# GPT-4 Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/gpt-4
> Markdown URL: https://aitinkerers.org/technologies/gpt-4.md
> Technology record last updated: 2026-02-22T10:50:14Z
> Generated: 2026-09-22T12:38:53Z

GPT-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.

- Official technology site: https://platform.openai.com/docs/models/gpt-4
- Public AI Tinkerers demos and talks: 529
- Result page: 1 of 23

## Recent Public Talks and Demos

### [Human Centered AI: Combining Design Thinking and lean methodologies for AI based product development](https://bogota.aitinkerers.org/talks/rsvp_D0H9UIYQOq0)

A practical methodology that blends Design Thinking and Lean into the AI development lifecycle to create human-centered AI products aligned with large-scale enterprise needs.

- Event context: AI Tinkerers Bogotá - Julio 24 — Bogotá
- Public talk page: https://bogota.aitinkerers.org/talks/rsvp_D0H9UIYQOq0

### [VOXMAP - Painel de diálogo - Analisador de Sentimentos](https://saopaulo.aitinkerers.org/talks/rsvp_f2hd9JW9cho)

Desenvolvi o VOXMAP, um assistente inteligente de atendimento e conciliação que transforma conversas em insights acionáveis. A aplicação permite que equipes analisem interações com clientes (como chats ou atendimentos), gerando automaticamente resumos estruturados, identificação de sentimento, propostas de solução e próximos passos recomendados — tudo em tempo real. Além disso, o sistema oferece análises visuais complementares, como nuvem de palavras e grafos de relacionamento, ajudando a entender padrões, conflitos e oportunidades dentro das conversas. O VOXMAP foi pensado para reduzir o esforço operacional em atendimento, aumentar a clareza nas decisões e acelerar a resolução de conflitos com apoio de IA.

- Event context: AI Tinkerers SP - Meetup de Maio - Kiro & AWS — 2026-05-28 — São Paulo
- Public talk page: https://saopaulo.aitinkerers.org/talks/rsvp_f2hd9JW9cho

### [Stateful agents with open-strix](https://raleigh.aitinkerers.org/talks/rsvp_obcR2zOygIM)

open-strix is a minimalistic open source stateful agent harness that leans on the Unix principle and uses cybernetics principles to build a tiny, solid, extensible core.

- Event context: AI Tinkerers Raleigh Meetup — May 6, 2026 — 2026-05-06 — Raleigh
- Public talk page: https://raleigh.aitinkerers.org/talks/rsvp_obcR2zOygIM

### [VisionClaw Agent an Agentic AI Corporation Platform](https://chicago.aitinkerers.org/talks/rsvp_pqxZHBHIMTo)

VisionClaw Agent is a fully autonomous AI corporation platform where 14 specialized AI personas — from CEO to CFO to engineers to sales — operate as a complete company, autonomously executing business operations like revenue generation, content creation, market research, and financial management with humans only in the loop for final decisions. VisionClaw Agent is a fully autonomous AI corporation platform where 14 specialized AI personas — from CEO to CFO to engineers to sales — operate as a complete company, autonomously executing business operations like revenue generation, content creation, market research, and financial management with humans only in the loop for final decisions, featuring a live activity demo that simulates the AI corporation in real-time with agent delegations, revenue tracking, memory storage, and task completions cycling across departments to showcase how the platform runs itself.

- Event context: AI Tinkerers Chicago: April Meetup ft OneTwoLoop — 2026-04-14 — Chicago
- Public talk page: https://chicago.aitinkerers.org/talks/rsvp_pqxZHBHIMTo

### [Failing Fast with AI: Rapid Prototyping Using Google AI Studio](https://pereira.aitinkerers.org/talks/rsvp_BLcMVGVLlTs)

This demo explores a paradigm shift in product development: failing fast to learn faster. I’ll demonstrate how Google AI Studio can be used to rapidly prototype AI-powered applications, validate ideas, and surface potential product value—without investing significant time, money, or engineering resources upfront. The focus will be on hands-on experimentation, iteration cycles, and technical workflows rather than slides or theory.

- Event context: Cambio de paradigma AITINKERERS PEREIRA 2026 — 2026-02-26 — Pereira
- Public talk page: https://pereira.aitinkerers.org/talks/rsvp_BLcMVGVLlTs

### [Self-Improving Agents with Honcho](https://nyc.aitinkerers.org/talks/rsvp_u3mcI_u6ioA)

Learn how you can use Honcho to create a stateful agent that learns and improves itself over time. Remove context window and context engineering burdens, let your OpenClaw know what it needs when it needs it.

- Event context: 🦞Demo Night: OpenClaw ft Convex — 2026-02-17 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_u3mcI_u6ioA

### [Stop Cloud Waste: AI Checks Costs Before Deploy in AWS](https://raleigh.aitinkerers.org/talks/rsvp_MX33E7LzJoM)

Ever had your IT team spin up cloud resources that cost way more than expected? I've developed an AI-powered assistant that reviews cloud infrastructure plans before deployment - like having a financial advisor check your shopping cart before checkout. Instead of finding out you spent $10,000 after the fact, teams get instant feedback: "This database is oversized for a dev environment - similar projects in your company use something 5x cheaper" or "You forgot the required cost tags that finance needs for billing." In this 5-minute demo, I'll show: Upload a cloud infrastructure plan (Terraform file) AI analyzes it against your company's cost policies written in plain English Get a breakdown: estimated monthly cost, policy violations, and smart suggestions See how it learns from your organization's past projects to give better recommendations The magic? It understands context - not just "this violates rule 247" but "this looks expensive for what you're building, here's what similar teams did."

- Event context: AI Tinkerers Raleigh Meetup — February 11, 2026 — 2026-02-11 — Raleigh
- Public talk page: https://raleigh.aitinkerers.org/talks/rsvp_MX33E7LzJoM

### [Should You Obey Your AI Reviewer?](https://belgium.aitinkerers.org/talks/rsvp_3tv20yxQ8mQ)

"Code Quality" is a system that posts feedback comments on your pull requests. We'll take a deep dive into how we hide non-determinism caused by LLMs and how we optimize the LLM's accuracy.

- Event context: AI Tinkerers Ghent Meetup - February 11 — 2026-02-11 — Belgium
- Public talk page: https://belgium.aitinkerers.org/talks/rsvp_3tv20yxQ8mQ

### [Sensora](https://conakry.aitinkerers.org/talks/rsvp_chnxLIer_5Q)

Logo Sensora Donnez une voix au silence Sensora accompagne les personnes sourdes et malentendantes avec des technologies accessibles qui transforment la communication et renforcent l'inclusion au quotidien. Découvrir Sensora Voir la démo Sensora - Application mobile et utilisatrice A Une technologie au service de l'accessibilité Découvrez comment Sensora transforme la communication quotidienne avec des fonctionnalités pensées pour répondre aux besoins réels des personnes sourdes et malentendantes. LSF Appareil connecté Capteurs santé (rythme cardiaque, stress, température) avec alertes d'urgence intégrées.

- Event context: AI Tinkerers – Conakry: Inaugural AI Conference @ Afrinov Tech Expo — 2026-02-11 — Conakry
- Public talk page: https://conakry.aitinkerers.org/talks/rsvp_chnxLIer_5Q

### [Building a Stock Market Research Agent with LangGraph](https://st-louis.aitinkerers.org/talks/rsvp_a06ZanAIgII)

I’m demonstrating Infera, an app that automates stock market due diligence. Instead of manually looking up tickers, Infera takes a list of companies (e.g., UBER vs. LYFT), pulls real-time data via Yahoo Finance, profiles leadership, and generates a ranked Markdown report with comparative radar charts.

- Event context: AI Tinkerers – St. Louis Meetup: February 4, 2026 — 2026-02-04 — St. Louis
- Public talk page: https://st-louis.aitinkerers.org/talks/rsvp_a06ZanAIgII

### [AI agents as interface layer for mobile apps](https://tiruchirappalli.aitinkerers.org/talks/rsvp_qrJiLeqgTOo)

Mobile interfaces are reaching their limit. More features mean more screens, more taps, and more friction. This talk explores a different direction. AI agents not as assistants bolted onto apps, but as the interface itself. Through a live demo of Kuralit, I show how user intent can bypass traditional UI and directly trigger real actions inside an app. No buttons. No navigation trees. Just intent to execution. This is not about voice for convenience. It is about interface evolution. From visual control to intent-driven software. The goal is to question a simple assumption. If software can understand what a user wants, why does it still wait for clicks?

- Event context: AI Tinkerers Trichy: January Meetup & Live Demos — 2026-01-31 — Tiruchirappalli
- Public talk page: https://tiruchirappalli.aitinkerers.org/talks/rsvp_qrJiLeqgTOo

### [AI-driven construction contract management tool](https://nashville.aitinkerers.org/talks/rsvp_wDbnTDTr_F0)

Mori Solution is an AI-driven contract analytics tool focused on interpreting complex construction contracts and technical specifications. This presentation demonstrates a working Retrieval-Augmented Generation (RAG) pipeline that enables semantic search and question answering over large, unstructured PDF documents. I will cover how construction contracts are parsed, chunked, embedded, and retrieved to support accurate queries related to safety requirements, bonds, and payment terms. The demo includes a live code walkthrough of the ingestion and retrieval pipeline, along with a speech-recognition interface that allows users to ask natural language questions and receive grounded, source-cited responses from the underlying contract data.

- Event context: AI Tinkerers Nashville – January 29th, 2026: Live Demos, Code, and Architecture — 2026-01-29 — Nashville
- Public talk page: https://nashville.aitinkerers.org/talks/rsvp_wDbnTDTr_F0

### [AI Predictions for 2026 from AI Tinkerers](https://montreal.aitinkerers.org/talks/rsvp_iBOlQ50Yzlk)

AI Predictions for 2026 from AI Tinkerers Community

- Event context: AI Tinkerers Montreal - January 2026 Meetup at Ateko — 2026-01-21 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_iBOlQ50Yzlk

### [Agent Runner](https://seattle.aitinkerers.org/talks/rsvp_VwLZmNweANo)

Agent Runner is a desktop application that brings AI agent execution to your fingertips. Press Ctrl+Shift+A and a UI panel slides in, giving you instant access to your library of self authored AI-powered agents. Built with Electron, React, and TypeScript, Agent Runner lets you create and execute reusable AI agents using BAML (BoundaryML) for type-safe definitions. Connect to OpenAI or Anthropic Claude with your own API keys. I'll be presenting the functional UI along with the underlying BAML code for each of the demoed agents. Features: Hotkey-triggered panel, BAML-based agents, clipboard integration, multi-LLM support, natural language agent creation, Discord-inspired dark UI. Status: Functional wireframe with database and hotkey system. By demo date, expect working agent execution with BAML integration. Open Source: Will be published on GitHub for community contribution.

- Event context: AI Tinkerers Seattle Meetup: Dev Tools Track — January 12th, 2026 — 2026-01-13 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_VwLZmNweANo

### [Violex — I’ll demo my project that enables learning to play the violin in a fun yet professional way, especially for people who have difficulty reading musical notation.](https://eindhoven.aitinkerers.org/talks/rsvp_BcDWQ0V1L38)

Violin is a very hard instrument to play. I’ll present my ongoing project called Violex, it is intended to help reading music sheets and mapping them on the instrument in a fun, intuitive and engaging way. The system also records your play and creates an AI/ML based feedback on how well you are performing! I’ll showcase my progress, the technical hurdles and the feedback mechanisms needed for creating an AI powered hardware like this.

- Event context: AI Tinkerers – Eindhoven Inaugural Meetup · 22 December 2025 — 2025-12-22 — Eindhoven
- Public talk page: https://eindhoven.aitinkerers.org/talks/rsvp_BcDWQ0V1L38

### [Coding Agents Are Good at Algorithms](https://eindhoven.aitinkerers.org/talks/rsvp_OMCQjnHBa1o)

I've been working on a solver for a word game called Strands. Wanting to try out the latest coding agents, I let Claude take a shot at writing an algorithm. I expected a little vibe-coding would get me most of the way there, but the computational complexity proved to be a lot more challenging than I thought. Along the way though, I learned to collaborate with my coding agent in a way that wasn't just a time save, it truly extended my abilities.

- Event context: AI Tinkerers – Eindhoven Inaugural Meetup · 22 December 2025 — 2025-12-22 — Eindhoven
- Public talk page: https://eindhoven.aitinkerers.org/talks/rsvp_OMCQjnHBa1o

### [From Blood Work to Biological Age in 500ms: Building a Mortality Risk Predictor](https://seattle.aitinkerers.org/talks/rsvp_Uu5hPbAkfyc)

I'll show you how I turned a 2018 mortality prediction algorithm into a production API that calculates "biological age" from 9 blood biomarkers—and the surprising engineering problems that emerged. The demo walks through: (1) why unit conversions almost destroyed us (one wrong conversion = 10 years off), (2) how we detect when the linear model breaks down and produces negative ages, (3) our counterfactual engine that ranks which biomarkers matter most for each individual, and (4) why population benchmarking was harder than the core algorithm. You'll see live requests, edge cases that produce impossible results, and the mathematical tricks we used to make confidence intervals fast.

- Event context: The Holiday Science Fair (Hot Cocoa, Cookies, and Demos!) — 2025-12-19 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_Uu5hPbAkfyc

### [PRESENT: Voice + Steward Architecture for Real-Time Multi-Agent Meeting Assistant](https://seattle.aitinkerers.org/talks/rsvp_zHytRNk1_tA)

Present is a custom Voice AI application and real-time meeting producer built with Next.js. In this talk I’ll cover how I refactored the codebase from the legacy three-agent architecture into a simplified voice + steward system. The production pipeline now runs as two lightweight Node processes: a real-time voice agent using LiveKit’s Agents API that listens to room audio, transcribes speech and calls UI tools, and a conductor that delegates to domain stewards running on the server. Stewards read state from Supabase, reason holistically with the latest LLMs (e.g. Claude Haiku via the CANVAS_STEWARD_MODEL env var), and emit structured UI patches. A browser ToolDispatcher executes these actions in TLDraw and React, enabling collaborative canvas editing. I’ll also show how I integrated Model Context Protocol (MCP) to connect to other AI services, added canvas branding and improved the agent tool catalog, and cleaned up the ‘duct-tape’ code from the summer. Live demos will include voice-driven component creation, flowchart steward updates, and multi-agent cooperation.

- Event context: The Holiday Science Fair (Hot Cocoa, Cookies, and Demos!) — 2025-12-19 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_zHytRNk1_tA

### [Porting Microsoft VibeVoice Realtime to Mac Silicon in One Night. No CUDA, All Metal!](https://seattle.aitinkerers.org/talks/rsvp_w07rXeYvwho)

Microsoft released VibeVoice for NVIDIA, but I wanted it on Mac. In this demo, I’ll show how I used Cursor to rip out the CUDA requirements and force the model to run on Metal. The result? Real-time, local TTS on an M4 Pro with zero cloud dependencies.

- Event context: The Holiday Science Fair (Hot Cocoa, Cookies, and Demos!) — 2025-12-19 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_w07rXeYvwho

### [Gotchas while building ChatGPT Apps](https://seattle.aitinkerers.org/talks/rsvp_ysWTzBfVe4w)

A ChatGPT app that helps you organize your next travel trip.

- Event context: The Holiday Science Fair (Hot Cocoa, Cookies, and Demos!) — 2025-12-19 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_ysWTzBfVe4w

### [Stop Generating, Start Understanding: Building a "Diagnosable" ColBERT for Grounded Late-Interaction Reasoning](https://belgium.aitinkerers.org/talks/rsvp_d9B2-FA9J54)

In a landscape obsessed with generative tokens, how can we build millisecond-latency reasoning engines that are interpretable by design and debuggable at the token level? In this demo, I will pop the hood on ClinicalEncoder25 to show how we achieve hallucination-free reasoning through the novel Diagnosable ColBERT architecture. I will walk through a live Jupyter notebook to demystify Late-Interaction Retrieval, visualizing the actual tensor operations that preserve token-level geometry instead of squashing documents into single embeddings. We will inspect the raw vector outputs of clinical text and, using my pre-computed ClinicalMap vector database, demonstrate a live debugging loop where we mathematically map specific token vectors back to SnomedCT concepts. You will see how the model connects the dots betwen a patient working at a "car repair shop" and his "lead contamination" to nudge the vector representation of the latter towards "past history of exposure to lead-based paint," proving that deep semantic understanding is possible without generating a single token.

- Event context: AI Tinkerers Brussels - December 17 — 2025-12-17 — Belgium
- Public talk page: https://belgium.aitinkerers.org/talks/rsvp_d9B2-FA9J54

### [x402-Enabled AI Gateway](https://atlanta.aitinkerers.org/talks/rsvp_-fDgoBtKAzQ)

I built a LLM Gateway (think OpenRouter) that uses the new x402 protocol to allow users to pay-per-request for LLM inference calls in real-time, using dollar stablecoins. This eliminates the need for advanced LLM users to avoid LLM Vendor specific subscriptions, API key management, billing, and vendor specific credits. Use any model you want, pay for what you use when you use it. Credits never expire.

- Event context: Co-Co-Code & Cocoa: The AI Tinkerers Atlanta Holiday Meetup — 2025-12-16 — Atlanta
- Public talk page: https://atlanta.aitinkerers.org/talks/rsvp_-fDgoBtKAzQ

### [Shifting Out: Using AI to Translate Across the Organization](https://atlanta.aitinkerers.org/talks/rsvp_ws8aA88TM4Y)

I will explores how AI can act as a translation layer across the organization. Not replacing people, but helping teams shift perspective without losing meaning. How to: Translate executive intent into actionable product and engineering scopes Normalize language between product, design, engineering, and marketing Preserve context while shifting between abstraction levels (strategy ↔ tactics ↔ implementation) Reduce “telephone game” loss across async, distributed teams Rather than focusing on prompt tricks or specific models, this talk centers on organizational leverage: where AI creates clarity, where it introduces risk, and how to design workflows that make translation reliable instead of fragile.

- Event context: Co-Co-Code & Cocoa: The AI Tinkerers Atlanta Holiday Meetup — 2025-12-16 — Atlanta
- Public talk page: https://atlanta.aitinkerers.org/talks/rsvp_ws8aA88TM4Y

### [Securing AI agent apps from identity perspectives](https://sydney.aitinkerers.org/talks/rsvp_mG9DEBJjWJQ)

I will be presenting identity challenges for Gen AI applications and how to solve those challenges with Auth0, with a particular focus on authorization for RAG to prevent the disclosure of sensitive information.

- Event context: Trust and Security in AI - Sydney Demo Night — 2025-12-11 — Sydney
- Public talk page: https://sydney.aitinkerers.org/talks/rsvp_mG9DEBJjWJQ

## Related Technologies

- [LangChain](https://aitinkerers.org/technologies/langchain) ([Markdown](https://aitinkerers.org/technologies/langchain.md)) — 445 public demos
- [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 520 public demos
- [Llama-2](https://aitinkerers.org/technologies/llama-2) ([Markdown](https://aitinkerers.org/technologies/llama-2.md)) — 227 public demos
- [GPT-3](https://aitinkerers.org/technologies/gpt-3) ([Markdown](https://aitinkerers.org/technologies/gpt-3.md)) — 191 public demos
- [PyTorch](https://aitinkerers.org/technologies/pytorch) ([Markdown](https://aitinkerers.org/technologies/pytorch.md)) — 273 public demos
- [BERT](https://aitinkerers.org/technologies/bert) ([Markdown](https://aitinkerers.org/technologies/bert.md)) — 179 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [RoBERTa](https://aitinkerers.org/technologies/roberta) ([Markdown](https://aitinkerers.org/technologies/roberta.md)) — 118 public demos
- [BLOOM](https://aitinkerers.org/technologies/bloom) ([Markdown](https://aitinkerers.org/technologies/bloom.md)) — 115 public demos
- [PaLM 2](https://aitinkerers.org/technologies/palm-2) ([Markdown](https://aitinkerers.org/technologies/palm-2.md)) — 116 public demos
- [Claude-3](https://aitinkerers.org/technologies/claude-3) ([Markdown](https://aitinkerers.org/technologies/claude-3.md)) — 110 public demos
- [Transformers](https://aitinkerers.org/technologies/transformers) ([Markdown](https://aitinkerers.org/technologies/transformers.md)) — 148 public demos
- [TensorFlow](https://aitinkerers.org/technologies/tensorflow) ([Markdown](https://aitinkerers.org/technologies/tensorflow.md)) — 90 public demos
- [scikit-learn](https://aitinkerers.org/technologies/scikit-learn) ([Markdown](https://aitinkerers.org/technologies/scikit-learn.md)) — 84 public demos
- [Keras](https://aitinkerers.org/technologies/keras) ([Markdown](https://aitinkerers.org/technologies/keras.md)) — 74 public demos
- [ONNX](https://aitinkerers.org/technologies/onnx) ([Markdown](https://aitinkerers.org/technologies/onnx.md)) — 83 public demos
- [Streamlit](https://aitinkerers.org/technologies/streamlit) ([Markdown](https://aitinkerers.org/technologies/streamlit.md)) — 89 public demos
- [RAG](https://aitinkerers.org/technologies/rag) ([Markdown](https://aitinkerers.org/technologies/rag.md)) — 147 public demos

## More Results

- Next: https://aitinkerers.org/technologies/gpt-4.md?page=2