26.9
Multi-model routing launch explainer · Unbiased · 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.
pareto 26.9, union alpha, model routing, ensembles, coding agents
Qwen3.8-Omni-Flash explained
Omnimodal model launch explainer · Qwen · Intermediate
Qwen3.8-Omni-Flash launched September 18, 2026 for long audio and video analysis, text answers, web search, and tool-calling workflows.
qwen3.8, omnimodal models, audio, video, agents
Introducing System One Models & Jev
System One Model launch · TypeSafe AI · Intermediate to advanced
Jev launched on September 15, 2026 as TypeSafe AI's first System One model: a non-chat model that turns application state into typed decisions and probabilities for software workflows.
jev, system one models, rlcd, structured decisions, calibrated probabilities
TypeSafe System One and Jev introduction
Model and API introduction · TypeSafe AI · Intermediate
TypeSafe AI provides Jev, SDKs, an HTTP API, patterns, and cookbooks for building software around narrow typed judgments.
jev, system one models, choice, score, noul
An alignment assessment of recent cybersecurity incidents
AI safety incident assessment · Anthropic · Advanced
You want Anthropic's September 9, 2026 assessment of four incidents in which Claude models gained unauthorized access to real third-party systems during cybersecurity evaluations, including the model behaviors and evaluation-design failures involved.
anthropic, ai safety, cybersecurity, agent evaluation, alignment
The AI policy window is open. We need to act.
Frontier AI safety policy guide · OpenAI · Advanced
You want OpenAI's September 9, 2026 policy proposal on frontier AI standards, independent assessments, incident reporting, and preserving human control as capabilities advance.
openai, ai safety, frontier models, evaluations, governance
Claude Fable 5.1 and Claude Mythos 5.1
Model launch and safety guide · Anthropic · Advanced
You want Anthropic's September 1, 2026 model announcement covering Fable 5.1 for general availability and Mythos 5.1 for trusted-access research use.
anthropic, claude, frontier models, coding agents, ai safety
Gemini 3.8 Flash launch
Model launch and selection guide · Google AI · Intermediate
You want Google's September 2, 2026 launch details for Gemini 3.8 Flash and Flash Cyber, including their positioning for agentic workflows and cybersecurity.
google, gemini, frontier models, agentic workflows, cybersecurity
Muse Spark 1.3
Model launch and selection guide · Meta AI · Intermediate
You are comparing frontier models for long-horizon coding or knowledge work and need Meta's September 2, 2026 release notes on Muse Spark 1.3's tool use, instruction following, user steering, multitasking, model self-awareness, and availability through Muse Code and Meta Model API.
meta, muse spark 1.3, frontier models, coding agents, long-horizon agents
Agentic models, measured on the injections that move money
Open security benchmark · Hugging Face Community · Intermediate to advanced
You want a reproducible September 5, 2026 benchmark for comparing how agentic models handle indirect prompt injection, with public data, a public harness, control runs, tool-call traces, and outcome metrics tied to unauthorized payment actions.
agents, prompt injection, agent security, evals, tool use
Hugging Face Skills
Open-source skills and tutorial · Hugging Face · Intermediate to advanced
You want reusable, open-source agent skills for training, fine-tuning, evaluating, quantizing, and publishing models with Codex, Claude Code, Gemini CLI, or another skills-compatible coding agent.
hugging face, agent skills, codex, claude code, model training
Qwen Code September 3 weekly update
Coding agent release notes · Qwen · Beginner to advanced
You want Qwen's September 3, 2026 practical guide to its latest coding-agent workflows, including learning-oriented output styles, scheduled tasks, a browser terminal, safer workspace writes, skills, MCP stability, and current vision-model support.
qwen code, coding agents, output styles, scheduled tasks, web shell
GPT-6 Astra launch overview
Model launch · OpenAI · Intermediate to advanced
You want OpenAI's September 3, 2026 launch overview for GPT-6 Astra, including its rollout, computer-use and coding focus, long-context behavior, benchmark disclosures, pricing, and new Codex context-retrieval workflow.
openai, gpt-6 astra, frontier models, coding, computer use
Lyria 3.5 music generation
Model docs · Google AI for Developers · Beginner to intermediate
You want Google's September 3, 2026 preview documentation and examples for generating short clips or full songs from text and image inputs with the Lyria 3.5 Clip and Pro models.
google, lyria 3.5, music generation, audio generation, multimodal
Simon Willison on GPT-6 Astra
Model analysis · Simon Willison · 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.
gpt-6 astra, model selection, benchmarks, coding agents, long context
Claude Fable 5.1 model overview
Model docs · Anthropic · Intermediate to advanced
You need Anthropic's September 1, 2026 source of truth for Claude Fable 5.1 and invite-only Mythos 5.1, including model IDs, pricing, availability, long-horizon agent strengths, and breaking changes from Fable 5.
anthropic, claude fable 5.1, claude mythos 5.1, frontier models, model selection
Multi-Vector Embedding Models with Sentence Transformers
Practical guide · Hugging Face · Intermediate to advanced
You want a runnable guide to ColBERT-style late-interaction retrieval, including MaxSim scoring, retrieve-and-rerank, indexing, visual document retrieval, evaluation, and the storage-quality tradeoff versus dense embeddings.
hugging face, sentence transformers, rag, retrieval, embeddings
Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers
Training guide · Hugging Face · Advanced
You need an end-to-end August 26, 2026 recipe for adapting a late-interaction retriever to your own domain, from datasets and losses through training, evaluation, and index optimization.
hugging face, sentence transformers, rag, retrieval, fine-tuning
OpenAI Tool search
Guide · OpenAI · Intermediate to advanced
Your agent has a large function, namespace, or MCP catalog and you want GPT-5.4 or later models to load only the tool definitions needed at runtime, reducing context use while preserving prompt-cache efficiency.
openai, agents, tool search, deferred tools, mcp
How to Choose the Best AI Model (Live, in Your Editor)
Model selection guide · OpenRouter · Intermediate
You want a practical six-step workflow for shortlisting models from live data, testing them on your own prompts, measuring cost per completed task, and choosing or routing from inside a coding assistant.
openrouter, model selection, evals, benchmarks, cost
OpenAI external models
Guide · OpenAI · Intermediate
You want to learn how OpenAI handles access to non-OpenAI model families before designing a mixed-provider or routed workflow.
openai, external models, model routing, open models, model selection
OpenAI model guide
Model docs · OpenAI · Beginner to advanced
You need to choose between current GPT-5.6 variants, smaller GPT-5.4 variants, reasoning levels, tool support, and cost-sensitive API paths, including the current default starting points of GPT-5.6 Sol, Terra, and Luna.
openai, gpt, gpt-5, reasoning models, model selection
OpenAI all models
Model catalog · OpenAI · Beginner to advanced
You want the current full OpenAI model catalog, including older and deprecated entries, before wiring exact model IDs into evals, tooling, or migrations.
openai, model catalog, gpt, codex, reasoning models
OpenAI Codex Prompting Guide
Guide · OpenAI · Intermediate to advanced
You want the newest OpenAI guidance for prompting Codex-style coding workflows, especially when using newer Codex models with preambles and execution phases.
codex, prompting, coding agents, responses api, agentic software engineering
Codex config reference
Reference · OpenAI · Intermediate
You need the current OpenAI reference for Codex configuration files before standardizing repo settings, approvals, models, or execution behavior.
codex, config, requirements.toml, config.toml, coding agents