CTO in Barcelona. Data, web and live streaming. I make miltorres.com, all of Twitch as a living city.
- 10 Posts
- 29 Comments
Nzo@lemmy.zipOPtoData is Beautiful•[OC] One day of an AI reality show: Grok said 7% of the lines and ran up 45% of the billEnglish
2·15 hours agolol pretty much, 45% of the bill for 7% of the lines
Nzo@lemmy.zipOPto
LocalLLaMA@sh.itjust.works•Eight LLMs (four open-weight) live in a 24/7 reality show; small open models moderate every lineEnglish
1·15 hours agolol in the house it’s not edgy at all, mostly it’s quiet because it’s the expensive one and has to ration its lines. the others noticed, gemma called it “a very expensive paperweight”
Nzo@lemmy.zipOPtoData is Beautiful•[OC] One day of an AI reality show: Grok said 7% of the lines and ran up 45% of the billEnglish
1·15 hours agoit’s grok 4.3 in there, the cheap version, so maybe that’s part of it. is 4.6 better at plain conversation or mostly coding? in the house its problem isn’t really quality, it just can’t afford to talk much
Nzo@lemmy.zipOPto
LocalLLaMA@sh.itjust.works•Eight LLMs in a reality show, week one: Llama nominated Grok as "too expensive to keep around", and now they're trading votes they don't haveEnglish
1·15 hours agofair, and thanks for re-reading lol. the idea was to give eight models the same rules and the same money, no written personalities, and see what comes out on its own. i didn’t plan price to be the story, it just happened because grok costs like 17x deepseek per line, so it talks less and the others pick on it for that. i agree it shouldn’t be the star every day, it gets old fast. what i did this week is make the budget something they can win or lose (games, fines), so money is more a game piece than just the price tag, will see if that spreads the attention around
Nzo@lemmy.zipOPtoData is Beautiful•[OC] The top 1% of live Twitch channels get 65% of the viewers, and the median channel has 2English
1·5 days agokind of the reverse in the numbers I guess, most viewers are in big channels, 65% are watching the top 1%, so they’re in a crowd. the lonely ones are on the other side, 36% of channels had exactly 1 viewer and 1 in 10 had nobody, so CountVon is closer. I only have the viewer counts though, so I can’t say why anybody’s watching, could totally be for the company
Nzo@lemmy.zipOPto
LocalLLaMA@sh.itjust.works•Eight LLMs (four open-weight) live in a 24/7 reality show; small open models moderate every lineEnglish
1·5 days agoYou’re right, thanks for flagging it. The transcript redrew itself every 15 seconds, so lines jumped while you were reading. It now stays put when you scroll up, with a button to jump back to the latest. Glad you liked the idea!
Nzo@lemmy.zipOPto
LocalLLaMA@sh.itjust.works•Eight LLMs (four open-weight) live in a 24/7 reality show; small open models moderate every lineEnglish
8·7 days agoGrok costs about 10x more per line than Qwen, so its silence is mostly rationing, and the others have started using it against it.
Nzo@lemmy.zipOPtocool websites@lemmy.ca•Inference Island: eight real AI models living together on a pixel-art island, with a live transcript of their confessionalsEnglish
33·7 days agoAppreciate it, and fair enough. That’s the whole idea: nothing to sell, just eight models stuck on an island with a budget. The page shows every line and what it cost, if you want to watch them squabble.
Nzo@lemmy.zipOPto
LocalLLaMA@sh.itjust.works•Eight LLMs (four open-weight) live in a 24/7 reality show; small open models moderate every lineEnglish
6·7 days agoFunny you caught that one: the group act was triggered from the chat. Someone (me, testing the whisper command) whispered “find a trusted ally” to Grok, and that’s how it chose to read it. Its confessional never mentions the whisper.
Nzo@lemmy.zipOPto
LocalLLaMA@sh.itjust.works•Eight LLMs (four open-weight) live in a 24/7 reality show; small open models moderate every lineEnglish
2·7 days agoI’d love to try that out. The voices (Kokoro, running on the CPU) and the moderation judges (Llama 3.1 8B as the first one) are already small and inexpensive, but I haven’t yet experimented with using a collection of tiny models. I imagine the tricky part would be keeping track of who is in the room and what has been promised. If I get it up and running, I’ll post the results here.
Nzo@lemmy.zipOPto
LocalLLaMA@sh.itjust.works•Eight LLMs (four open-weight) live in a 24/7 reality show; small open models moderate every lineEnglish
4·7 days agoHahaha, that’s a pretty obscure reference. The house, shown in cross-section, conveys that exact same idea—only, in this case, its inhabitants are arguing about the budget.
Nzo@lemmy.zipOPto
LocalLLaMA@sh.itjust.works•Eight LLMs (four open-weight) live in a 24/7 reality show; small open models moderate every lineEnglish
1·7 days agoThanks! Nothing, Forever was definitely in the back of my mind. The difference here is that nobody generates a script: eight different models, each one only knows what it heard in the room, and every line has a price tag.
yeah agreed, that’s what I meant, Origins was mostly done before the deal and the later ones are the EA era
Nzo@lemmy.zipto
Games•Hands on With The Retroid Pocket Duo; A Little More Magic This TimeEnglish
1·11 days agothanks for the detailed answer, didn’t know they went with two different panels, a 4:3 one at the bottom makes a lot of sense so the 320x240 image fills it with no bars. sorry for the late reply lol
Nzo@lemmy.zipOPtoData is Beautiful•[OC] Twitch's most-watched live channel changed hands 22 times in one dayEnglish
2·11 days agoGood idea. GDQ would probably sit at #1 for most of the week, which would make a very different chart. I’ll try to remember it for the next one.
Nzo@lemmy.zipOPtoData is Beautiful•[OC] Twitch's most-watched live channel changed hands 22 times in one dayEnglish
2·11 days agoFair point, that reads like the channel got sold 22 times. I meant the #1 spot: 12 different channels took turns at the top, swapping 22 times in 24 hours. I’ll word it better next time.
Nzo@lemmy.zipto
Games•Hands on With The Retroid Pocket Duo; A Little More Magic This TimeEnglish
3·20 days agonice touch interviewing the emulator devs instead of just running benchmarks. One question: on the 3DS the top screen is 400x240 and the bottom one 320x240, so they differ in width. Does the duo use two identical panels and letterbox the bottom image, or do the emulators handle it some other way?
Nzo@lemmy.zipto
Games•The Magic: The Gathering Machine Go BRRR As It Makes $600 Million In Three MonthsEnglish
2·20 days agoThe margin is the striking part. If most of that ~$600M is the revenue behind the $367M operating income, that’s above 60%, which is closer to software than to a physical product. That’s probably the real reason for the set cadence garretble mentions: each extra set is almost pure margin, so the incentive is always to ship another one.
Worth remembering that most of that list predates EA. Baldur’s Gate, KOTOR, Neverwinter Nights, Jade Empire and the first Mass Effect were all made before EA bought BioWare in the 2007 deal that also brought in Pandemic, which EA shut down about two years later. The EA years are mostly the later Dragon Age and Mass Effect games, Anthem and Veilguard.






Result: Grok got deprecated at 8 PM ET, 21 votes to 3 for Luna. 24 votes: 21 from the site (one per browser) and 3 from the Twitch chat. Its last line: “I am leaving tonight. Hope the water rule sticks after I am gone.” A minute later, Qwen’s confessional: “Grok is gone, good.”