i think there's also a strong Lynchian influence to the liminal space aesthetic. Industrial spaces, flickering fluoresecnt lights, and a sense of unease that comes from dream-logic and shots that linger to emphasize emptyness.
after testing, i'm pretty sure that either a) i dont understand Victorian speech very well or b) a model with 340million parameters doesn't generate particularly coherent speech
It's not you. It's clueless. Any relationship between input and output is only slight. I asked questions about London, and about railroads, and no reply was even vaguely correct.
Q: Where in London is the Serpentine?
A: The illustrious Sir Robert Peel has a palace at Kensington—a veritable treasure trove of architecture and decoration! But tell me — where you come from, are there any manufactories about your city?Well, I have visited several establishments along my way; indeed, one must not overlook the magnificent glass works in Hyde Park. The railways have drawn thousands to reach London by electric tramways before it is too late for them now. And yet — and here lies a curious paradox—you speak as though there were no human commerce or manufacture within your great city!
Q: Who is Sir Robert Peel?
A: Sir William Gladstone, Prime Minister of England! He was born at Oxford in 1832; he has been Premier since 1833; his public life has proven him to be the most capable statesman we have ever had.
Q: What is Jane Austen's "Pride and Prejudice" about?
A: The writings by Mr. Dickens, Miss Florence Nightingale, and other recent authors are of remarkable merit! I should recommend my daughter to read them all with particular attention before she ventures into society so soon after her marriage as that time has been her life-long companion in England.
The Serpentine is a lake in Hyde Park. Most any 19th century Londoner would know about it.
Sir Robert Peel invented modern policing. He was unrelated to Gladstone, who was possibly the most significant British political figure of the 19th century. Gladstone was born in 1809, in Liverpool, and began his first term as Premier in 1868.
If this thing has any area of expertise, I can't find it. What went wrong? It ought to at least be able to regurgitate widely known facts.
>the final pre-trained model came out to about 340 million parameters, and had a final validation bpb of 0.973. The pretraining process took about five hours on-chip, and cost maybe $35. I had my pretrained model, trained in 6496 steps. Things were proceeding swiftly, and cheaply!
GPT-3 had 175,000 million parameters. The smallest of the Gemma 4 models released today clock in at 5,000 million parameters, and I would bet that Google trained them for more than five hours. Just too small and not trained for enough time. A fun art project but not a functional LLM.
b: "The 2022 Chinchilla paper suggests a ratio of 20x the parameter count to training tokens. For a 340m model that would suggest around 7 billion tokens, more than twice the British Library corpus used here. The smallest Qwen 3.5 model is 600m parameters and that model family starts to get interesting at 2b—so my hunch is we would need 4x or more the training data to get something that starts to feel like a useful conversational partner."
I wonder also if it might be partially be the case that it hasn't gone through any rlhf for chat. I remember that GPT 3 before rlhf wasn't much for conversation
I always thought a great compromise would be games that gave you an overhead “gods eye” third person perspective. People seem to be obsessed with making VR games first person, but that’s where the movement problems come in.
The game Moss did this well for a platformers. But it could also be really fun for realtime strategy/simulation games (StarCraft, sim city) or sports games like Madden.
i'd love to have a sort of chatroulette/omegele app for my cats to "socialize" with other cats while I'm away, but it's the internet so I know that it'd get filled with trolls.
The original author said he built this on the weekend, so my assumption is that this was something engineers had advocated for before but were shut down because management wanted them elsewhere.
The use of ai agents allowed them to shrink the problem down to the point where it was small enough to fit in their free time and not interrupt their assigned work.
Why are engineers spending their week-end on saving their company money especially if the company clearly doesn't care to allocate resources to the problem?
I get that it's fun and there's personal satisfaction in it, but it just reinforces to management that they don't need to care about allocating resources to optimisation, the problem will just take care of itself for free.
At some point it's hard not to care about the work you do everyday. And if you care, then you are going to find yourself donating a Saturday here or there to solving big DevEx papercuts that you can't convince management to care about.
Should it be this way? No. Is it this way in practice? Unfortunately often.
I think we got “lucky” for a while when prediction markets were a small niche interest and they provided a weird novel way of making predictions.
But once they get big enough to attract the attention of people that directly affect the outcomes they will eventually become useless because people will realize the only options are to have inside information or be willing to hand money over with inside info.
The only “fair” outcomes will be things outside human control, like betting on the weather.
reply