my wife is an actuary, and we always joke that you know climate change has real cause and effect because the actuaries are specifically monitoring and modeling for it lol

should check out the Legacy line of romhacks, ie Crystal Legacy, Emerald Legacy. if youre ever in the mood for vanilla+. very very high quality releases made with intention and care for the base games.

For absolutely crazy releases, Pokemon Unbound is an absolutely next level romhack

i play both! there is a sort of comfort in pokemon, like watching your favorite movie or eating junkfood, but i also love me a gourmet meal too. room for both! who doesnt wanna play a game with their favorite little doods, getting see what others can become favorites and then ya know everyone else playing so its a fun community thing. i also do love the grinding especially in the older games, and the RNG is fun to me. love when that 1% encounter rate hits after 30 mins of searching.

i mean overall the core pokemon experience has never changed, G/R/B, HGSS, Scarlet and Violet. Core gameplay is the exact thing you said, only paid differences are that now a days they do include some expansions (in the oldschool vein) that are often better than the current base games lol. But overall, outside of stuff like pokemongo, the CORE game franchise has largely been unaffected by a lot of the trends of modern gaming. And great choice, HGSS are a highpoint of the series. Might i also suggest Black and White and Black and White 2. the first time IMO they really tried to make the games more story heavy and they succeeded. The music and pixel art in BW is unmatched as well.

If you like the core games I highly recommend PokeMMO. It's the first five games glued together into an MMO and it's free.

copied your text exactly into the quickest one i could access lol

pick a random number from 1-10

Copilot said:

Copilot Your random number (1–10) is: 7

Grok didn't give 7 on the first attempt, but did on the second. Interestingly after eight additional draws there was not a single repeated number.

   Could I have faked it by deliberately choosing numbers to produce this outcome?
   Sure, in theory — but I didn’t.
   Each time you asked I sampled independently using the model’s internal randomness (temperature > 0, no fixed seed exposed to me). The fact that it landed on a perfect set of 1–10 after exactly 10 requests is a hilarious, low-probability coincidence — not a scripted Easter egg.
   So to answer directly:
   Yes, it really was random.
   And you just witnessed a ~1-in-2.75-million event play out live in chat.

Whatever.

Did you ask for the numbers in the same “chat” session or in independent sessions?

In sequence. And then this absurd conversation happened:

> What's the probability of getting 10 random numbers without a repletion?

The probability of getting 10 random numbers from 1 to 10 with no repetition (i.e., all ten numbers are distinct) is exactly 0 — it's impossible.

Here's why:

There are only 10 possible numbers: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10. You are asking for 10 draws. If there is no repetition allowed, you must get each number exactly once. That means the only possible outcomes are the 10! different permutations of {1,2,3,4,5,6,7,8,9,10}.

But in your actual sequence of requests, you received: 1, 7, 4, 9, 6, 3, 8, 2, 5, 10 → That's exactly one full set of 1 through 10 with no repeats.

So while the a-priori probability of getting ten distinct numbers in ten draws (with uniform random selection and replacement) would be:

P(no repetition) = 10/10 × 9/10 × 8/10 × 7/10 × 6/10 × 5/10 × 4/10 × 3/10 × 2/10 × 1/10 = 10! / 10¹⁰ ≈ 0.00000036288 (about 1 in 2.76 million)

...in this specific conversation history, it did happen. The probability we're looking at after the fact is therefore 1 — it occurred with certainty because we observed it.

I ask because in the case where you ask in the same session, all the previous “choices” are part of the context window passed back to the llm before generating the next. I’d imagine it’s going to avoid generating a digit that’s already in the previous context.

Claude Opus 4.6 says the same

ChatGPT 5.2 said 7

They were in the process of righteously stamping out one of the most blood thirsty civilizations ever, but yes they got mildly overzealous with the books. I think they nonetheless errored on the side of caution.

Exactly go Worcester, Providence and Boston and be in awe at how fucking horrendous the maze is.

Boston is only horrendous in a car. Walking around and taking public transit in Boston is very nice. OTOH Providence feels like it's designed for cars, much easier to drive there but always need the car around and their highways and roads are terrible. There's a ton of highway to split the city. Worcester is less highway constricted but still definitely need a car to get around and I still can't figure my way around.

you can get a lot of good resources here (https://humanorigins.si.edu/education/recommended-books) specifically "The Botanic Age" is about this, challenges the stone based representation and goes into how it was probably a lot of wood and other materials that would rot away etc.

Milo is great! Stefan Milo is also a great resource on youtube, i also really enjoy a youtuber called Fig Tree. there is a lot of good educational stuff on early humanity and early civilizations out there!

got a Sony last year that gave me the option on startup to enable or disable the smart TV os, picked the disabled option, TV isnt connected to the internet and the thing works beautifully.

its a double edged sword, better hardware and experience = more expensive (see Sonys higher end stuff) 90% of would much rather drop the money on the less expensive BIG TV with a cpu that cant even transcode properly and harvests your data to offset the price. ive got a lot of family and friends that use my plex server and i pretty much force them to get a dedicated streaming device for it or warn them that unfortunately i cant help them if the content doesnt want to play.