# BERT Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/bert?page=5
> Markdown URL: https://aitinkerers.org/technologies/bert.md?page=5
> Technology record last updated: 2026-02-24T08:39:03Z
> Generated: 2026-09-22T13:49:21Z

BERT (Bidirectional Encoder Representations from Transformers) is a foundational, pre-trained NLP model that uses a Transformer encoder to process text bidirectionally, capturing full word context for superior language understanding.

BERT is a revolutionary language representation model introduced by Google AI Language in 2018. It is built on the Transformer architecture and distinguishes itself by being deeply bidirectional: it processes the entire sequence of words (left and right context) simultaneously, unlike previous unidirectional models. This capability is achieved through a Masked Language Model (MLM) pre-training objective. The model, released in sizes like BERTBASE (110 million parameters) and BERTLARGE (340 million parameters), dramatically improved the state-of-the-art across 11+ Natural Language Processing tasks, including question answering (SQuAD) and sentiment analysis, establishing a new baseline for the field.

- Official technology site: https://arxiv.org/abs/1810.04805
- Public AI Tinkerers demos and talks: 179
- Result page: 5 of 8

## Recent Public Talks and Demos

### [Clipmarks: AI Bookmarks that Never Forget](https://palo-alto.aitinkerers.org/talks/rsvp_DkYTgXEaDxQ)

Clipmarks is an AI-powered bookmarking tool that solves the problem of knowledge overload. It automatically organizes saved pages into smart folders, generates meaningful titles and summaries, and lets you easily search and rediscover saved knowledge. We'll demonstrate how Clipmarks can ingest a deluge of tech articles, Twitter threads, and blog posts - extracting key insights, intelligently categorizing content, and making it effortless to find exactly what you need later. Clipmarks builds your personal AI knowledge base as you browse. You'll see how Clipmarks can be used standalone or integrated with the Andi AI search engine for question-answering and web search augmented by your personal web clippings. We'll show AI-assisted content discovery, using Clipmarks collections to find the most relevant new information. Never lose track of important ideas again. Clipmarks is your photographic memory for the web - automatically summarizing, organizing and surfacing knowledge when you need it. We're excited to give you a sneak preview of this powerful tool to tame information overload.

- Event context: AI Tinkerers - Palo Alto - August 2024 @ Groq — 2024-08-23 — Palo Alto
- Public talk page: https://palo-alto.aitinkerers.org/talks/rsvp_DkYTgXEaDxQ

### [Build AI agent to accelerate your life](https://palo-alto.aitinkerers.org/talks/rsvp_T8B787_f1bo)

My product is Coze, which is a one-stop AI chat bot development platform. Regardless of your AI development skills, Coze allows you to swiftly create a wide range of chat bots powered by AI, capable of handling everything from simple questions to complex conversations. Furthermore, you can publish your bots to various applications, fostering dynamic interaction with users on those applications.

- Event context: AI Tinkerers - Palo Alto - August 2024 @ Groq — 2024-08-23 — Palo Alto
- Public talk page: https://palo-alto.aitinkerers.org/talks/rsvp_T8B787_f1bo

### [Fashion in a post-AI world](https://berlin.aitinkerers.org/talks/rsvp__bwLSJCdazs)

Image generation tools has helped fashion designers explore different design variations and visualise their abstract ideas. However it left them with no support in bringing these designs to reality. This talk will show an early demo of what the future of fashion design looks like: prompt a system, get a simulated cloth automatically fitted to a given body, and receive the computed construction details. This reduces the fashion development cycle from weeks to hours.

- Event context: AI Tinkerers Berlin - August 22 — 2024-08-22 — Berlin
- Public talk page: https://berlin.aitinkerers.org/talks/rsvp__bwLSJCdazs

### [Solving AGI - ARC with Neural Nets that learn algebra](https://chicago.aitinkerers.org/talks/rsvp_C9wKKddDFas)

Arc agi challenge is unsolved for years now. But humans can do it easy. Is the secret to come up with a machine learning powered custom algebra system?

- Event context: AI Tinkerers Chicago August Meetup — 2024-08-20 — Chicago
- Public talk page: https://chicago.aitinkerers.org/talks/rsvp_C9wKKddDFas

### [Travel App powered by Dynamic RAG Filtering](https://chicago.aitinkerers.org/talks/rsvp_bML4MjDjpcg)

We've built a travel app that helps people find where to go, stay, eat, drink and what to do while on vacation. To make app work we created dynamic RAG filtering technology that in real time is able to build a database for each user's request using AI to read and filter data from the open internet, then turn it into a list of options that is presented to the user. In my talk I'd like to show how that technology works in both our web app and our chatbot. The technology is designed in a way it can easily be translated to other use cases and I think is a really interesting application of AI. In my talk, I'll showcase how the end product works and explain the tech powering it.

- Event context: AI Tinkerers Chicago August Meetup — 2024-08-20 — Chicago
- Public talk page: https://chicago.aitinkerers.org/talks/rsvp_bML4MjDjpcg

### [Deepgram (Community Demo Pit)](https://seattle.aitinkerers.org/talks/rsvp_MZOrhBz-sLA)

Stop by the community demo pit to check out amazing demos from Deepgram! Deepgram is a pioneering voice AI platform offering cutting-edge APIs for speech-to-text, text-to-speech, and language understanding. Their lightning-fast, highly accurate speech recognition and natural-sounding voice synthesis enable developers to build sophisticated voice AI applications with ease. Deepgram’s GPU-optimized infrastructure provides unparalleled speed and cost-efficiency, making it up to 40x faster and 3-5x cheaper than alternatives. From conversational AI to medical transcription, Deepgram empowers developers to unlock the full potential of voice data at scale.

- Event context: AI Tinkerers Summer Social - August 2024 — 2024-08-16 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_MZOrhBz-sLA

### [Fixie (Community Demo Pit)](https://seattle.aitinkerers.org/talks/rsvp_PXsoLKDf8XY)

Stop by the community demo pit to check out amazing demos from Fixie! Fixie is a Seattle-based AI startup aiming to revolutionize human-AI interaction by enabling real-time, multi-modal conversations. They’re working on giving AI a voice and face to create more human-like connections, maximizing the potential of large language models in various applications.

- Event context: AI Tinkerers Summer Social - August 2024 — 2024-08-16 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_PXsoLKDf8XY

### [Milton - AI agent for economic data analysis](https://singapore.aitinkerers.org/talks/rsvp_Z0VAQIJHtw0)

Every single step of writing an economic data report can be automated using LLMs. I show a demo that does 1. Searching for the right datasets, self-critique and reflection 2. Automatic code-writing with self-debugging 3. Graphing according to the user needs 4. Packaging all of these into a report that rivals the quality of research made on Wall St

- Event context: AI Tinkerers Singapore: Inaugural Meetup - August 2nd, 2024 — 2024-08-02 — Singapore
- Public talk page: https://singapore.aitinkerers.org/talks/rsvp_Z0VAQIJHtw0

### [Analisis de comentarios](https://bogota.aitinkerers.org/talks/rsvp_ZoVcwT20vYU)

Encontrar insights valiosos para ñas compañias sobre sus comentarios a bajo costo mediante LLMs usando Langchain. Es adaptable para diferentes usos y estamos probando como probar con casos reales.

- Event context: Tercer AI Tinkerers Bogotá — 2024-07-25 — Bogotá
- Public talk page: https://bogota.aitinkerers.org/talks/rsvp_ZoVcwT20vYU

### [Conversational AI with a subconscious, memories, and dreams](https://nyc.aitinkerers.org/talks/rsvp__pXksTkstuA)

LLMs have proven to be excellent tools for exploring our theories of mind, as well as spirituality. The culmination of a hackathon at Betaworks in April, “Dream Daimon” demoes how we might internalize the people we meet, and the things we hear and think when we dream.

- Event context: AI Tinkerers July Meetup — 2024-07-24 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp__pXksTkstuA

### [CodeDD - AI based code due diligence](https://vienna.aitinkerers.org/talks/rsvp_fPek6RNCqtM)

A tool for AI (LLMs) based code review for startups and investors alike. Easy: Copy git repo Complete: +40 code quality parameters Secure: No line of code is disclosed or stored

- Event context: AI Tinkerers Vienna ICML Edition — 2024-07-24 — Vienna
- Public talk page: https://vienna.aitinkerers.org/talks/rsvp_fPek6RNCqtM

### [How and why we use AI for creating serialized apparel](https://portland.aitinkerers.org/talks/rsvp_UfkXRFqKpd8)

Spot Vision uses machine learning to encode a digital record into graphic designs by introducing slight variations to the designs. These variations allows us to serialize the millions of items so that each is slightly different but still fitting a shared design intent. Designs can be read or authenticated by visually scanning. We will be demonstrating examples of serialized apparel covering a broad artistic range and talk about how AI drives optimization of encoding schemes and robust decoding from curved, obscured, and wrinkled surfaces.

- Event context: AI Tinkerers Portland Inaugural Meetup - July — 2024-07-24 — Portland
- Public talk page: https://portland.aitinkerers.org/talks/rsvp_UfkXRFqKpd8

### [In-Context Learning for Extreme Multi-Label Classification](https://chicago.aitinkerers.org/talks/rsvp_y-7-uutZyio)

How to leverage large language models to identify > 10,000 different labels with < 10 labelled examples for each class? And how to do it by systematically searching the prompt space without tinkering with prompts for each class? There is this Stanford paper (From Chris Potts' group) and an accompanying Github repository that offers an answer to the questions above. I have been tinkering with it. The idea was to share what I am learning with fellow tinkerers in a quick talk.

- Event context: AI Tinkerers Chicago July Meetup — 2024-07-23 — Chicago
- Public talk page: https://chicago.aitinkerers.org/talks/rsvp_y-7-uutZyio

### [Custom GPU-powered LLMs and Graph Neural Networks](https://boston.aitinkerers.org/talks/rsvp_LZl89lqLF3c)

A demo on running a variety of open LLMs with the power of GPUs. May dabble in using GPUs for graph neural networks trained on knowledge graphs.

- Event context: July 2024 Meetup at C10 Labs — 2024-07-22 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_LZl89lqLF3c

### [Testing LLMs despite non-determinism, hallucinations, and natural language](https://berlin.aitinkerers.org/talks/rsvp_UIY_LAtbPFk)

Testing applications that incorporate artificial intelligence is challenging. Components relying on natural language for input/output are a nuisance, but non-deterministic responses are the real problem. How can you automatically test apps that use LLMs? In this demo, we explore an approach to using LLMs to validate LLM responses and set up a practical testing environment. We'll use Testcontainers to programmatically spin up environments with Ollama; and use AI to validate whether AI responses meet our expectations. You can use the sample setup as a starting point and modify it as needed. It serves as a great starting point for discussions about testing applications with AI components.

- Event context: Ollama & Friends coming to AI Tinkerers Berlin — 2024-07-18 — Berlin
- Public talk page: https://berlin.aitinkerers.org/talks/rsvp_UIY_LAtbPFk

### [Browserbase Codegen](https://sf.aitinkerers.org/talks/rsvp_5c6ARxGau98)

This is a demo of a new way to generate repeatable code from human actions in a web browser. It paves the way for teaching AI how to use the web like a human.

- Event context: AI Tinkerers - San Francisco - Summer Edition - July 2024 — 2024-07-12 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_5c6ARxGau98

### [Post-Postman: Creative End-to-End API Testing with Generative AI](https://sf.aitinkerers.org/talks/rsvp_Ii4KZVOxftI)

Traditional API testing clients treat your service like a blackbox. They are unaware of the code running on each request, and unless you give them a spec, they're unaware of the inputs each route should expect. What does it look like when you use generative AI to bring this intelligence into an API testing client? Well, aside from helping with common toil of manually writing request parameters, I also see a path to more creative debugging and end-to-end testing workflows.

- Event context: AI Tinkerers - San Francisco - Summer Edition - July 2024 — 2024-07-12 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_Ii4KZVOxftI

### [LearnQuantum: AI Native Physics Engine](https://sf.aitinkerers.org/talks/rsvp_L724yA7lINQ)

LearnQuantum's AI-native physics engine translates natural language into precise physical simulations across multiple scales, from quantum to cosmic. Built on existing AI frameworks and architectures, including large language models (LLMs), it parametrizes and quantizes physical laws to produce complex simulations that ensure physically consistent results. This tool also generates synthetic data and optimizes complex systems. By facilitating rapid hypothesis testing, LearnQuantum accelerates scientific discovery and extends AI capabilities in physical reasoning, with potential revolutionary impacts in fields such as drug discovery and quantum computing. During my presentation, I will demonstrate the simplicity of generating real-time physics simulations from various prompts and managing complex physical data across different modalities, including interactive, static, and video generations.

- Event context: AI Tinkerers - San Francisco - Summer Edition - July 2024 — 2024-07-12 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_L724yA7lINQ

### [momentum - ensure code correctness at every git push](https://sf.aitinkerers.org/talks/rsvp_kVITxR9pLHE)

momentum is a code auditor that analyses the necessary code behavior and tests it at every git push to ensure the code is ready for production.

- Event context: AI Tinkerers - San Francisco - Summer Edition - July 2024 — 2024-07-12 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_kVITxR9pLHE

### [ExamGPT - An AI tool to help you prepare for your exam](https://seattle.aitinkerers.org/talks/rsvp_BvyjJi6DNdk)

Using flash cards to prepare for an exam is an incredibly useful technique, but creating flash cards is an absolute pain! So I created this application that uses AI to do it for you. It uses openai to generate the flash cards after chunking the content. The biggest problem was weeding out chunks that contain content that don't make for good flash cards (eg table of content, or page containing information about the exam itself). PDF parsing still seems very rudimentary in python. The live demo would be similar to the youtube video I linked to.

- Event context: AI Tinkerers Seattle - July 2024 Meetup — 2024-07-12 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_BvyjJi6DNdk

### [Collaborating Agents](https://toronto.aitinkerers.org/talks/rsvp_MrhTOEptmUo)

In a world where AI agents increasingly drive decision-making, trust is paramount. This demo explores teams of collaborating agents, and how blockchain technology can address the trust problem in AI. By leveraging blockchain's decentralized and immutable ledger, we can ensure transparency, accountability, and security in AI operations. Discover how these technologies converge to create a future where AI decisions are transparent and verifiable, fostering trust between technology and humans.

- Event context: AI Tinkerers - Toronto - June 2024 Meetup — 2024-06-27 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_MrhTOEptmUo

### [Unlocking Insights from Tabular Data with LLMs](https://toronto.aitinkerers.org/talks/rsvp_EVqtcfX0ujE)

This application demonstrates how we can leverage Large Language Models (LLMs) to extract valuable insights directly from your company's tabular data. Unlike unstructured data (PDFs, Docs etc.) that require Retrieval-Augmented Generation (RAG) techniques, this approach allows LLMs to interact with structured data in a more efficient way. Here's how it works: Natural Language Understanding with LLM: The user submits a question in plain text. The LLM parses this question to understand its intent and the relevant data points needed. SQL Query Generation: Based on the understanding, the LLM generates a corresponding SQL query to retrieve the desired information from your company's data warehouse. Data Retrieval and Summarization: The generated SQL query is executed, fetching the relevant data points. Finally, the LLM summarizes the retrieved data in a clear and concise manner, providing a comprehensive answer to the user's initial question.

- Event context: AI Tinkerers - Toronto - June 2024 Meetup — 2024-06-27 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_EVqtcfX0ujE

### [OpenSesame Demo](https://toronto.aitinkerers.org/talks/rsvp_7C5CZ6quT8M)

OpenSesame is a plug-and-play API that detects AI hallucinations and improves response accuracy for companies using LLMs. Our platform leverages context-based information to detect hallucinations in LLMs with precision. By ensuring accurate and error-free text generation, we provide a reliable solution for enhancing AI outcomes.

- Event context: AI Tinkerers - Toronto - June 2024 Meetup — 2024-06-27 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_7C5CZ6quT8M

### [AI-powered Legal Contract Analysis POC](https://kuala-lumpur.aitinkerers.org/talks/rsvp_SRNn5lVdOsI)

We are using LLMs to help do legal contract analysis in the following areas: 1. Clause Identification (and custom Key clause identification) 2. Clause Recommendation 3. RAG over Contract

- Event context: AI Tinkerers Kuala Lumpur - June 27th — 2024-06-27 — Kuala Lumpur
- Public talk page: https://kuala-lumpur.aitinkerers.org/talks/rsvp_SRNn5lVdOsI

## Related Technologies

- [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
- [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
- [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
- [PyTorch](https://aitinkerers.org/technologies/pytorch) ([Markdown](https://aitinkerers.org/technologies/pytorch.md)) — 273 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
- [RAG](https://aitinkerers.org/technologies/rag) ([Markdown](https://aitinkerers.org/technologies/rag.md)) — 147 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
- [Machine Learning](https://aitinkerers.org/technologies/machine-learning) ([Markdown](https://aitinkerers.org/technologies/machine-learning.md)) — 20 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
- [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/bert.md?page=4
- Next: https://aitinkerers.org/technologies/bert.md?page=6