Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
AI Gamemaster for Voice Games
This talk explores building an AI Gamemaster for a D&D-like voice-based game, focusing on combining game systems, human content, and gamemastery principles.
Building a voice-based agent for entertainment is a huge challenge. Game development is a unique craft that most engineers struggle with: iterating to “find the fun” feels unintuitive. I present our D&D-like experience delivered by an AI Gamemaster, and share how combining game systems, human-authored content, and the craft of gamemastery, has resulted in a compelling experience that players spend hours enjoying.
Demonstrates user authentication via Discord OAuth and anonymous guest session management.
AI Game Master platform enables TTRPG module creation, dynamic narrative adaptation, and monetization.
- ClaudeClaude is Anthropic's flagship family of large language models (LLMs): a high-performance, Constitutional AI system built for safety, complex reasoning, and expert-level collaboration.Claude is a next-generation AI assistant developed by Anthropic, a research firm prioritizing AI safety. The models (including Opus, Sonnet, and Haiku) leverage Constitutional AI to ensure helpful, honest, and harmless outputs, a key differentiator from competitors. Claude excels at complex enterprise tasks: processing massive context windows for in-depth data analysis, generating and reviewing code, and providing expert-level summarization for documents up to 200,000 tokens. It is deployed as a conversational chatbot and via API, offering scalable AI solutions for developers and businesses.
- SonnetSonnet is Anthropic's powerful, mid-tier AI model, balancing frontier intelligence with high-speed, cost-efficient performance for production-scale deployments.Sonnet (currently Claude Sonnet 4.5) is Anthropic’s versatile model, optimized for complex agentic workflows and coding tasks. It delivers state-of-the-art performance, achieving 77.2% on the SWE-bench Verified coding benchmark (cite: 2.2, 2.4). The model is engineered for high-volume, real-time applications like customer support automation and financial analysis, supporting a 200K token context window (cite: 2.8). Pricing is set for efficiency: $3 per million input tokens (cite: 2.8). This makes Sonnet the recommended choice for developers needing top-tier reasoning and coding capability at a practical, scalable cost.
- Prompt EngineeringPrompt Engineering is the discipline of structuring inputs (prompts) to Large Language Models (LLMs) to reliably and efficiently elicit a desired, high-quality output.This is the core skill for maximizing performance from models like GPT-4 and Claude 3: it's the art and science of guiding an AI. The process involves systematic iteration and applying specific techniques to control the model's behavior and reduce 'hallucination.' Key advanced methods include Chain-of-Thought (CoT) prompting, which forces the LLM to process complex problems step-by-step, and Few-Shot prompting (providing 2-3 examples) to establish a clear output format or style. Mastery of these methods directly translates to tangible gains: improved accuracy, reduced API costs from fewer retries, and production-ready outputs for applications like customer service bots or code generation.
- Data trackingData tracking is the systematic collection and analysis of user behavior across digital platforms (websites, apps) to inform business strategy and deliver personalized experiences.This technology monitors user interactions: it records clicks, page views, and purchases to build detailed behavioral profiles. Core mechanisms include first- and third-party cookies, invisible 1x1 pixel tags, and device fingerprinting (a unique profile of browser settings). Tools like Google Analytics and Adobe Analytics process this data, enabling businesses to optimize conversion rates and execute targeted advertising campaigns. However, this power demands compliance: regulations like GDPR and CCPA now mandate explicit user consent, shifting the operational focus from pure collection to responsible data governance and transparency.
- State trackingState Tracking (ST) is the core computational process that maintains a real-time, structured representation of a user’s goals, constraints, and requests throughout an interaction.This technology, often called Dialogue State Tracking (DST) in AI, is mission-critical for task-oriented systems: it estimates the user’s belief state at every turn, typically as a set of slot-value pairs (e.g., 'destination: Paris', 'date: tomorrow'). The DST unit processes natural language understanding (NLU) outputs, updates the belief state, and feeds this structured data to the Dialogue Policy module for the next action. Modern approaches leverage deep learning models like BERT-DST and are validated on benchmarks such as the MultiWOZ dataset, with performance measured by Joint Goal Accuracy (JGA) — a metric that demands perfect state prediction per turn.
Related projects
WeMadeThis.World - A Collaborative Worldbuilding Tool
Seattle
This talk demonstrates a collaborative worldbuilding tool using LLMs to extract and organize user-generated content via interactive role-play…
Better Insights into Team Activity
Los Angeles
The session demonstrates a Jupyter Notebook proof‑of‑concept that combines usage‑tracking dashboards, forecasting models, and a retrieval‑augmented LLM to…
AI Game Master
Seattle
We’ll explain how our bootstrapped AI adventure reached 100 k users, using text, audio, image, and 3D AI, with cost‑saving…
Choose Your Own Adventure
Amsterdam
This talk explores creating a fully AI-generated Choose Your Own Adventure game, covering story generation with LLMs, visual…
Building AI react apps
Seattle
This talk demonstrates building a simple AI app using the Tambo dev tool, enabling AI to control and…
WorldEnder.ai
Seattle
This talk explores using LLMs as interactive engines in text-based RPGs, focusing on structured JSON output validated with…