If the split is going to be a longer term thing, I like to run 1 group at a time and have the players who are not in the split group run temporary characters or NPCs. Usually those are something like MCDM Followers/Companions or just simplified PC characters so that there isn’t much of a learning curve, but it just depends on the people at the table.
If the party already has bunch of followers or NPC friends, it’s really easy and people seem to enjoy taking the reins of their favorite NPC’s for a few sessions. It’s also a nice chance for players who like trying our different builds to have a small timeline to try something out with an NPC, and it adds the bonus of shared worldbuilding.
Once the first group is finished, we swap roles and pick up the second group.
Its best to keep this limited in scope, make sure its not more than a few sessions per group, and to only employ it occassionally.
However, if it’s only for a part of a session, I go for the A/B storyline in a TV show strategy and tend to verbalize the “camera” a bit more, especially if it makes sense to give some subtle progress hints to the other group so they don’t feel the need to worry too much about metagaming. If one group in in combat while the other isn’t, I’ll switch back to the non-combat group after every round or two. Gives everyone a little more time to get their bearings in a reduced party size and makes the combat action feel a little more intense with some good ol’ tension and release.
“OK, as Jimothy unlocks the door and peers inside, it’s dark and will take a moment for their eyes to adjust. Swords McGee, watching Jimothy’s back, nothing seems out of the ordinary from the perception check, but he does see a flash of orange on the northern wall of the compound where your friends should be at, followed by the distant, unmistakable crack of your allies fireball spell.”
“back to the rest of the group, Bobby Fireballs finished up last round by blowing up the guard station, top of initiative, the guard captain…”
It doesn’t always go that smoothly, but you’d be surprised how easy it can be once you get in the rhythm of when to change cameras. Its also very important to briefly summarize a hook when changing cameras to transition everyone elsewhere.
If it makes more sense to stay with one party for the entire combat, I’ll usually hand over a few monsters to the non-participant players so they have an opportunity to be doing something, if it makes sense.
I’m not entirely against LLMs as a tool, but I especially despise the image-based LLMs. They are certainly neat for some fun things. I’ve used them a little bit here and there for a dumb profile picture or a “I’m kinda thinking about this…” Brainstorm, but even in those cases I noticed the capabilities of the LLM and its tendencies quite literally pidgeon hole my artistic vision and push me in other directions that felt less and less creative. (Sidenote: I feel the same way about coding LLM tools. The longer I use them at any given time, the less creative I feel and it has a noticeable impact on my interest in the code I’m writing. So I don’t really use them much. Also I consistently manage to point out coding LLM code in PR reviews because it’s always kinda funky)
I’ve avoided using AI art tools for a while now. I’ll consider some limited use if the cost, billionaire ownership, blatant theft of real IP without compensation, and environmental impact problems are solved. (No, an “open source” model doesn’t solve all of these problems, especially since nearly all open source models are not truly open source and are almost always benefiting from upstream theft)
You know what I do like about AI art? I like the older Google machine learning art experiments from the mid-2010s. They invoked a strange existential curiosity. But those weren’t done with LLM’s.
Outside of LLMs, I like that there are some newer tools for editing that can do a better “lasso” select, that can mix and match into brushes as an alternative to something more algorithmic, the audio plugin that uses a RNN to simplify or expand upon an audio technique. Things that are tools that can be chosen or avoided and have nothing to do with LLMs.
I honestly cannot wait for this bubble to burst and for these tools to return to a cost that they’d need to be for these companies to turn a profit. A higher cost would eliminate all this casual use that is making people worse at research, critical thinking, and creativity, as well as make the art tools less competitive to just paying artists, even for scumbags wanting to cut the artists out. And it’d incentivize non-LLM, non-insanely costly ML techniques again instead of the current “LLMs for everything” nonsense right now.