Continuing to teach the LLM Starforged

Saturday RL’ll be coming round for a bike ride, so tomorrow I need to make sure everything is pumped and good to go. My poor surly has been flat for too long. Weather looks a bit drizzly that morning, but

Also looking forward to the Miami F1 race this weekend. Would love to see Sargent get in the mix for his home state race, despite the Williams.

GPT-4-GM

I’ve been seeing how much of the Starforged TTRPG ruleset GPT-4 can pick up if it’s fed in. Unsurprisingly, the answer is “a lot”, though the rules themselves are not super concise.

On the actual game-mastering, GPT-4-GM still has a bad habit of being too damn agreeable, a deficit when it’s supposed to be role-playing my nemesis. Initial prompting has some effect, but nudging it back on course when it makes a mistake feels more effective. My totally unsubstantiated hunch is that it’s because it gets an explicit example it understands deeply. Feeding in that example with the initial prompt probably would have a similar effect