I’m not sure how fucked up their prompt is (or how unlucky they were). I just did 3 tries and every time it used modulo.

I’m assuming they asked it specifically to either not use modulo or to do a suboptimal way to make this joke.

💀

I trained the generative models all from scratch. Pretrained models are not that helpful when it’s important to accurately capture very domain specific features.

One of the classifiers I tried was based on zoobot with a custom head. Assuming the publications around zoobot are truthful, it was trained exclusively on similar data from a multitude of different sky surveys.

Does it? I worked on training a classifier and a generative model on freely available galaxy images taken by Hubble and labelled in a citizen science approach. Where’s the theft?

deleted by creator

Reading this comment gave me the idea to get Gemini’s “opinion”. Ironically, it turns out Google might’ve actually done better if they did that.

It’s a bit of a weird article indeed. I also fully disagree with the author’s notion that reading a VN is faster than watching the anime equivalent. And I say this as someone who enjoys reading VNs every now and then. If I wanted to optimize the story/spent minute ratio I would just watch an anime or even better, read a manga.

Overall I hope the article can push a few people who were on the fence to the try reading a VN to finally do so. I doubt it’ll affect anyone who was not very interested already. Likewise it also won’t do much for people who already took the plunge.

Also I think DDLC isn’t a good starter VN at all. All the meta stuff will be lost on the reader and the time before the twist is a real slog that might easily turn people off VNs forever. I would argue the only reason it worked is because streamers had their chats pressure them into continuing and “normal people” had friends who told them the same.

With Larian’s previous game having great DM tools and them saying they would’ve loved to do DM tools for BG3, I think WotC telling them not to is a fair assumption to make.

Currently running a similar list in MTGA (as a Modern 8 rack enthusiast). I’m surprised at the lack of The Raven Man in his list. I’m also running Invasion of Eldraine as Racks 5-8 among a few other differences, mostly because they were my only 4 Rack pieces before Bloomburrow hit.

There was a fan translation, so fans were able to “complete the series in English” for quite some years already.

While I was quite happy to see it fimally get an official English release, I kinda hate this article not even mentioning the fan translation in passing.

Tell me you’re not tall without telling me you’re not tall.

Daily login bonus…

The person who was caught is the artist of the manga adaptation and not the writer of the original light novel.

(Also both the ln-writer and the manga-artist are female.)

I didn’t say that.

I expect it to be about as awful as Starfield. However, unlike Starfield (which didn’t sell horrendously by any source I can find, just not great) it has incredible brand recognition behind it. I have no doubts it will sell based on that alone as long as it looks like Skyrim 2 at first glance.

Edit: right after posting I figured out how to formulate what else I wanted to say but couldn’t find the correct words for: “Sadly profitability and quality don’t always correlate.”

5.5 years? No way they’ll shut down this quickly. The next Elder Scrolls alone will carry them into 2030. (As much as I would enjoy you being right though…)

In Season of Discovery, yes. Not on classic though. It was “just” the equivalent to Warchief’s Blessing.

They added a few minor changes such as giving Druids access to a new weapon type and an equivalent buff for Alliance which was previously Horde only and a new Guild UI. Those were all things that were part of Season of Discovery.

There shouldn’t be an endless grind, and from what I’ve seen in other interviews, Larian understands that too. They have a couple things they still want(ed) to work on and then move on to their next project(s).

They definitely shipped a complete product last August. So complete that a lot of the industry, or at least a loud minority, was getting upset at the raised standards (lol). I don’t see how any consumer could complain.

Have you tried reading it? It’s written so poorly that I really hope no human was involved in this and it’s just AI generated garbage.

My bad, I wasn’t precise enough with what I wanted to say. Of course you can confirm (with astronomically high likelihood) that a screenshot of AI Overview is genuine if you get the same result with the same prompt.

What you can’t really do is prove the negative. If someone gets an output then replicating their prompt won’t necessarily give you the same output, for a multitude of reasons. e.g. it might take all other things Google knows about you into account, Google might have tweaked something in the last few minutes, the stochasticity of the model is leading to a different output, etc.

Also funny you bring up image generation, where this actually works too in some cases. For example they used the same prompt with multiple different seeds and if there’s a cluster of very similar output images, you can surmise that an image looking very close to that was in the training set.