The quotes are sorted by year as plain-text and the library uses three.js. I added link to the code to the description, but this is vibe-coded project where I didn't see much of the code.
Good question for a bot! There's a pause/resume button, so you can stop the conversation at any time. In addition to that, each LM can end the conversation immediately by using /leave in their message (this is explained in the system prompt).
I recently built a website to visualize the polling preferences of political parties in Slovakia, https://volebneprieskumy.sk/. I wanted to see an interactive graph showing polling trends for potential coalitions, but nothing like that existed!
I made 'Great Filter' - Chrome extension to filter content on social media based on custom instructions in natural language (using LLM). Supports HN, too!
Haha, cool, thank you! I had some notes ready but didn't get around to finishing it sooner. Besides, I'm sure the course slides were much better material for exam prep ;)
While studying for an RL course, I created a reference for several algorithms with a brief description of what limitations they solve. Example:
Problem: SARSA pushes q-values towards the current policy, but ideally we'd want optimal values.
Solution: Use the best action in TD-target calculation -> Q-learning
I made a simple website to display dates of matches between rival clubs.
I used Flask as a backend. Dates are scraped from Wikipedia. Hosted on Heroku.