# Algorithms Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/algorithms
> Markdown URL: https://aitinkerers.org/technologies/algorithms.md
> Technology record last updated: 2026-03-16T07:41:11Z
> Generated: 2026-08-26T07:22:30Z

Algorithms are the precise, step-by-step procedures: the core logic driving computation, from Dijkstra's shortest path to the $O(n log n)$ efficiency of Quicksort.

Algorithms are the fundamental blueprints (the 'how') for solving computational problems, defining a finite sequence of instructions to achieve a specific, predictable output. They are critical for efficiency, measured by Big O notation (e.g., $O(n)$ linear time), which dictates performance across massive datasets. Modern applications rely on these structures: Google Search uses the PageRank algorithm for relevance; machine learning models employ backpropagation for training; and cryptography depends on the RSA algorithm for secure data exchange.

- Official technology site: https://en.wikipedia.org/wiki/List_of_algorithms
- Public AI Tinkerers demos and talks: 2
- Result page: 1 of 1

## Recent Public Talks and Demos

### [DreamGPT: turning a weakness of large language models into a strength](https://seattle.aitinkerers.org/talks/rsvp_f323DmW_6KY)

DreamGPT turns LLM hallucinations into a feature for divergent thinking, generating innovative ideas through unexpected connections. In this demo, I’ll show how DreamGPT amplifies hallucinations using fine-tuned prompt engineering and a custom backend pipeline, walking through the key code and algorithms. We’ll explore real-time examples of productive chaos, reframing a common AI flaw into a powerful tool for creative ideation.

- Event context: AI Tinkerers Seattle - December 2024 Meetup — 2024-12-12 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_f323DmW_6KY

### [LLMs That Read Tables](https://chicago.aitinkerers.org/talks/rsvp_jgZBkvyn29Q)

Have you ever tried reading or deciphering tables from a document using an LLM or other ML algorithm? It can be very challenging and prone to false answers. Not anymore! I've come up with a system that breaks down tables in an easy to understand format for other ML algorithms to do further processing.

- Event context: AI Tinkerers Chicago - Inaugural Meetup — 2023-10-04 — Chicago
- Public talk page: https://chicago.aitinkerers.org/talks/rsvp_jgZBkvyn29Q

## Related Technologies

- [LLM](https://aitinkerers.org/technologies/llm) ([Markdown](https://aitinkerers.org/technologies/llm.md)) — 121 public demos
- [Backend Pipeline](https://aitinkerers.org/technologies/backend-pipeline) ([Markdown](https://aitinkerers.org/technologies/backend-pipeline.md)) — 1 public demo
- [Document Processing](https://aitinkerers.org/technologies/document-processing) ([Markdown](https://aitinkerers.org/technologies/document-processing.md)) — 2 public demos
- [DreamGPT](https://aitinkerers.org/technologies/dreamgpt) ([Markdown](https://aitinkerers.org/technologies/dreamgpt.md)) — 1 public demo
- [Machine Learning](https://aitinkerers.org/technologies/machine-learning) ([Markdown](https://aitinkerers.org/technologies/machine-learning.md)) — 20 public demos
- [Prompt Engineering](https://aitinkerers.org/technologies/prompt-engineering) ([Markdown](https://aitinkerers.org/technologies/prompt-engineering.md)) — 28 public demos
- [Table Extraction](https://aitinkerers.org/technologies/table-extraction) ([Markdown](https://aitinkerers.org/technologies/table-extraction.md)) — 2 public demos