# BLOOM Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/bloom?page=2
> Markdown URL: https://aitinkerers.org/technologies/bloom.md?page=2
> Technology record last updated: 2026-02-24T08:39:03Z
> Generated: 2026-09-22T06:47:17Z

A 176-billion parameter open-access multilingual language model built by the BigScience research collective.

BLOOM is the result of a year-long collaboration involving 1,000+ researchers from 70+ countries. It supports 46 natural languages and 13 programming languages: it provides a high-performance alternative to proprietary models. The model was trained on the Jean Zay supercomputer in France using the 1.6-terabyte ROOTS dataset (a massive collection of diverse text sources). By providing full access to its weights and training process, BLOOM enables global developers to build and audit AI tools without the restrictions of closed-door APIs.

- Official technology site: https://huggingface.co/bigscience/bloom
- Public AI Tinkerers demos and talks: 115
- Result page: 2 of 5

## Recent Public Talks and Demos

### [Xelerit - AI Copilot for industrial robotics](https://zurich.aitinkerers.org/talks/rsvp_a35OOTyQzVs)

I will go through how our software works, which mirror the complete work of a robotics engineer, making it much faster. Our mvp has: • robot code generation (in the native robot-brand language) • copilot chat (for easy navigation of robot docs) • code translator between robot languages • I/O automatic configuration from PLC to robot. • Simulation

- Event context: AI Tinkerers Zurich - February 6 — 2025-02-06 — Zürich
- Public talk page: https://zurich.aitinkerers.org/talks/rsvp_a35OOTyQzVs

### [The Unreasonable Power of Structured Outputs](https://paris.aitinkerers.org/talks/rsvp_iQiulV7QSbc)

This demo will show 3 solutions with one common denominator: structured outputs. 1. A PowerPoint presentation generator 2. A smart search bar 3. A skin diagnostic tool

- Event context: AI Tinkerers - Paris Meetup on January 30th — 2025-01-30 — Paris
- Public talk page: https://paris.aitinkerers.org/talks/rsvp_iQiulV7QSbc

### [Evaluating a Medical Assistant](https://poland.aitinkerers.org/talks/rsvp_NPP2O6J7Te4)

How do you evaluate an AI system that assists doctors with medical documentation? In this talk, we'll share practical insights from building an evaluation framework for Noa Notes @ Docplanner - a system that transcribes and summarizes doctor-patient conversations. We will discuss our two-tier evaluation approach combining detailed factual assessment with style analysis, see how we leverage LLMs in the evaluation pipeline, and share specific examples of how prompt engineering improved our metrics. We'll also discuss challenges unique to the medical domain and how we addressed them.

- Event context: AI Tinkerers Poland - Second Meetup in Warsaw (January) — 2025-01-30 — Poland
- Public talk page: https://poland.aitinkerers.org/talks/rsvp_NPP2O6J7Te4

### [BigSleep - Using Large Language Models To Catch Vulnerabilities In Real-World Code](https://mumbai.aitinkerers.org/talks/rsvp_1b6rjVoZomw)

BigSleep is an autonomous security agent that finds vulnerabilities in code. As the code comprehension and general reasoning ability of Large Language Models (LLMs) has improved, we have been exploring how these models can reproduce the systematic approach of a human security researcher when identifying and demonstrating security vulnerabilities. We hope that in the future, this can close some of the blind spots of current automated vulnerability discovery approaches, and enable automated detection of "unfuzzable" vulnerabilities. The BigSleep Agent has access to a code search tool, a debugger and a python sandbox. It dynamically explores the codebase and figures out potential program points where a vulnerability exists. It then generates an input to demonstrate the crash, as proof.

- Event context: 🚀 AI Tinkerers Mumbai Chapter: Community Social Event! — 2025-01-25 — Mumbai
- Public talk page: https://mumbai.aitinkerers.org/talks/rsvp_1b6rjVoZomw

### [Chatting With Logs -- Rethinking the Log Search Interface](https://atlanta.aitinkerers.org/talks/rsvp_7hVDp4YESNo)

Most of the observability data products have different languages that the developers have to learn. Oftentimes, these languages are significantly different from each other and moving for a developer to move between products, it would involve a big learning curve. In our work, we are looking at making these query interfaces easier by finetuning LLMs to generate these languages. This involves a set of challenges as the logs often do not fit into the context window of most LLMs, and off the shelf LLMs lack application specific knowledge for generating the queries. In this demo, I'd walk through the framework that organizations would need to follow for finetuning their own models for this task and deploy it into production. Along with this, I will showcase the dataset, finetuned models and a demo currently deployed using Modal labs.

- Event context: AI Tinkerers Atlanta January Meetup — 2025-01-23 — Atlanta
- Public talk page: https://atlanta.aitinkerers.org/talks/rsvp_7hVDp4YESNo

### [AI Decision-Making in Low / No Trainable Data Domains](https://dc.aitinkerers.org/talks/rsvp_IF15w4fLhMM)

Despite their power, Large Language Models struggle with specialized expert tasks where there is little or no trainable data. But what if we could teach them like we teach management consultants - using expert-created rules of thumb? This harnesses the LLM's general reasoning abilities but provides domain-specific guidance to provide high-quality results. I've been looking at how to apply this to negotiations and geopolitical challenges and early results show this practical approach could unlock AI's potential in these high-value domains.

- Event context: AI Tinkerers - DC Metro Meetup (January 15th 2025) — 2025-01-15 — DC
- Public talk page: https://dc.aitinkerers.org/talks/rsvp_IF15w4fLhMM

### [Finding Patent Prior Art with AI](https://chicago.aitinkerers.org/talks/rsvp_vHz4JF0Wu5U)

Patents form the cornerstone of innovation protection, with the USPTO processing over 600,000 applications annually representing billions in economic value. To get a patent, an invention must be genuinely novel—but proving novelty is a complex, time-consuming process that costs companies tens of thousands of dollars per application. Patent examiners and professionals spend countless hours searching for "prior art" that might show an invention already exists. In this talk, I will demonstrate an AI-powered system that not only identifies relevant prior art but provides detailed mapping between patent claims and existing disclosures, enabling patent examiners to quickly evaluate patentability and transform the examination process.

- Event context: AI Tinkerers Chicago January Meetup — 2025-01-14 — Chicago
- Public talk page: https://chicago.aitinkerers.org/talks/rsvp_vHz4JF0Wu5U

### [Cognitive Architectures -- A principled way to build agents](https://singapore.aitinkerers.org/talks/rsvp_9GgmNHjgPsk)

In the quest to build artificial intelligence, could understanding natural intelligence help? Cognitive architectures is the field of understanding and implementing the various building blocks of intelligence in cognitive science, offering a principled way to build agents. In this demo, I'll show some basic blocks that I've built and assembled into a coding agent.

- Event context: AI Tinkerers Singapore: 4th Meetup - January 10th, 2025 — 2025-01-10 — Singapore
- Public talk page: https://singapore.aitinkerers.org/talks/rsvp_9GgmNHjgPsk

### [Human machine](https://seattle.aitinkerers.org/talks/rsvp_cDs_nfJfXZs)

A code editor and runtime to use multiple AIs together to prototype stuff. Code with voice and pen, or make art.

- Event context: AI Tinkerers Seattle - December 2024 Meetup — 2024-12-12 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_cDs_nfJfXZs

### [Using LLM's for Social Good: A Chicago Public Schools Case Study](https://chicago.aitinkerers.org/talks/rsvp_hIVPfEz9-7k)

I'll talk about my recent project that used web crawling and LLM's to create a directory of before school and after school childcare options for Chicago public schools. https://www.cps-care.info/

- Event context: AI Tinkerers Chicago December Meetup — 2024-12-10 — Chicago
- Public talk page: https://chicago.aitinkerers.org/talks/rsvp_hIVPfEz9-7k

### [Space LLM](https://paris.aitinkerers.org/talks/rsvp_Wu5F_vrQMUw)

Generative Floor Plans Designs using fine-tuned LLMs

- Event context: AI Tinkerers - Paris Meetup on December 10th — 2024-12-10 — Paris
- Public talk page: https://paris.aitinkerers.org/talks/rsvp_Wu5F_vrQMUw

### [Travel agency companion - a WIP](https://montreal.aitinkerers.org/talks/rsvp_xVI91aR3PHw)

My project is a travel agency companion chatbot designed to assist solo travelers in finding inspiration and planning their itineraries. Utilizing Google Cloud Platform (GCP) and Large Language Models (LLMs), this AI-driven tool engages users in natural conversations to provide personalized travel recommendations based on their preferences, budget, and interests. The chatbot suggests destinations and creates detailed itineraries. This project is a practical application of deploying AI technologies and allowed me to learn about GCP infrastructure and the intricacies of LLMs for information extraction. While the primary focus is on travel, the underlying framework is adaptable to other domains. For instance, the technology can be employed in medical document analysis or legal document processing, showcasing its versatility in extracting and summarizing relevant information across various fields.

- Event context: AI Tinkerers Montreal - December 2024 Meetup at IVADO Labs — 2024-12-03 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_xVI91aR3PHw

### [Steering LLMs and Embeddings with SAEs](https://mumbai.aitinkerers.org/talks/rsvp_pYismAp8lgc)

In this demo, we'll explore how Sparse Autoencoders (SAEs) can be utilized to steer Large Language Models (LLMs) and their embeddings. By leveraging tools like Goodfire's API and Google's Gemma Scope, we'll demonstrate how SAEs can interpret and modify the internal activations of LLMs, enabling precise control over their knowledge selection behaviors. This approach addresses challenges such as context-memory knowledge conflicts, enhancing the reliability and accuracy of AI-generated outputs.

- Event context: AI Tinkerers Mumbai Chapter - 2nd Event Incoming! — 2024-11-23 — Mumbai
- Public talk page: https://mumbai.aitinkerers.org/talks/rsvp_pYismAp8lgc

### [Unlocking the 95% of unstructured data in construction](https://munich.aitinkerers.org/talks/rsvp_OAevBQmVyOI)

I’ll showcase how vertical applied AI can deliver end-to-end work results for processing, thousand of documents in construction companies, improving accuracy from 42% to 82%.

- Event context: AI Tinkerers Munich - November 21 — 2024-11-21 — Munich
- Public talk page: https://munich.aitinkerers.org/talks/rsvp_OAevBQmVyOI

### [Making sense of vegetables](https://munich.aitinkerers.org/talks/rsvp_zAc9Px-e8TY)

At Freshflow, we help supermarkets place perfect orders for fresh produce. The raw data we have to deal with is about fruits and vegetables that were ordered, delivered and sold, naturally in very messy format. Using LLMs proved to be an irreplaceable tool to make sense of these real world inputs, from product names abbreviated beyond recognition to poorly formatted pdfs, unlocking the insights needed to reduce food waste in supermarkets.

- Event context: AI Tinkerers Munich - November 21 — 2024-11-21 — Munich
- Public talk page: https://munich.aitinkerers.org/talks/rsvp_zAc9Px-e8TY

### [Hyper-Realistic AI Video Calls](https://munich.aitinkerers.org/talks/rsvp_bA1SHk3Xq28)

Ever wanted to have an AI clone of yourself that can join virtual meetings on your behalf? If so, then this demo is for you. At Beyond Presence we're building an online self-service platform where anyone can create, deploy, and manage hyper-realistic digital AI clones of themselves. I'll be sharing a sneak peak of our upcoming product, including a live demo of our real-time conversational avatar technology.

- Event context: AI Tinkerers Munich - November 21 — 2024-11-21 — Munich
- Public talk page: https://munich.aitinkerers.org/talks/rsvp_bA1SHk3Xq28

### [Using LLMs for storytelling](https://singapore.aitinkerers.org/talks/rsvp_IItm85bd8Es)

Generate a story with different branches using a LLM generated DAG

- Event context: AI Tinkerers Singapore: 3rd Meetup - November 19th, 2024 — 2024-11-19 — Singapore
- Public talk page: https://singapore.aitinkerers.org/talks/rsvp_IItm85bd8Es

### [AI Native React compiler](https://amsterdam.aitinkerers.org/talks/rsvp_a42GWjmALJw)

I would give a talk on building a React compiler that’s optimized for interacting with LLMs. I want to highlight the opportunity that exists from creating optimizations in the toolkit that LLMs can use. I want to dive into what technical optimizations you can apply across a vertical level to achieve better performance.

- Event context: AI Tinkerers Amsterdam - November — 2024-11-12 — Amsterdam
- Public talk page: https://amsterdam.aitinkerers.org/talks/rsvp_a42GWjmALJw

### [Automating my own video editing with whisper, ffmpeg and llms](https://amsterdam.aitinkerers.org/talks/rsvp_ndSVOIxM5xc)

When recording videos for my own startup content (which is about llm monitoring not related to videos at all), I kinda found a good flow recording it, but I loathe how much time I spend editing it, and it's not complicated edits, I started seeing some patterns so I thought it could be automated easily with tech we already have, still not perfect but the results are super good, wanted to share the hacks I threw together for it to work

- Event context: AI Tinkerers Amsterdam - November — 2024-11-12 — Amsterdam
- Public talk page: https://amsterdam.aitinkerers.org/talks/rsvp_ndSVOIxM5xc

### [AI for Capital Markets, Agents, Evaluation](https://london.aitinkerers.org/talks/rsvp_k2jEXYltQMw)

The talk will discuss the reality of building applications with generative models in environments that demand high quality and actionable responses in production. We’ll be going into our particular challenge of creating an application within the very domain-driven space we are working in (financial). We’ll also discuss strategies we are building to evaluate the output of generated by leveraging LLMs, and challenges around LLM evaluations for agentic pipelines.

- Event context: AI Tinkerers London - October Meetup 🎃 — 2024-10-31 — London
- Public talk page: https://london.aitinkerers.org/talks/rsvp_k2jEXYltQMw

### [Remember anything & interact with everything with Pieces for Developers](https://cincinnati.aitinkerers.org/talks/rsvp_tFtjjW_oeAA)

Learn how Pieces for Developers uses advanced RAG (Retrieval Augmented Generation) paired with LLMs to give developers long-term memory superpowers.

- Event context: AI Tinkerers - Cincinnati Inaugural Meetup (October) — 2024-10-30 — Cincinnati
- Public talk page: https://cincinnati.aitinkerers.org/talks/rsvp_tFtjjW_oeAA

### [From Haikus to Helper - Wrangling Agentic LLM's](https://montreal.aitinkerers.org/talks/rsvp_ykR1yUDQJ08)

We built a product that uses LLM's for data transformations + enrichment ( think spreadsheet) but also supports Agentic responses/actions on these datasets. I'll do a brief demo of the product and describe the architecture and challenges productizing augmentation and agentic behaviours. We'll walk through adding an AI enrichment column, and specifically cover: * The path of data through the system: Ingestion => SQL / Vectorization => Retrieval, * LLM touch points - importance estimation, schema prediction, extraction/augmentation. Use the agent to analyze results and support the user: * Prepare a report, have it posted to slack

- Event context: AI Tinkerers - Montreal Inaugural Meetup (October) — 2024-10-29 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_ykR1yUDQJ08

### [Cooktok](https://montreal.aitinkerers.org/talks/rsvp_5t8RKHulk5Q)

I made a really basic AI app to help me turn TikTok videos into recipes so I can cook with my husband. It takes the captions and description and turns it into a JSON object so I can print it out and cook it.

- Event context: AI Tinkerers - Montreal Inaugural Meetup (October) — 2024-10-29 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_5t8RKHulk5Q

### [LABEL: LLM Assistance for Better Evaluation Labels](https://seattle.aitinkerers.org/talks/rsvp_kadYvSmadkQ)

A demo workflow and UX for labeling data, using it to evaluate LLM-evaluators, and then aligning the LLM-evaluator to human judgments (and perhaps optimizing the evaluator!) P.S., Kyle Corbitt of OpenPipe will be demoing something similar, and I hope to have a faceoff with them by going before them so the audience can decide the pros and cons of each.

- Event context: AI Tinkerers - Seattle - October 2024 Meetup — 2024-10-25 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_kadYvSmadkQ

## Related Technologies

- [BERT](https://aitinkerers.org/technologies/bert) ([Markdown](https://aitinkerers.org/technologies/bert.md)) — 179 public demos
- [GPT-3](https://aitinkerers.org/technologies/gpt-3) ([Markdown](https://aitinkerers.org/technologies/gpt-3.md)) — 191 public demos
- [GPT-4](https://aitinkerers.org/technologies/gpt-4) ([Markdown](https://aitinkerers.org/technologies/gpt-4.md)) — 529 public demos
- [Llama-2](https://aitinkerers.org/technologies/llama-2) ([Markdown](https://aitinkerers.org/technologies/llama-2.md)) — 227 public demos
- [PaLM 2](https://aitinkerers.org/technologies/palm-2) ([Markdown](https://aitinkerers.org/technologies/palm-2.md)) — 116 public demos
- [RoBERTa](https://aitinkerers.org/technologies/roberta) ([Markdown](https://aitinkerers.org/technologies/roberta.md)) — 118 public demos
- [RAG](https://aitinkerers.org/technologies/rag) ([Markdown](https://aitinkerers.org/technologies/rag.md)) — 147 public demos
- [scikit-learn](https://aitinkerers.org/technologies/scikit-learn) ([Markdown](https://aitinkerers.org/technologies/scikit-learn.md)) — 84 public demos
- [TensorFlow](https://aitinkerers.org/technologies/tensorflow) ([Markdown](https://aitinkerers.org/technologies/tensorflow.md)) — 90 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
- [PyTorch](https://aitinkerers.org/technologies/pytorch) ([Markdown](https://aitinkerers.org/technologies/pytorch.md)) — 273 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [Generative AI](https://aitinkerers.org/technologies/generative-ai) ([Markdown](https://aitinkerers.org/technologies/generative-ai.md)) — 45 public demos
- [Large Language Models](https://aitinkerers.org/technologies/large-language-models) ([Markdown](https://aitinkerers.org/technologies/large-language-models.md)) — 8 public demos
- [Prompt Engineering](https://aitinkerers.org/technologies/prompt-engineering) ([Markdown](https://aitinkerers.org/technologies/prompt-engineering.md)) — 28 public demos
- [Fine-tuning](https://aitinkerers.org/technologies/fine-tuning) ([Markdown](https://aitinkerers.org/technologies/fine-tuning.md)) — 20 public demos
- [AI agents](https://aitinkerers.org/technologies/ai-agents) ([Markdown](https://aitinkerers.org/technologies/ai-agents.md)) — 35 public demos

## More Results

- Previous: https://aitinkerers.org/technologies/bloom.md
- Next: https://aitinkerers.org/technologies/bloom.md?page=3