# Jupyter notebook Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/jupyter-notebook
> Markdown URL: https://aitinkerers.org/technologies/jupyter-notebook.md
> Technology record last updated: 2026-02-26T04:17:06Z
> Generated: 2026-09-22T03:48:34Z

Jupyter Notebook is an open-source, web-based platform that merges live code, narrative text, equations, and rich media (like visualizations) into a single, shareable computational document.

This interactive computing environment is a core tool for data science and AI development (e.g., rapid experimentation, model prototyping). It supports over 40 programming languages (including Julia, Python, and R—from which the name 'Jupyter' is derived) via pluggable kernels. Notebooks, saved in the `.ipynb` format, organize work into executable code cells and Markdown text cells, making the workflow transparent, reproducible, and highly effective for collaborative analysis and sharing results with both technical and non-technical teams.

- Official technology site: https://jupyter.org/
- Public AI Tinkerers demos and talks: 13
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Intrinsic Dimension: Finding Optimal Dimensionality for Vector Embeddings](https://austin.aitinkerers.org/talks/rsvp_7Kk2MUDsi-0)

A Jupyter notebook with Python code that measures the intrinsic dimension (https://en.wikipedia.org/wiki/Intrinsic_dimension) of two large datasets of 768-dimensional semantic vector embeddings downloaded from Hugging Face. Interpretation of surprisingly low but complex results. Practical suggestions for how to use this method to choose the dimension of embedding vectors in various applications.

- Event context: Community AI Demos – Austin • July 10 2025 — 2025-07-10 — Austin
- Public talk page: https://austin.aitinkerers.org/talks/rsvp_7Kk2MUDsi-0

### [Sovereign Voice AI for Indic languages that listens, learns and perform agentic searches.](https://delhi.aitinkerers.org/talks/rsvp_zSlwbXmB6ms)

I will be presenting a demo on how to build a Sovereign voice-first AI interface built for the rich diversity of Indic languages. The demo will be capturing spoken input, understanding and retaining -provided facts, perform context-aware agentic searches and taking actions on user's behalf. All built on open-source, sovereign infrastructure to keep data within national borders yet leveraging widely available ecosystem tools.

- Event context: AI Tinkerers - Delhi - June Meetup — 2025-06-28 — Delhi
- Public talk page: https://delhi.aitinkerers.org/talks/rsvp_zSlwbXmB6ms

### [AI Agent Observability](https://seattle.aitinkerers.org/talks/rsvp_pzeKhDkm4VA)

I'll be showcasing how I've used Comet Opik to implement an observability strategy for my AI Agent project. I build an AI Agent to perform data analysis for me with CrewAI, but how do I monitor and evaluate a non-deterministic system like this? I'll talk through my code and show you the observability strategy I used for AI Agents.

- Event context: AI Tinkerers Seattle - April Meetup — 2025-04-25 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_pzeKhDkm4VA

### [SomosNPL](https://quito.aitinkerers.org/talks/rsvp_P95HhD6MedE)

Professor and Researcher - Representante en Ecuador de SomosNPL

- Event context: AI Tinkerers - Quito Primer Meetup (Abril) — 2025-04-24 — Quito
- Public talk page: https://quito.aitinkerers.org/talks/rsvp_P95HhD6MedE

### [Automated Documentation: Bridging the Documentation Void](https://toronto.aitinkerers.org/talks/rsvp_14QYpww1FyE)

A lack of documentation is a common pain point for any developer recently onboarded to a team. This absence frequently leads to difficulties in the comprehension of a piece of software, often leading to errors as a result. Under the guidance of Julia Longtin of the Human Feedback Foundation, the program that will be demoed will be our solution to fill this gap in knowledge: a program that will automate the generation of either documentation or a dockerfile, wherein the latter will hence can be run to replicate commands of the user. Our program achieves this automation through dividing tasks amongst three fine-tuned variants of DeepSeek R1 (and one model responsible for markdown outputs, which had been developed by a previous team utilizing a version of Gemma). We will be presenting the user flow of an individual inputting their terminal recording session, and receiving a dockerfile that can be used to replicate the commands used during the recording session. To output a dockerfile, we will present a session that will first be inputted to a model that will be responsible for dividing the session into relevant "events", and these events will be both annotated (i.e., summarized) and assigned a hierarchical structure (i.e., an event being a subevent of exiting a previous event's hierarchy) by a subsequent model. Finally, the annotated session will be inputted to a model responsible for the generation of a dockerfile, which will be ran to replicate the user's commands during the recorded session. Further, the motivation behind this approach over other solutions will also be discussed in detail.

- Event context: AI Tinkerers Toronto - March 2025 Meetup at Mozilla — 2025-03-27 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_14QYpww1FyE

### [AI "copilot" for Jupyter notebook](https://boston.aitinkerers.org/talks/rsvp_tpSLIq7fnnI)

Two containers running in docker compose, one a Jupyter notebook server, the other an LLM running in Ollama.

- Event context: AI Tinkerers Boston February 2025 — 2025-02-24 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_tpSLIq7fnnI

### [The plumbing behind intelligent IDEs](https://london.aitinkerers.org/talks/rsvp_uq6370Giy8o)

I'd like to give a brief overview of some of the tricks that go into making intelligent IDEs. I've been reverse engineering many of Cursor's features to make my own Jupyter notebook client, Satyrn (https://satyrn.app), much better, and I've learned some cool things along the way I think would be fun to put into talk. I'll basically cover what I have learned about how I think Cursor do command-k, chat context management, and Tab-to-edit. This research has been drawn from studying open source editors and plugins including Zed, Continue.dev, and Twinny; as well as some public published research on the topic: - https://arxiv.org/abs/2405.17103 - https://arxiv.org/abs/2207.14255

- Event context: AI Tinkerers London - December Meetup 🎄 — 2024-12-04 — London
- Public talk page: https://london.aitinkerers.org/talks/rsvp_uq6370Giy8o

### [Model and Prompt Evals the Hard Way](https://nyc.aitinkerers.org/talks/rsvp_v5odhPiV_Qs)

There appear to be two dominant approaches to evaluating AI models (and prompts): manual human review (thumbs up or down) or using an AI to apply automated scoring metrics. In this short presentation, I'll show how I used simple data analysis in a jupyter notebook to get valuable insights into prompt optimization and model selection.

- Event context: AI Tinkerers August Meetup — 2024-08-28 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_v5odhPiV_Qs

### [Exploiting the Signal-Leak Bias in Diffusion Models](https://lausanne.aitinkerers.org/talks/rsvp_vhQGhvfVwH4)

I will show a Jupyter Notebook demo of my research work on a bias present in most diffusion models for image generation, especially Stable Diffusion (v1 and v2). I will show that there is currently a discrepancy between training and inference processes in these models, and show how to fix and exploit this discrepancy to gain more control over generated images. The method does not require any additional training and can be applied directly during inference. Project page: https://ivrl.github.io/signal-leak-bias/ Research paper: https://arxiv.org/abs/2309.15842 Github: https://github.com/IVRL/signal-leak-bias

- Event context: AI Tinkerers Lausanne Inaugural June Meetup — 2024-06-24 — Lausanne
- Public talk page: https://lausanne.aitinkerers.org/talks/rsvp_vhQGhvfVwH4

### [LMNT: Surreal TTS and Voice Clones](https://palo-alto.aitinkerers.org/talks/rsvp_AIBN84aLfXU)

LMNT is an API for AI-powered generative speech synthesis, including text-to-speech (TTS) and voice cloning. Our TTS model is the best in the industry, with consistently low latency (~150ms between input and output), reliable service (competitors often experience multi hour long outages), and superb speech quality (we infuse the human “LMNT” in our speech models!). It can be useful in a variety of contexts, including supporting accessibility services, language learning, content creation, video narration, and many more. I would love to demo our newest model's capabilities (currently unreleased to the public) and answer everyone's questions about our vision for the future of AI-generated emotive speech.

- Event context: AI Tinkerers Palo Alto - June 2024 Meetup — 2024-06-12 — Palo Alto
- Public talk page: https://palo-alto.aitinkerers.org/talks/rsvp_AIBN84aLfXU

### [Generating SQL using LLMs](https://nyc.aitinkerers.org/talks/rsvp_CHSwRRxJmQQ)

I can give a demo of using RAG to generate accurate SQL for your database. I'll be using the Vanna Python package for orchestration and I can even show it using fully open source components like using Ollama to run your LLM locally and Chroma running locally as a vector storage layer. We can discuss the prompting strategy, various approaches, and anything else that may be related.

- Event context: Live from Civic Hall! AI Tinkerers Meetup | NY#TechWeek — 2024-06-03 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_CHSwRRxJmQQ

### [Deploying fine-tuned language models: From start to finish, in nothing but Python](https://toronto.aitinkerers.org/talks/rsvp_6a2kJuTUIXQ)

What does it take to fine-tune and deploy a customized LLM on state-of-the-art cloud hardware? In this talk, we explore a fully Pythonic solution to this problem, using just a few extra lines on top of ordinary code. No cloud expertise is required to follow along. We’ll start with a simple example and scale things gradually to arrive at a powerful, high-compute workflow that creates a “model inference” service with a custom API—all within the confines of a Jupyter Notebook!

- Event context: AI Tinkerers - Toronto - May 2024 Meetup — 2024-05-30 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_6a2kJuTUIXQ

### [Better Insights into Team Activity](https://la.aitinkerers.org/talks/rsvp_hitAVKjsOb0)

Our application tracks the applications people use throughout their work day. We currently present this information to team managers primarily in the form of dashboards & data tables, and are now building forecasting models & an LLM integration to enhance & present the data in a more accessible & insightful way, enabling managers to more easily optimize process-oriented teams. I'll walk us thru a proof-of-concept Jupyter Notebook.

- Event context: Feb 8th - AI Tinkerers Meetup — 2024-02-09 — Los Angeles
- Public talk page: https://la.aitinkerers.org/talks/rsvp_hitAVKjsOb0

## Related Technologies

- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [Ollama](https://aitinkerers.org/technologies/ollama) ([Markdown](https://aitinkerers.org/technologies/ollama.md)) — 77 public demos
- [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 520 public demos
- [Anaconda](https://aitinkerers.org/technologies/anaconda) ([Markdown](https://aitinkerers.org/technologies/anaconda.md)) — 1 public demo
- [API](https://aitinkerers.org/technologies/api) ([Markdown](https://aitinkerers.org/technologies/api.md)) — 19 public demos
- [arXiv](https://aitinkerers.org/technologies/arxiv) ([Markdown](https://aitinkerers.org/technologies/arxiv.md)) — 9 public demos
- [bash](https://aitinkerers.org/technologies/bash) ([Markdown](https://aitinkerers.org/technologies/bash.md)) — 12 public demos
- [Chroma](https://aitinkerers.org/technologies/chroma) ([Markdown](https://aitinkerers.org/technologies/chroma.md)) — 8 public demos
- [Claude Sonnet 4](https://aitinkerers.org/technologies/claude-sonnet-4) ([Markdown](https://aitinkerers.org/technologies/claude-sonnet-4.md)) — 18 public demos
- [Continue](https://aitinkerers.org/technologies/continue) ([Markdown](https://aitinkerers.org/technologies/continue.md)) — 2 public demos
- [Covalent](https://aitinkerers.org/technologies/covalent) ([Markdown](https://aitinkerers.org/technologies/covalent.md)) — 1 public demo
- [Crew AI](https://aitinkerers.org/technologies/crew-ai) ([Markdown](https://aitinkerers.org/technologies/crew-ai.md)) — 4 public demos
- [Cursor](https://aitinkerers.org/technologies/cursor) ([Markdown](https://aitinkerers.org/technologies/cursor.md)) — 65 public demos
- [Dashboards](https://aitinkerers.org/technologies/dashboards) ([Markdown](https://aitinkerers.org/technologies/dashboards.md)) — 2 public demos
- [datasets](https://aitinkerers.org/technologies/datasets) ([Markdown](https://aitinkerers.org/technologies/datasets.md)) — 6 public demos
- [Diffusion models](https://aitinkerers.org/technologies/diffusion-models) ([Markdown](https://aitinkerers.org/technologies/diffusion-models.md)) — 5 public demos
- [Docker](https://aitinkerers.org/technologies/docker) ([Markdown](https://aitinkerers.org/technologies/docker.md)) — 147 public demos
- [Docker Compose](https://aitinkerers.org/technologies/docker-compose) ([Markdown](https://aitinkerers.org/technologies/docker-compose.md)) — 5 public demos