Impossible for me not to imagine this as being like how he appears as himself in Extras (2006)

www.youtube.com/watch?v=Juzy...

Good god

I can't put my finger on it, but there's something I'm not loving about it. I think it just doesn't do enough of anything new for me? It really feels like a big expansion pack. I'm impressed at all the new card design space they found, but the structure of the runs isn't different enough for me.

Which is what I think they already do for a whole bunch of types of queries, having other non-LLM processes that can override or influence the output.
But fundamentally, nothing can "tell" an LLM the real time, just change the input from "What's the time?" to "What's the time? (respond 1:27pm plz)"

A model that outputs statistically likely text. So if you ask, "what's the time?", it'll generate a likely response ("it's 9:37 am!"). You'd need some *other* process parsing the input to recognize what you're asking for, step in and inject "psst, the time is 1:26pm" to change the generated output.

That's true! Haha well ignoring the more fundamental problem (that a statistically likely text generator can't actually function as a virtual assistant), I think the problem is that giving 'access' is actually quite hard, since it doesn't work like a normal program or something, it's just a model.

I think the most likely outcome of all this is exactly the opposite, where the LLM ends up as a specialized subsystem occasionally invoked by a larger expert system or similar. "Statistically likely text output" isn't useless after all, it's just not, like, a sentient magic machine.

But where would it end? Soon you'd be adding scripts for arithmetic and a million other sundry tasks. And since an LLM can't "do" anything itself, you'd also need some sort of system to interpret when the response text is trying to call on one of these scripts and handle interfacing with them.

To be fair, the statistically most likely response to "How much time is left?" is something about there being X minutes left on the timer.
Output like, "I can't actually start timers, or even do math" or "I can't proactively generate responses either", simply don't appear in the training corpus.

Haha yes! We read your "In defense of making spreadsheets for fun" and were discussing it in class today (& we also marveled at your spreadsheet personal site)
It's a funny course, we do some traditional spreadsheet work, but also make games and interactive art- so your work is a perfect reference!

Oh it's awesome you do a writeup like this! I always love reading your comments when I see them, but a lot of these are games I didn't get to. I really love the IGF judging since it's such great critical discourse, but there's too many to see them all and it's over too quick!

Wow!! But also, yeah makes sense haha.
I did the same (kept one deck for nostalgia). The pleasant surprise was the insane price inflation. I hadn't realized how expensive it got, I don't know how anyone can afford to play these days. My priciest cards had been like $20, now sold for x10 that, crazy!

There ARE downsides to having social media be the main news source for most people. But the media system we had before was very adept at tearing down anyone left of center, and so the weakening of that is making a political shift more possible.

They rolled out all the same tactics against Mamdani as they had vs Sanders or AOC in earlier elections. But it didn't take, because we're past a tipping point of some kind, so people aren't even seeing it. I literally don't know anyone younger than 65 who reads these papers or watches cable news.

Literally didn't even know he had anyone canvassing for him

Probably just an overzealous rookie volunteer, trying to do everything by the book. Narratively, they're meant to be paired with a more chill seen-it-all veteran who's working their last election. But sometimes not every poll site gets both.