Office Hours #1
Trying out a new thing.
Hey!
I’m starting this weekend with the idea of “Office Hours.” This will be a space for you to ask anything about AI or Computer Science in general and get straight answers from me and the rest of the community.
Including but not limited to:
Asking for clarification on concepts or ideas you don’t understand completely.
Asking for my opinion on current news in the AI and tech world.
Asking for advice for a concrete problem, application, or idea in general.
Engaging in philosophical discussions—I love these!
Sharing insights or things you’ve learned or seen recently.
And any other comments or ideas you want to share.
(If it’s a topic I’m not well-informed about, I’ll do my best to at least give you some pointers.)
Don’t limit yourself to asking questions; feel free to drop into any conversation and share your thoughts.
So, go ahead and leave me a comment. I’ll answer during the weekend… whenever my little monsters give me a break.
See ya!
Alex
I'm looking for a reinforcement API with an interface. I.e. I code my use case as class implementing the specified interface, and then pass that off to the API. My use case is backgammon variations. Specifically, hunting for variants that highly reward skill.
I usually just ask Copilot, but if you fancy competing: :-)
An LLM has to be trained on a vast amount of data which is then locked in. When I ask it a question and start a thread the context builds as the conversation goes to and fro. Where is the context held?