A Serbian Film
80085
joined 2 years ago
? Russia is capitalist, engaging in imperialism, and committing genocide.
GPT-4 is quite a bit better, but the subscription is expensive. I subscribe because I think it saves me quite a bit of time. I use it almost every day for things like refactoring (shorter) blocks of code, "translating" code into different languages or frameworks, or just for generating examples for completing tasks using frameworks or libraries I'm unfamiliar with.
What method did you use to generate only JSON? I'm using it (gpt3.5-turbo) in a prototype application, and even with giving it an example (one-shot prompting) and telling it to only output JSON, it sometimes gives me invalid results. I've read that the new function-calling feature is still not guaranteed to produce valid json. Microsoft's "guidance" (https://github.com/microsoft/guidance) looks like what I need, but I haven't got around to trying it yet.
I watched it on shrooms when I was a teenager. From what I remember, it was pretty good as an art piece (atmospheric, cool visuals and audio).
Book is better for the plot/storytelling. IIRC the film was supposed to be a companion piece for the book.
I'm not too well-versed in world-history, but when you look up definitions of "left-wing," and the policies Stalin implemented, there doesn't seem to be much overlap. Seems like a lot of authoritarian leftists just used the idea of a vanguard party to seize power and implement policies closer to fascism and state-capitalism than those of communism. Similar to the National "Socialist" Party.
Threads doesn't need to do an EEE attack. They've already gained many more users than the entire Fediverse. At this point, I wouldn't be surprised if they decided to not join the Fediverse at all.
I would never use Threads, but I would use a Mastodon instance that federated with Threads. I already see many journalists and content creators I like trying it out, who either stopped using Mastadon long ago or never even tried it in the first place. If Threads started doing things that negatively affected my experience, I would then switch to a Mastodon instance that wasn't federated with Threads.
Nobody really knows because it's an OpenAI trade secret (they're not very "open"). Normally, it's a hard limit for LLMs, but many believe OpenAI are using some tricks to increase the effective context limit. I.e. some people believe instead of feeding back the whole conversation, they have GPT create create a shorter summaries of parts of the conversation, then feed the summaries back in.
I'm not a crypto supporter. I do find the tech a bit interesting. I guess, tech-wise, Lemmy would be more comparable federated crypto like Stellar or Ripple (dunno if these are still federated, or if more popular federated crypto exists; been a very long time since I kept up with it). Without some sort of "trust" decentralized systems are too expensive (resource-wise) to be worth it, IMO.
Off-topic, but I'm kinda surprised p2p networks haven't really advanced since Gnutella. I believe they had the concepts of trust/reputation and self-organizing networks with "super-peers" way back then.
Yeah, I used that for a long while. Probably one of the most secure ways of doing things. Can't remember why I switched to BitWarden; I think I had file conflicts a few times, and it was annoying to figure out which passwords caused the conflicts.
Yeah, that's how these models work. They have also have a context limit, and if the conversation goes too long they start "forgetting" things and making more mistakes (because not all of the conversation can be fed back in).
"America bad."