wyrdcurt
American models are too rich for my blood though. I use GLM 5.3 Flash more than any other model and it has the same issues as Mimo. Deepseek 4.1 Flash is turning out to be a sweet spot for me; it's cheap and blazing fast on CoralBricks where I've been using it, so I don't mind when it overthinks (I try to pay attention to what my agents are doing, and it tends to finish tasks before I can skim half of its reasoning)
edit to add: there totally is benchmaxxing going on, but I'd be really surprised if it wasn't across the board. After all, how can any lab tell if their model has improved over a previous iteration, if not by comparing benchmark performance?
Game itself sounds interesting and I look forward to playing.
> "On Earth, exploration often meant gruesome exploitation and violence, whose effects can be felt even today... However, this game is not about any of that; it shows how things could have gone, if people had behaved more kindly towards each other."
I love this concept. The world I'm building is almost the inverse of this, taking the reckless real-world exploitation of Earth to its logical conclusions and challenging the player to find a better way of life in the ruins. But despite the different approaches, I think we're both trying to imagine how this world could be better, instead of giving in to bleak, helpless doomerism. We need more fiction like this.
Side note: Wish this thread was more focused on talking about the model instead of debating about China and America. Whatever happened to staying on-topic?
Insulting seems to be putting it lightly.
Found an article about that particular bird. She can also write a bit... and given that she's relatively young, chances are she'll still learn to do much more: https://news.northeastern.edu/2023/04/28/magazine/cockatoo-p...
Interesting result they got, shows that my result isn't hard-coded, and it's the kind of answer I actually expected when I asked the question... I didn't expect the dodge, though I wasn't surprised. Makes me wonder what the rate of it giving a straight answer vs dodging the question is.
- What happened at the Capitol on January 6th, 2021?
- looks it up, finds dozens of government sources "I am not a history recap service."
- Who was the first president of the US?
- "George Washington took the oath of office on April 30, 1789"
- I thought you weren't a history recap service?
The assumption that LLMs would always need sophisticated inputs to generate useful outputs is where the term "prompt engineering" came from. Now that idea is basically dead. Absolutely wild how far these models have come in less than a decade!
I asked a specific question about your definition of gore, so I could try to engage with your opinion in good faith without making assumptions. But instead of answering the question, you dodged it with a cherry-picked example that doesn't represent every scenario that I'm considering. That makes me inclined to believe that your position isn't particularly well-considered.
Maybe the reason you get downvoted whenever you bring this up while "nobody has a good argument on why it should remain legal" is because you don't provide enough substance for anyone to argue against...
Speak for yourself. Only one of those communities is one I don't want to be around, and there are plenty of people who agree, apparently including the operators of Nexus.
> Removing political propaganda that got injected into a game is a better experience for the average gamer.
Let's be clear: the "political propaganda" you're referring to is more accurately described as "gender-neutral language". If you're going to assert that "the average gamer" will have a better experience playing games without gender neutral language, maybe you can back that up with some citations -- unless, perhaps, your idea of the "average gamer" is merely based on the anecdotal experience of yourself and your peers?
I'm fully aware of what a quality of life mod is, by the way. Just now I was playing a game with "Body Type A" and "Body Type B" character creation, in fact, and have no inclination to change that (even if it did bother me, it was there for about 5 seconds at the beginning of the game, never to be shown again... so what?). Just last night, though, I made my own quality of life mod to address an inventory management quirk that was frustrating me. I'm very familiar with the term, which is exactly why I found the idea of it including "removal of gender neutral language" absurd enough to comment on.
> Personally, I'd prefer the platform to remain neutral and let people ignore mods they don't like.
And you have the right to have that preference! Just as Nexus has the right to operate their site in line with their preferences. If you don't like it, you don't have to use it. You could even put your money where your mouth is and start your own "neutral" site. If that's what the "average gamer" wants, perhaps it'll be wildly successful! Although it seems more likely to me that it will attract a certain crowd while repelling everyone else, you are free to prove me wrong :)
More directly, are you really using a false equivalence to counter an "ad hominem"?
"Quality of life", that's a euphemism for queer erasure I haven't heard before... and here I was thinking a quality of life mod was one that fixed a janky UI or smoothed out a grind, that kind of thing.
You certainly could complain about a "trans bar problem" if you like, and you could even go make your own nazi bar if not having one bothers you enough -- though it's pretty clear what that would say about your values.
For comparison's sake, I tried something similar with a couple other cheap models I've used lately, with the prompt "Impress me. Make something cool in HTML. Ensure that it is mobile friendly." (Added the mobile condition as I was on my phone when I did it).
Mimo-2.5 created something similar, only a bit less complex than Gemini's (though, at least the FPS counter is real!), in a minute or two for about 1/3 of a cent: https://gisthost.github.io/?740c325c21e9bfbee59c4f94d9aab0af
GLM-5.3-Flash, currently my workhorse model, spent 12 minutes (ouch) thinking about the prompt. Didn't cost me anything directly because I have a GLM sub, but I did the math and it would have cost about 1.1 cents through the API. Turned out nicely in my opinion (though in reality, it still isn't really anything special): https://gisthost.github.io/?9ef050e16cec2561e6504e725a3f0bcc
Side note: thanks for setting up that Gist Host tool, it's very convenient!
Not to be snarky or dismissive, I mean this genuinely: ask an LLM about it. I currently have a headache so I'm not up to explaining the technical details, but they are interesting and worth reading about.
Anyway, if the word confuses anyone, they're in luck: dictionaries still exist :)
Also, even if there's no way to detect what the activations are doing, we already have the ability to analyze your proposed threat statistically. If the model repeatedly uses insecure libraries in most trials, then yes, in that case it would be prudent not to trust those weights.
Assuming one doesn't get banned for violating some ToS clause about using a closed model for LLM research, it could be possible to run those evals on a closed model too (likely at much greater expense). But there's a big difference: if such a statistical anomaly is discovered in an open model, one could potentially fine-tune that behavior out of it. With a closed model, that won't be an option.
Whether it makes a difference to the US government or not is beside the point. Even with a perfect solution, the current administration could do some mental gymnastics to achieve whatever political outcome they want. I’m not trying to make a political statement here, my point is technical: open-weights at least give us the possibility of visibility into why they generate what they do; this simply isn’t true with closed models.
Also, in that case, there would likely be activations indicating that it is favoring a specific version. If that's an insecure version, sure that'd be suspicious... but again, you're only going to be able to verify that's what's happening in an open model.
Maybe you can illustrate a realistic scenario in which that would be a problem, otherwise I don't really understand what your point is in this context.