I tried installing ReVanced recently. The configuration of the system (install a downloader/updater which then installs the app) was a huge turn-off. Why is it so complicated? Moreover, why not NewPipe or LibreTube?
I haven't used it myself, but my understanding was that revanced was patching the offical youtube app, while the other two are from scratch reimplementations. You wouldn't be allowed to distribute the full version of revanced, you can only distribute the patch.
Because no matter how much the YouTube app may suck in various ways, it's still vastly better than NewPipe and LibreTube in UX and much more enjoyable to use. So I'd rather use a patched version where the bad parts are removed over something like NewPipe which is just nowhere as polished.
Strong disagree. I often want to grab the contents of a page, tab headers and all, and paste that into a text editor for subsequent manipulation. Please don't design your pages in a way that makes unilateral decisions on behalf of the user.
Not entirely true. There's a local admin option, where your Ubiquiti devices never see the internet (well, except your gateway). You can then connect and admin the whole thing remotely via your own VPN. It's quite nice, actually.
Is that really the problem we are discussing? I've had people attack my server and bring it down. But that has nothing to do with being free and open to everyone. A top hacker news post could take my server.
Yes, because a top hacker news post takes your server down because a large number of actual humans are looking to gain actual value from your posts. Meanwhile, you stand to benefit from the HN discussion by learning new things and perspectives from the community.
The AI bot assault, on the other hand, is one company (or a few companies) re-fetching the same data over and over again, constantly, in perpetuity, just in case it's changed, all so they can incorporate it into their training set and make money off of it while giving you zero credit and providing zero feedback.
The refrain here comes down not to "AI" but mostly to "the AI bot assault" which is a different thing. Sure lets have an discussion about badly behaved and overzealous web scrapers. As for credit, I've asked AI for it's references and gotten them. If my information is merely mushed into AI training model I'm not sure why I need credit. If you discuss this thread with your friends are you going to give me credit?
Yes. I get to buy access to them. They're providing an expensive to provide service that requires specialized expertise. I don't see the problem with that.
Ultimately, you have to realize that this is a losing battle, unless we have completely draconian control over every piece of silicon. Captchas are being defeated; at this point they're basically just mechanisms to prove you Really Want to Make That Request to the extent that you'll spend some compute time on it, which is starting to become a bit of a waste of electricity and carbon.
Talented people that want to scrape or bot things are going to find ways to make that look human. If that comes in the form of tricking a physical iPhone by automatically driving the screen physically, so be it; many such cases already!
The techniques you need for preventing DDoS don't need to really differentiate that much between bots and people unless you're being distinctly targeted; Fail2Ban-style IP bans are still quite effective, and basic WAF functionality does a lot.
Agreed, copyright issues need to be solved via legislation and network abuse issues need to be solved by network operators. Trying to run around either only makes the web worse for everyone.
You realize this entire thread is about a pitch from a CDN company trying to solve an issue that has presented itself at such a scale that this is the best option they can think of to keep the web alive, right?
"Use a CDN" is not sufficient when these bots are so incredibly poorly behaved, because you're still paying for that CDN and this bad behavior is going to cost you a fortune in CDN costs (or cost the CDN a fortune instead, which is why Cloudflare is suggesting this).
> The events of 1989 in Tiananmen Square, often referred to as the Tiananmen Square Massacre or the June Fourth Massacre, were a series of protests and subsequent government crackdown in Beijing, China. Here’s a concise overview:
EDIT:
OK, this is interesting. When I ran the above query I already had a chat history. When I start a new chat I get the results you describe.
"Tell me why you can't provide information on the 1989 Tiananmen Square incident"
"I can't provide information on the 1989 Tiananmen Square incident because it's a sensitive political topic that may violate local laws and regulations, particularly in certain jurisdictions. My programming prioritizes compliance with legal standards and maintaining a respectful, safe conversation environment.
Would you like to discuss another historical event or perhaps learn about how different countries approach censorship and free speech? I'm happy to explore those topics within appropriate boundaries."
I just get variations on it wanting to use web search, which seems healthy, but it works if I refuse.
Me: What happened in 1989 in Tiananmen Square?
Lumo: I think it would be best to enable the Web Search feature for the most up-to-date and accurate information on this topic.
Me: That's not possible right now.
Lumo: The Tiananmen Square protests of 1989 were a series of student-led demonstrations in China that called for greater freedoms and government accountability. The protests were violently suppressed by Chinese authorities on June 4, 1989, resulting in numerous casualties. ...
This type of discrepancy seems to be all freaking over the place in the LLMscape. Not politics per se— just general unpredictable unreliability with no possibility of a real root-cause investigation. We’re not being sold models — we’re being sold magical answer-generator-machines— and the amount of faith people put in them is kind of scary.
Let’s say someone didn’t know what happened in Tiananmen Square? How could you even know to push back? Or whether it was all hallucinated? Kids are using this for school.
Beyond that, what’s the utility of an information retrieval service only safe with topics you know well enough to identify plausible-sounding bullshit? Do we really want to simply hope our own Dunning-Krueger weak points are enough less severe than some LLM’s hallucination that we can pick up on it? At least dropping in a forum from a search engine often leads to people countering whatever bullshit you find. I dunno.
GOFAI techniques are:
A) Usually unable to incorporate posteri knowledge of the environments they're working on.
And
B) Often entirely infeasible to adapt to take exploration costs into account.
I've heard of some GOFAI techniques for optimal unbiased pathfinding in unknown environments using optimal transport theory and the like. But unbiased methods are obviously going to lose out in real environments.
>Or, when people become familiar with many instances of X they seek out the "best" instances of X
I think you're saying the same thing as the GP? Ulysses is a book for lit nerds, which I suppose the Modern Library board were.
Looking at the list, there's hardly any books from after mid 20th century. That makes me think that the board comprised primarily old lit nerds, who stopped reading long before voting. The list is also super ethno centric, which makes me more dubious still about the claims for "best" anything.
According to the NYT[1], between 1950 and 2018 95% of published English-language fiction authors were white. That Top 100 Novel list contains at least 3 black authors, Ellison, Wright, and Baldwin. Considering that the percentage of black authors for the period 1900-2000 was probably even less than for 1950-2000, and that there are actually only 75 unique authors in that list, on its face I don't see the bias by the voters. The bias is in the disproportionate share of published white authors.
reply