https://github.com/tjpalanca/tjbots
TJ's adventures with LLMs
https://github.com/tjpalanca/tjbots
chatbot llm py-shiny python
Last synced: 11 months ago
JSON representation
TJ's adventures with LLMs
- Host: GitHub
- URL: https://github.com/tjpalanca/tjbots
- Owner: tjpalanca
- License: agpl-3.0
- Created: 2025-07-03T12:41:42.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-08-12T18:09:51.000Z (11 months ago)
- Last Synced: 2025-08-12T18:29:15.909Z (11 months ago)
- Topics: chatbot, llm, py-shiny, python
- Language: Python
- Homepage: http://github.tjpalanca.com/tjbots/
- Size: 1.33 MB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 4
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# TJBots 
## Motivation
To explore the [jagged
frontier](https://www.oneusefulthing.org/p/centaurs-and-cyborgs-on-the-jagged)
of the capabilities of LLMs, I think the right approach is to be very
experimental - try out new use cases and see how we can tweak the
various levers (prompts, models, tools, configurations) to solve the
goal.
In order to do that, I think we need to build a test harness for trying
out various configurations against different problems, for the following
purposes:
- to reduce the time from an idea (hey, maybe I can use an LLM to solve
it) to implementing it in code where I can hold it and use it in my
day-to-day life, and
- if there are problems that are currently unsolvable, be able to take
advantage of new research and tools developed to re-visit them in the
future.
- make it easy for me to share my findings with others, so that they can
benefit from my work and I can learn from them.