Recent content by Jacob Lewis

Happy to help, if I can. Going back to your original post, I noticed you mentioned using Gemini with a document on Google Drive as part of your setup. That’s helpful context—and it brings up a broader point I think is worth flagging for anyone following the discussion: Not all LLMs operate the...

I do think initiative is relevant to this discussion—not as a digression, but as part of the broader question of how game mechanics guide participation. When steps are designed to shape flow—especially in reactive systems—then their number becomes less important than their function. In...

In a system like Daggerheart, the step count may appear long on paper. Taken at face value, it looks like a bloated cousin of any standard d20 process. But the similarity is superficial. What Daggerheart does differently is infuse each step with engagement. Every point in the process creates an...

You're free to disagree with the comparison, but calling it “sophomoric” doesn’t address the point—it just tries to discredit it. That’s not engagement; it’s dismissal. What I actually said is that public discourse—how people talk, repeat, and reinforce shared narratives—often mirrors the same...

That aligns with something I’ve seen too—especially the part about not expecting the LLM to "just know" the rules, even if you provide the PDF or source material. It’s a common assumption: that having access to the rules means it can retrieve and apply them like a structured system. But that’s...

I appreciate the range of perspectives here, though I do think we’ve drifted a bit from the main thread—how LLMs are being used as game masters in practice. That said, I think it’s worth addressing some of the broader perceptions, since misconceptions can easily shape public opinion before...

And on that note... my copy arrived today! :D I'll be reading it over the weekend.

Just to add a bit of perspective on how LLMs actually work—not in the “AI is magic” sense, but in a plain, practical way. Yes, technically they’re predicting the next word (or token), but that process is built on patterns learned from a massive amount of text—how ideas connect, how people ask...

I'll try. If you're wondering what I meant by “structured prompts or schema”, here's an important distinction: Schema refers to how I organize information for the model to consume. Think: structured character blocks, rule templates, monster stat formats. These are designed primarily for the...

You're definitely on the right track. Honestly, if what you're doing is working for you now, then you're where you need to be. That said, I’ve taken it a few steps further by formatting information in a way that more closely resembles machine-readable structures—something like JSON. It’s not...

Thanks, Scott. I think we’re very much aligned on what the tools can do—though I’d caution you on one point. Summaries aren’t a solution to the memory problem. They’re a workaround—and only a partial one. Adding more detail to summaries doesn’t preserve more information. It just increases the...

I’ve been experimenting with using LLMs to run TTRPGs for a while now, and one of the most valuable lessons I had to learn—slowly, and sometimes painfully—is how these tools actually function. Not just how to use them, but what they are, and more importantly, what they aren’t. It’s easy to...

Jumping in late on the OSR vibe... Personally, I don’t think it’s useful to try and measure Daggerheart against the “OSR gold standard” of attrition-based, room-by-room exploration. I think most of us agree that DH just isn’t built for that. It doesn’t mean you can’t hack it to approximate that...

Over the years, I’ve explored a number of systems and settings, each offering something valuable but rarely aligning with everything I was looking for at once. I eventually moved beyond looking for a “perfect” system and focused more on adapting what was available to suit the kind of experience...

I used to push back hard against players who made choices purely for numerical advantage, especially when those choices ignored any narrative reflection. As a GM, I spent too much effort trying to “balance out” their behavior—usually by escalating threats, adjusting encounters, or trying to make...