ChatGPT versus DeepSeek (it starts with valid moves, then deteriorates, and both boths keep giving nonsense explanations of their moves)
The most recent ChatGPT versus Stockfish (this one has a twist at the end, I won’t even spoil it)
He also did his own Chatbot Chess Championship (playlist is in reverse order, so I linked the last video in the list, which is the first game).
The host plays the games out on-screen for you, with explanations and commentary. These ones aren’t for serious chatbot-testing purposes, they’re for entertainment — so when the bots make up illegal moves, he usually just runs with them. Sometimes with narration like “and here ChatGPT summons an extra rook from another dimension” or “You might think this is just a pawn, but Grok knows it’s secretly a horse pawn!”
Once in a while, he’ll tell the bot its move is illegal. Some of them go into “yes, of course, you’re right, my mistake” sycophancy mode. Others just get weirder.
The bots teleport pieces through each other. Manifest already-taken pieces back from the Shadow Realm. Spawns more pieces than it had to start with. Move pieces in directions they don’t go. And just because it’s making up moves, doesn’t mean it’s making up good moves! Sometimes it takes its own pieces. Sometimes it puts itself in check!
Sometimes they also generate their opponent’s moves. Because “black moves 1” is typically followed by “white moves 2, black moves 3, white moves 4” — and the bots don’t actually have a meaningful sense of “stop auto-generating text at the end of move 1.”
I was curious if the LLM’s idea of moves included “making up whole new categories of pieces” or “moving to squares that aren’t on the 8×8 chess grid.” Haven’t seen either of those so far.
One thing I didn’t anticipate is, sometimes a bot tells the other player their move is illegal. Even when it’s not! Saying “there’s a piece in your way” (when there isn’t), or “the king can’t move to E7” (not for any rules-based reason, the bot was just gatekeeping E7).
The newer bots also give general paragraphs on “here’s the explanation for my move,” which are absolutely just LLM Word Salad(TM) made of chess words. As a person who knows Basic Chess Rules but doesn’t actively play the game, sometimes I need GothamChess’s breakdown to see why they’re nonsense. Other times it’s just the bot saying “I have put you in check!” when the other player is blatantly not in check.
The whole thing was very informative, and also really entertaining. (…And it doesn’t involve the chatbots doing anything consequential, so it’s a nice break from all the stories about LLMs putting someone’s life in danger.) Give it a look.
Remember how last year, I watched (and wrote about watching) Mawaru Penguindrum, and paired it with the episode reactions from the Imagine Me & Utena podcast? And how the IMAU reactions had only gotten through episode 17, but they had been on hiatus for long enough that I figured they weren’t going to come back to it, so I went ahead and watched the rest of the show?
The IMAU folks came back! After a year-and-a-half gap, they started up again, and got through the rest of the series!
(It’s in my folder of “podcasts that stopped updating a long time ago, but didn’t officially finish, so I check in once or twice a year, just to see if anything’s changed.” And sure enough, something had.)
Overall, I didn’t like the Penguindrum anime. There were some good parts, even a few great ones, and I still listen to the music — but that wasn’t enough to outweigh all the parts that were bad/rushed/nonsensical/poorly thought-out/generally-unpleasant.
Still looking forward to finally finishing the IMAU recaps. If you’re a fan of the series, or even if you also didn’t care for it but ended up watching the whole thing, check them out. (Direct link to the RSS feed.)
Charlie Morningstar, Princess of Hell, opens the titular hotel with the goal of “helping demons workshop their way to earning a spot in Heaven.” Most demons aren’t even interested, the handful that show up all have ulterior motives, and the other plot threads happening around it involve murder, genocide, hard drugs, and sex slavery. Watch Charlie flail her way through the hopelessly-doomed prospect of coaching this crowd to “do trust falls with each other” and “sing songs about how to apologize”!
Accurately described as “what if somebody got to make a professionally-animated TV series with all her 2000s-era DeviantArt OCs?” That’s not a complaint — they are good designs, aesthetically pleasing, fun to watch — it’s just a description of this very specific energy they bring.
Based on fandom osmosis, I was expecting a good amount of darkness and irreverence, with a generous serving of sexy iddiness. (Of the two characters whose names I knew before I started watching, one of them is the gay porn star who presents himself as sassy and slutty but is hiding a deep vulnerability in his soul. Obviously fandom loves him.)
I didn’t realize it was going to do all that and try to have fully, unironically earnest messages about love and redemption. Charlie’s quest is not hopelessly doomed! And the show does actually want you to get on board with that! One minute you’re getting a totally-serious song about the power of fighting for love (did I mention this is also a musical?), the next you’re getting a comically-bloody scene about the demon whose gimmick is indiscriminate stabbing!
It mostly works, too. You would really expect this to fall apart, and there are points where it teeters, but overall it holds together as it soars through the first season and sticks the landing.
Weird and enjoyable. Looking forward to season 2.
Marvel Zombies:
A very short (4 half-hour episodes) expansion of that one What If…? episode. I never like zombie stuff, but I do like post-apocalyptic survival stuff…and, listen, it had some new tidbits of Moon Knight stuff. So I had to catch it at some point.
I liked all the scenes that focused on “here’s a handful of disparate MCU characters who got thrown together by the weird circumstances, let’s watch them wrangle the apocalypse as a team.” In general, it felt like the character interactions were written by people who liked them, and put some thought into them. (After that disappointing s3 episode with Shang-Chi and Kate Bishop, it’s extra-refreshing to see an AU where Shang-Chi and Katy’s friendship gets to shine, and Kate gets a subplot with a trick arrow.)
But then the show tried to have an over-arching plot. And it felt like the plot was written by people who thought “Wanda makes a cool and terrifying villain, so our priority is to make her a cool villain, and we don’t really care how she got to that point or whether her motives make any sense.”
The MK content was “in this AU, Marc and company got zombie’d early in the outbreak, and their buddy Blade was recruited as next Moon Knight.” This is the MCU version of Blade, who suffers from a bad case of His Main-Timeline Debut Hasn’t Actually Happened Yet. So I don’t blame these writers at all for not knowing what to do with him. (The guy is half-vampire, there should be all kinds of questions to explore about how that interacts with a mostly-zombified world — and this show has no interest in any of them.)
At least we got a cool new MK suit design out of it. And a fun scene of Khonshu having an argument with Valkyrie.
Knights of Guinevere:
Sci-fi psychological horror, which is also a scathing commentary on the creator’s career as a Disney animator. Follows a couple of friends who live and work in the garbage-strewn shadow of a planet-sized theme park, and a broken android (?) mascot who could really use their help.
Only the first episode is finished right now, so there’s a lot we can’t know, but it’s so rich and dense with worldbuilding info that there’s a ton of possibilities to speculate about. At this point I’ve seen multiple “breakdown of all the little things you missed in the Knights of Guinevere pilot!” videos, and haven’t stopped picking up new details yet.
Very excited to see where the rest of the series goes.
Roughly in the reverse order they were finished, most-recent first.
Technically the round ends on the 30th, but I'm not jumping on any new tags at this point! So this is the final version of the list.
I thought about emoji-coding these based on how much work I did ("just one of the final syn checks", "some of the synning", "basically all the synning", etc)...then decided, no, that's too much effort. The point is, over the last 3 months, I did Some Amount Of Wrangling on every single one of these:
![[community profile]](https://www.dreamwidth.org/img/silk/identity/community.png){kind=small}
![[personal profile]](https://www.dreamwidth.org/img/silk/identity/user.png){kind=small}
erinptah
