# LLM Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/llm
> Markdown URL: https://aitinkerers.org/technologies/llm.md
> Technology record last updated: 2026-02-24T08:34:56Z
> Generated: 2026-09-20T18:55:32Z

Large Language Models (LLMs) are deep learning models, built on the Transformer architecture, that process and generate human-quality text and code at scale.

LLMs are a class of foundation models: massive, pre-trained neural networks (often with billions to trillions of parameters) that leverage the self-attention mechanism of the Transformer architecture (introduced in 2017) to predict the next token in a sequence. Trained on vast datasets (e.g., Common Crawl's 50 billion+ web pages), these models—like GPT-4, Gemini, and Claude—acquire predictive power over syntax and semantics. They function as general-purpose sequence models, enabling critical applications such as complex content generation, language translation, and automated code completion (e.g., GitHub Copilot). Their core value: generalizing across diverse tasks with minimal task-specific fine-tuning.

- Official technology site: https://en.wikipedia.org/wiki/Large_language_model
- Public AI Tinkerers demos and talks: 123
- Result page: 1 of 6

## Recent Public Talks and Demos

### [From idea to production in one loop: how a PM, a data bot and a coding agent ship at Fasset.](https://lahore.aitinkerers.org/talks/rsvp_c7poPoSKGUM)

Fasset is a global stablecoin backed neobank which gives access to digital banking and wealth building tools. It serves the freelancer, remote workers many of them are young professionals in Pakistan. This demo will be a product manager's view of how an idea reaches production with AI at every step, in three demos: prototype first (the team builds clickable prototypes with Claude instead of writing PRDs); decide with data (Dasset, an internal Slack bot that answers plain-English questions against a governed warehouse layer); and ship (Fasset Harness, a Claude Code plugin that makes coding agents work from human-reviewed test trees).

- Event context: AI Tinkerers Lahore: September 19, 2026 — 2026-09-19 — Lahore
- Public talk page: https://lahore.aitinkerers.org/talks/rsvp_c7poPoSKGUM

### [Teaching an Agent to Behave Like a Data Scientist: A Statistical Harness for Tabular ML](https://amsterdam.aitinkerers.org/talks/rsvp_dYE4vQbTMCM)

We built QAgent, an agent that plans and acts like a human data scientist. Coding harnesses such as Claude Code treat data science as a coding problem and miss the nuances: checking for bias, treating data leakage, and ultimately producing results that look correct but rest on flawed methodology. QAgent fixes that with a harness built for data science: the right interface to the data, and constraints that unlock principled data science capabilities in LLMs.

- Event context: AI Tinkerers Demo Night: Agents in Various Forms — 2026-09-03 — Amsterdam
- Public talk page: https://amsterdam.aitinkerers.org/talks/rsvp_dYE4vQbTMCM

### [AI Innovation at Ingram Micro](https://orange-county.aitinkerers.org/talks/rsvp_XNSVkIWqm8w)

Joyce will be giving an overview of tools that Ingram is developing and is using, to support their global multi-billion dollar business, with over 50 years of history and data within the organization.

- Event context: AI Tinkerers OC - August 19th, 2026 Meetup @ Ingram Micro — 2026-08-20 — Orange County
- Public talk page: https://orange-county.aitinkerers.org/talks/rsvp_XNSVkIWqm8w

### [What aviation safety teaches us about human-in-the-loop](https://orange-county.aitinkerers.org/talks/rsvp_WHC6Ea08Nhg)

Abstract: When an agentic automation can't go all the way or needs help, we've become used to falling back on "human-in-the-loop". We've all been through the journey of hitting Enter on agent permissions to giving in and running in YOLO mode. However, there is a deep literature that looks at exactly this problem of humans and automation interplaying. There is also a painful history of aviation disasters involving cockpit automation. These can be helpful when undersrtanding the current agent/human design problem.

- Event context: AI Tinkerers OC - August 19th, 2026 Meetup @ Ingram Micro — 2026-08-20 — Orange County
- Public talk page: https://orange-county.aitinkerers.org/talks/rsvp_WHC6Ea08Nhg

### [Putting a leash on LLM's with BAML](https://atlanta.aitinkerers.org/talks/rsvp_h6YMTIcqU7Q)

VibeKeys is a piano learning app designed to test the boundaries of interactive AI education capabilities. I am also testing the boundaries of building with AI in coding the app, which is 100% coded by AI, yet meticulously reviewed by a human. I’ll show an app demo where the student plays a section incorrectly, and how the voice AI agent is engaged to provide insight to the student through its multi-level agent orchestration and context engineering system. The app has an interactive context layer that allows low-latency responses for simple tool calling combined with more escalated handoff to a deep-reasoning “Music Education” agent. We will then walk through key code sections of the AI orchestration layer to see how easy BAML makes it to implement multi-agent LLM's with in-app tool-calling capabilities. Optional: A brief discussion of an AI skill I developed to curate project-specific principles that reflect the unique taste of your project and help the AI follow those principles across business, product, and technical domains.

- Event context: AI Tinkerers Atlanta x AI Collective: Community Demos at ATL Tech Week — 2026-08-13 — Atlanta
- Public talk page: https://atlanta.aitinkerers.org/talks/rsvp_h6YMTIcqU7Q

### [Message encryption tool](https://paris.aitinkerers.org/talks/rsvp_Yv9XlRBxVx4)

A tool that encrypts and decrypts messages

- Event context: AI on Rails: Level Up the Way You Code with AI w/ Paris.rb — 2026-08-04 — Paris
- Public talk page: https://paris.aitinkerers.org/talks/rsvp_Yv9XlRBxVx4

### [AI at scale \[FR\]](https://paris.aitinkerers.org/talks/rsvp_v8TZx7I87mc)

[Talk en Français] Appliquer l'IA à l'échelle d'une boîte de 1 200 personnes implique des challenges intéressants, Maxime l'évoquait déjà dans son interview donnée aux Échos sur son usage de l'IA. Il viendra nous parler de ce défi de scale à travers un workflow de soutien aux équipes Sales qu'il est en train de mettre en place, en s'adaptant à 15 équipes avec des besoins différents différents.

- Event context: AI on Rails: Level Up the Way You Code with AI w/ Paris.rb — 2026-08-04 — Paris
- Public talk page: https://paris.aitinkerers.org/talks/rsvp_v8TZx7I87mc

### [A context-aware interactive Piano tutor](https://atlanta.aitinkerers.org/talks/rsvp_Rf2oBe4bzK8)

VibeKeys is a piano learning app designed to test the boundaries of interactive AI education capabilities. I'l show an app demo where the student plays a section incorrectly, and how the voice AI agent is engaged to provide insight to the student through its multi-level agent orchestration and context engineering system. The app has an interactive context layer that allows low-latency responses for simple tool calling combined with more escalated handoff to a deep-reasoning "Music Education" agent. I could also show some of the cool AI tools and skills I use to build this project: - Project-Specific "Pattern Languages" (Christopher Alexander) to help guide decision-making - BAML (open-source AI wrapper infrastructure that turns all LLM calls into statically typed function calls). - My code review process which uses Reviewable.io to host the diffs and interactively communicate with the AI agent to address review issues.

- Event context: AI Tinkerers Atlanta: 2-Year Anniversary & Best Demos of the Year — 2026-07-30 — Atlanta
- Public talk page: https://atlanta.aitinkerers.org/talks/rsvp_Rf2oBe4bzK8

### [How we managed to recover a stolen bike thanks to my AI-powered platform](https://valencia.aitinkerers.org/talks/rsvp_ObUQQ3GZ0Ds)

I'll demo all the AI integrations I did for our subscription bike company.

- Event context: AI Tinkerers Valencia July Demo Night — 2026-07-28 — Valencia
- Public talk page: https://valencia.aitinkerers.org/talks/rsvp_ObUQQ3GZ0Ds

### [AI as a Citizen's Governance Sidekick: Building a Practical Accountability Toolkit for Indiana Townships](https://fort-wayne.aitinkerers.org/talks/rsvp_lzBNfCu-WNk)

The Citizen Accountability Toolkit is a practical, citizen-led, AI-assisted guide that helps Indiana residents evaluate and strengthen local government performance in areas like public safety, transparency, and fiscal responsibility." In this demo, I'll showcase the real-world workflow we built: the 0-100 scoring system (with the Jackson Township fire services case study), the Live Interview Agent that turns meeting notes into scores, action trackers, one-page briefs, and APRA follow-ups, plus governance checklists. You'll see it live as I paste sample notes and instantly generate an updated score, brief, and next-step letter—demonstrating a human-controlled system that delivers immediately usable results for civic impact.

- Event context: AI Tinkerers Fort Wayne: July 2026 Meetup — 2026-07-25 — Fort Wayne
- Public talk page: https://fort-wayne.aitinkerers.org/talks/rsvp_lzBNfCu-WNk

### [Dig.rest](https://orange-county.aitinkerers.org/talks/rsvp_a0OCfbGWoFA)

Digging into events of the world, building cause and effect maps and getting to know the layers behind the news.

- Event context: AI Tinkerers Orange County: Tuesday, July 21, 2026 at Centercode — 2026-07-22 — Orange County
- Public talk page: https://orange-county.aitinkerers.org/talks/rsvp_a0OCfbGWoFA

### [Multi-agent Drawing Analysis](https://orange-county.aitinkerers.org/talks/rsvp_W9mR7pms2vA)

Agent teams to analyze construction drawings of any discipline, and return PDFs and report with findings. Uses the Claude API and deployes many agents. Splits the drawings into many tiles and assigns an agent to each tile. This program is useful to engineers and builders.

- Event context: AI Tinkerers Orange County: Tuesday, July 21, 2026 at Centercode — 2026-07-22 — Orange County
- Public talk page: https://orange-county.aitinkerers.org/talks/rsvp_W9mR7pms2vA

### [UserVolley follow up](https://orange-county.aitinkerers.org/talks/rsvp_KunnnLXa2pM)

Luke Freiler, CEO and founder of Centercode www.centercode.com

- Event context: AI Tinkerers Orange County: Tuesday, July 21, 2026 at Centercode — 2026-07-22 — Orange County
- Public talk page: https://orange-county.aitinkerers.org/talks/rsvp_KunnnLXa2pM

### [Build your own harness](https://orange-county.aitinkerers.org/talks/rsvp_f1CYnXjUlJQ)

A "compiler" for building your own agentic harness for a bounded task -- https://www.youtube.com/watch?v=75V0ZbCE9_0

- Event context: AI Tinkerers Orange County: Tuesday, July 21, 2026 at Centercode — 2026-07-22 — Orange County
- Public talk page: https://orange-county.aitinkerers.org/talks/rsvp_f1CYnXjUlJQ

### [AI for Electronics](https://seattle.aitinkerers.org/talks/rsvp_FQXXd6NroIw)

I built a physical circuit board and had it manufactured. I used AI at every stage of the design, from component selection and board layout through firmware and cloud software, and post-manufacture debugging.

- Event context: AI Dev Tools Track - Seattle - July 13 — 2026-07-14 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_FQXXd6NroIw

### [Kevin Riggen](https://honolulu.aitinkerers.org/talks/rsvp_8Xj0LRPLb1I)

Kevin Riggen will walk through the core engineering learnings that encompass the first O’ahu A.I. Publication: “Field Notes Volume 01”. This booklet looks back at three years in the field of Applied AI engineering and product development, sharing how local builders and the broader Hawai’i ecosystem stand to benefit from our collective work. This session is designed for active developers, engineers, and technical founders who want to move past API wrappers and explore the architectural patterns of production-grade AI systems.

- Event context: AI Tinkerers Honolulu - AI Loops, Agents & Knowledge Graphs — 2026-07-11 — Honolulu
- Public talk page: https://honolulu.aitinkerers.org/talks/rsvp_8Xj0LRPLb1I

### [audience interactive recap of AIE (AI Engineering Worlds Fair)](https://seattle.aitinkerers.org/talks/rsvp_LOzA5u2pjZI)

audience interactive recap of AIE (AI Engineering Worlds Fair)

- Event context: Special Topic: AIE Recap & Science Fair — 2026-07-09 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_LOzA5u2pjZI

### [Harness for ARC-AGI-3](https://zurich.aitinkerers.org/talks/rsvp_DuQxaJngv4g)

At Tufa Labs, we built a top-performing harness for the ARC-AGI-3 challenge. We will be releasing it open-source and would like to present it at the event.

- Event context: AI Tinkerers Zürich: July Build Night with Swisscom Ventures — 2026-07-01 — Zürich
- Public talk page: https://zurich.aitinkerers.org/talks/rsvp_DuQxaJngv4g

### [AI Powered Company Evaluation & Coaching](https://cairo.aitinkerers.org/talks/rsvp_erT3jGWE7MU)

VCDNA is a multi-agent platform that evaluates and coaches the companies companies you consider - turning each into a consistent, evidence-traced, IC-evidence-traced, IC-ready assessment.

- Event context: AI Tinkerers Cairo: Inaugural Meetup — 2026-07-01 — Cairo
- Public talk page: https://cairo.aitinkerers.org/talks/rsvp_erT3jGWE7MU

### [Building Brushi: A Local VLM Agent That Understands Kids’ Drawings](https://toronto.aitinkerers.org/talks/rsvp_duZsN9qwZvs)

Brushi is a kids coloring and drawing app with a local multimodal AI companion that can observe what a child is creating and respond through a small, bounded interaction loop. The project explores a question I have been thinking about in my recent work on edge AI: small VLMs and LLMs should not be treated as weaker versions of large cloud models. Like children are not simply “small adults,” edge models behave differently because the system around them has to provide structure, grounding, and feedback. In the live demo, I’ll show the working Brushi app, the local VLM/agentic architecture, and the event loop that connects the child’s drawing activity to the AI mascot’s reactions. The demo will focus on the technical workflow: how drawing events are captured, how visual context can be passed to a local VLM, how the LLM layer interprets the learning or creative context, and how the app decides whether to encourage, guide, correct, or stay silent. I’ll show the architecture, app workflow, logs/traces from the interaction loop, and examples of where the system succeeds or fails when trying to understand a child’s drawing.

- Event context: AI Tinkerers Toronto - June 2026 - with Relay Financial x PostHog — 2026-06-30 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_duZsN9qwZvs

### [AI Writes the Code. Who Cleans Up the Mess?](https://sf.aitinkerers.org/talks/rsvp_WjUo0pvA_j0)

I built an autonomous agent that diagnoses repositories for tech debt and raises prioritized fixes automatically. Shipped as an installable skill on Rovo Dev CLI: Atlassian's AI-powered developer tooling. It's now adopted across 5 engineering teams in my org. For the demo: I'll run the agent live against a repository, walk through diagnostic output across 18 signal categories, and raise a real PR on stage: end to end in under 5 minutes.

- Event context: AI Tinkerers San Francisco: Offensive Security Demo Night — 2026-06-26 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_WjUo0pvA_j0

### [Apertus: SwissAI’s fully-transparent multilingual LLM](https://lausanne.aitinkerers.org/talks/rsvp_yoFNhymPd9I)

Apertus is an Apache 2.0 family of open language models. This demo focuses on the Mini instruct variants, distilled into 0.5B, 1.5B, and 4B parameter checkpoints and uses Transformers.js and WebGPU for fast, client-side inference.

- Event context: AI Tinkerers Lausanne June 2026 Meetup — 2026-06-25 — Lausanne
- Public talk page: https://lausanne.aitinkerers.org/talks/rsvp_yoFNhymPd9I

### [Building Graph Navigation Tool for the Visually Impaired](https://hong-kong.aitinkerers.org/talks/rsvp_5Setv57KQwQ)

Access8Graph, a keyboard-input, speech-output system that allows screen reader users navigate complex graph data — starting with Taipei Metro System. The tool parses GraphML files (a common visual graph format), extracts semantic relationships that visual editors often ignore, and provides three distinct navigation modes matched to different user mental models — directional navigation, linear exploration, and route planning.

- Event context: AI Tinkerers Hong Kong & GBA at Dialogue in the Dark (June) — 2026-06-24 — Hong Kong
- Public talk page: https://hong-kong.aitinkerers.org/talks/rsvp_5Setv57KQwQ

### [Teaching an LLM to Play Riftbound](https://ottawa.aitinkerers.org/talks/rsvp_CPcwK2QKRgg)

Samuel demonstrates a framework he built to teach AI agents to play Riftbound, the League of Legends-based trading card game. The system translates English card text and the current board state into legal actions, uses Gemma to choose moves in player-versus-bot or bot-versus-bot simulations, and is designed to generate training experience so a faster machine-learning policy can eventually select optimal plays without relying on slower LLM inference at the final decision stage.

- Event context: AI Tinkerers Ottawa Meetup - June 20th, 2026 — 2026-06-20 — Ottawa
- Public talk page: https://ottawa.aitinkerers.org/talks/rsvp_CPcwK2QKRgg

## Related Technologies

- [AI](https://aitinkerers.org/technologies/ai) ([Markdown](https://aitinkerers.org/technologies/ai.md)) — 55 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [ML](https://aitinkerers.org/technologies/ml) ([Markdown](https://aitinkerers.org/technologies/ml.md)) — 11 public demos
- [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 520 public demos
- [RAG](https://aitinkerers.org/technologies/rag) ([Markdown](https://aitinkerers.org/technologies/rag.md)) — 147 public demos
- [MCP](https://aitinkerers.org/technologies/mcp) ([Markdown](https://aitinkerers.org/technologies/mcp.md)) — 129 public demos
- [API](https://aitinkerers.org/technologies/api) ([Markdown](https://aitinkerers.org/technologies/api.md)) — 19 public demos
- [AI agents](https://aitinkerers.org/technologies/ai-agents) ([Markdown](https://aitinkerers.org/technologies/ai-agents.md)) — 35 public demos
- [Transformers](https://aitinkerers.org/technologies/transformers) ([Markdown](https://aitinkerers.org/technologies/transformers.md)) — 148 public demos
- [TypeScript](https://aitinkerers.org/technologies/typescript) ([Markdown](https://aitinkerers.org/technologies/typescript.md)) — 205 public demos
- [AGENTS](https://aitinkerers.org/technologies/agents) ([Markdown](https://aitinkerers.org/technologies/agents.md)) — 20 public demos
- [Anthropic API](https://aitinkerers.org/technologies/anthropic-api) ([Markdown](https://aitinkerers.org/technologies/anthropic-api.md)) — 66 public demos
- [AWS](https://aitinkerers.org/technologies/aws) ([Markdown](https://aitinkerers.org/technologies/aws.md)) — 38 public demos
- [Claude](https://aitinkerers.org/technologies/claude) ([Markdown](https://aitinkerers.org/technologies/claude.md)) — 173 public demos
- [DL](https://aitinkerers.org/technologies/dl) ([Markdown](https://aitinkerers.org/technologies/dl.md)) — 4 public demos
- [JavaScript](https://aitinkerers.org/technologies/javascript) ([Markdown](https://aitinkerers.org/technologies/javascript.md)) — 40 public demos
- [JSON](https://aitinkerers.org/technologies/json) ([Markdown](https://aitinkerers.org/technologies/json.md)) — 20 public demos
- [LangChain](https://aitinkerers.org/technologies/langchain) ([Markdown](https://aitinkerers.org/technologies/langchain.md)) — 445 public demos

## More Results

- Next: https://aitinkerers.org/technologies/llm.md?page=2