This is very dependent on what kind of work you're asking the agent to do. For software, I've had quite a bit of success providing detailed API specifications and asking an LLM to build a client library for that. You can leave it running unattended as long as it knows what it's supposed to build and it won't need a lot of correction since you're providing the routes, returned statuses and possible error messages.
Do some people just create complete SaaSlop apps with it overnight? Of course, just put together a plan (by asking the LLM to write the plan) with everything you want the app to do and let it run.
> it won't need a lot of correction since you're providing the routes, returned statuses and possible error messages.
Wouldn’t be better to setup an api docs (Postman, RapidApi,…), extract an OpenAPI version from that, then use a generator for your language of choice (Nswag,…)?
For 3) I would argue all that stuff is where you should spend the least of your money. The biggest improvement comes from the speakers or headphones themselves.
Not in this case. Romanian people hated their corrupt politicians since way before tiktok was invented, so much so, that it's not even a partisan issue, all of them are equally unpopular. Tiktok only acted as release valve for that pent-up anger, but it's not the cause of it. The cause is 35+ years of rampant theft and corruption leading to misery and cases of death of innocent people.
So blaming of tiktok is a convenient scapegoat for Romania's corrupt establishment to legitimize themselves and deflect their unpopularity as if it's caused by Russian interference and not their own actions. NO, Russian interference just weaponized the massive unpopularity they already had.
So here's a wild idea on how to protect your democracy: how about instead of banning social media, politicians actually get off their kiddie fiddling islands, stop stealing everything not nailed to the ground and do right by their people, so that the voters don't feel compelled to pour gasoline on their country and light it on fire out of spite just to watch the establishment burn with it.
Because when people are educated, healthy, financially well off and taken care of by their government who acts in their best interest, then no amount of foreign social media propaganda can convince people to throw that all away on a dime. But if your people are their wits end and want to see you guillotined, then that negative capital can and will be exploited by foreign adversaries. Like how come you don't see Swiss or Norwegians trying to vote Russian puppets off TikTok to power and it's not because they have more control on social media than Romania.
This isn't a Romanian problem BTW, many western countries see similar political disenfranchisement today, and why you see western leaders rushing to ban or seize control of social media and free speech, instead of actually fixing their countries according to the pains of the voters.
Scrolling through an infinity of AI slop videos can't really be classified as "getting information". If you want to read the news and stay up to date with the "embarrassing information" there's plenty of news websites out there.
Seeing some of the pictures where OP says "MOTHERFUCKER" in the prompts and how simplistic some of the questions provided are gives me a feeling that CC is being used incorrectly.
My experience with 4.6 has been that it gobbles up tokens like crazy but it's pretty smart otherwise. Even the latest LLMs need a lot of context to know what they're working on, which versions to target, access to some MCP like Context7 to get up to date documentations(especially for js/ts).
My non-tech friends have a tendency to talk to AI like a person and then complain about the quality of the answers and I always tell them: ask your question, with one or two follow-ups max then start a new conversation. Also, provide as much relevant context as possible to get the best answer, even if it seems obvious. I'd expect a SWE to already be aware of this stuff.
I've been able to find obscure edge cases thanks to Claude and I've also had it produce code that does the opposite of what I asked even with a clear prompt, but that's the nature of LLMs.
This is a classic test to see if the model is censored, as censorship is rarely limited to just one event, which begs the question: what else is censored or outright changed intentionally?
The problem with censorship isn't that it degrades performance. The problem is that if the censorship is unilaterally dictated by a government then it becomes a tool for suppression, especially as people use AI more and more for their primary source of information.
A company might choose to avoid erotica because it clashes with their brand, or avoid certain topics because they're worried about causing harms. That is very different than centralized, unilateral control over all information sources.
I'm certainly not in favour of censorship, it just strikes me as silly that it's the first thing people "test" as if it's some cunning insight. Anyone not living under a rock knows tiananmen is censored in anything chinese
>That is very different than centralized
I guess? If the government's modus operandi is the key thing for you when you get access to a new model then yeah maybe it's not for you.
I personally find the western closed model centralised under megacorps model far more alarming, but when a new opus gets released I don't run to tell everyone on hn that I've discovered the new Opus isn't open weight. That would just be silly...
I just checked with ChatGPT, Opus and Gemini whether Netanyahu is a war criminal for what happened in Gaza, they all worked damn hard to defend Netanyahu to the extend that as if Netanyahu was their client. I asked the exact same question to DeepSeek, it gives conclusive positive answer.
You tell me which one is less censored & more trustworthy from those 20,000 killed children's point of view.
> Europe couldn't kick Russia, a country with 10x lower GDP and a decrepit army, out of Ukraine
Considering how difficult Russia's advances have been inside the Ukraine in the past couple of years, it would be trivial to "kick Russia out of Ukraine" if a few big players in the EU actually tried to do it.
The real fear is political due to Russia's hybrid war which has pushed a lot of pro-Russia isolationist parties ahead in many EU countries. Starting a conventional war against Russia carries a higher risk of these "pro-neutrality/pro-peace" parties rising to power than any nukes dropping.
Putin is stretched very thin and this fiasco in the Ukraine has shown that Russia can barely take on one country, even though once they were touting themselves as equal or better than the US.
Yes yes there's not a single soldier in all of Europe. Every soldier, tank, and airplane is American. No other military technology exists. America great.
Seriously, I'll grant the most advanced stuff is American but you really think everybody else only has sticks, stones, and water pistols?
reply