Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
gh cli: Local Agents for PRs
Learn to use the `gh` CLI with local agents to open pull requests and respond to comments, combining local guidance with the GitHub UI.
I often find the UI for assigning agents (like copilot, etc) to tasks directly in github to be restrictive – they lack context and can’t be guided as easily. But I do like the github PR UI for providing specific feedback.
Use both – have the local agent use the gh cli to open the pr and respond to comments. Extra feedback can be given in the local chat if needed
- GPT-4GPT-4 is OpenAI’s large multimodal model: it processes both text and image inputs, delivering human-level performance on complex professional and academic benchmarks.This is OpenAI’s latest milestone in scaling deep learning: a large multimodal model accepting both text and image inputs. It demonstrates a significant capability leap over its predecessor, scoring in the top 10% on a simulated bar exam (GPT-3.5 scored in the bottom 10%). The model handles nuanced instructions and long-form content, supporting context windows up to 32,768 tokens (32K model). This capacity allows processing up to 25,000 words in a single, complex prompt. GPT-4 is engineered for enhanced reliability, steerability, and advanced reasoning across diverse tasks.
- Claude-3Claude-3 is Anthropic's state-of-the-art multimodal model family (Opus, Sonnet, Haiku), setting new industry benchmarks for intelligence, speed, and vision capabilities.Claude-3, developed by Anthropic, is a powerful family of three generative AI models: Opus, Sonnet, and Haiku. Opus, the flagship, excels in complex reasoning, outperforming peers on key benchmarks (MMLU, GPQA) and supporting a 200,000-token context window. Sonnet offers an optimal balance for enterprise workloads, delivering performance that is 2x faster than its predecessor, Claude 2.1. Haiku is the fastest and most cost-effective option, capable of processing a 10,000-token research paper (including charts) in under three seconds. All three models are multimodal, featuring strong vision capabilities for analyzing charts, diagrams, and PDFs alongside text, enabling advanced data extraction and analysis.
- Llama-2Llama 2 is Meta AI's powerful, openly accessible family of large language models (LLMs), featuring models from 7B to 70B parameters for research and commercial applications.Llama 2 is Meta AI's next-generation LLM family, released for free research and commercial use. The collection includes both pre-trained foundation models and instruction-tuned 'Chat' variants, scaling from 7 billion (7B) up to 70 billion (70B) parameters. Key technical upgrades over Llama 1 involve training on 2 trillion tokens (40% more data) and doubling the context length to 4096 tokens. The Llama-2-chat models were rigorously aligned using Reinforcement Learning from Human Feedback (RLHF), positioning them as a top-tier, openly available option for developers building advanced generative AI solutions.
- LangChainThe open-source framework for building and deploying reliable, data-aware Large Language Model (LLM) applications.LangChain is the essential framework for engineering LLM-powered applications: it simplifies connecting models (like GPT-4 or Claude) to external data, computation, and APIs. The platform provides a modular set of components—Chains, Agents, Tools, and Memory—allowing developers to quickly build complex workflows like Retrieval-Augmented Generation (RAG) pipelines and sophisticated conversational agents. Its Python and JavaScript libraries, combined with LangChain Expression Language (LCEL), offer a standardized interface for rapid prototyping and moving applications to production with confidence.
- OpenAI APIOpenAI API: Your direct gateway to cutting-edge AI models (GPT-4o, DALL-E 3, Whisper), enabling scalable, multimodal intelligence integration into any application.The OpenAI API provides authenticated, programmatic access to a powerful suite of generative AI models. Developers leverage REST endpoints and official libraries (Python, Node.js) to integrate capabilities like advanced text generation (GPT-4o), image creation (DALL-E 3), and speech-to-text transcription (Whisper). This platform is engineered for scale, supporting millions of daily requests for tasks from complex reasoning to real-time customer support agents, ensuring your application gets reliable, state-of-the-art intelligence.
Related projects
Brief: build context infrastructure so agents stop guessing
Seattle
This talk introduces a CLI tool that builds deterministic codebase context for agents, showing how static analysis and…
Exploring multi tasking with AI agents
Seattle
Explore post-IDE coding with AI agents, bespoke UIs for multitasking, and tools for hands-off agent workflows, containerized code…
From Tool Call to React Component: Building Generative UI for Agentic Workflows
San Diego
See how AI agents generate interactive React components directly in chat for agentic workflows. Learn about the callback…
From Autonomy to Observability: Running AI Agents Safely on Your Own Machine
Seattle
Explore local AI agent execution and observability. Learn how to monitor system actions, understand failures, and manage resource…
Agent Runner
Seattle
This talk demonstrates Agent Runner, a desktop app using BAML for type-safe AI agents, accessible via hotkey with…
Dual-Agent MCP Development: Builder and Tester in the Same Conversation
Seattle
See a live demo of building a 44-tool MCP server using two collaborating Claude agents: one builds, one…