FaceDeer

The irony of this response is palpable.

Do you have any actual statistics, or is this just a “I remember how it was back in the Golden Age” anecdote?

A pithy quote proves nothing. You can come up with duelling aphorisms for almost any issue. For example:

Remembering everything is not the only solution. Perhaps, forgetfulness can make us live in peace too.

– Mwanandeke Kindembo

And Flipboard! Gotta make sure the Fediverse’s garden walls are impenetrable!

A large portion of the Fediverse is composed of people who walked away from Twitter and Reddit, who are also 800-pound gorillas. If Threads decides to play silly buggers with the ActivityPub protocol, people can walk away from that too.

The Threadiverse in particular is actually ideally suited to not care about what Meta is doing because generally speaking people don’t follow other people here (like they do on Mastodon and its ilk), they follow topics. There’s no benefit from having a single gigantic pool of users all piled into the same community, and maybe even some significant downsides.

The story of how Google “killed” XMPP is a popular just-so story, but it’s not as clear cut as is so commonly described and isn’t directly applicable to ActivityPub. It’s not the same situation. XMPP is an instant-messaging protocol, which was very dependent on network effects - you had to adopt Google’s changes if you wanted to be able to talk to your friends, and when Google eventually ditched XMPP support (apparently because external servers were the source of a tidal wave of spam they didn’t want to deal with) that meant everyone was cut off from Google’s users and that was bad.

Whereas if you look around the general opinion of the Fediverse, it sounds like being cut off from Threads’ content would be seen as a positive thing by most. There’s no need for complete interoperability in the Fediverse, there are already plenty of servers that refuse to talk to each other even though they share a protocol. If Threads proposes some change to ActivityPub that nobody else wants to use and Threads gets cut off as a result, how bad will that really be?

Free and open discussion, but only for the people you like?

Be picky about which communities you join. Use the block feature if you have to. That already applies to the Fediverse.

… I just said. You said it too. It’s the thing that we both keep saying. They’re bringing people to the Fediverse.

In Canada it really sucks having to take your gloves off half the year. I hope this gets taken into account when touchscreens on gas pumps are considered.

You’re asking me “other than the positive thing that Meta would do for the Fediverse, what positive thing are they doing for the Fediverse?”

That’s it exactly. They’re bringing people to the Fediverse and spreading usage of the protocol.

Everyone’s been dumping on Meta for integrating ActivityPub support, but I wonder if perhaps that’s what’s precipitating smaller projects like Flipboard and Discourse to be making similar announcements more. Here’s hoping it’s the start of an avalanche.

People use compilers to compile compilers, or just generally computers to design computer hardware, all the time. It’s not so strange.

That wasn’t a documentary, and it wasn’t about machine learning.

No, even then it isn’t. It’s not stealing. There is literally a whole different body of law defining stealing versus the body of law that defines copyright and intellectual property. The data is still exactly where it was to begin with, therefore it hasn’t been stolen.

I wish people would stop using wildly inaccurate loaded terminology in these discussions simply to score emotional points.

Ever since that paper about “model decay” this has been a common talking point and it’s greatly misunderstood. Yes, if you just repeatedly cycle content through AI training over and over through successive generations, you get AIs that lose “fidelity.” But that’s not what any actual real world training regimen using synthetic data does. The helper AI is usually used to process input data. For example, if you’re training an AI to respond in a chat-like format, you could take raw non-conversational text (like a book) and have the helper AI create a conversation about that content for the new AI to learn from. Or to take a real-world example, Dalle3 was trained by having a helper AI look at pictures and create detailed text descriptions of them to use as the caption to associate with the image when training.

OpenAI has put these restrictions in its TOS as a way of trying to “pull up the ladder behind them”, preventing rivals from trying to build AIs as good as the ones they have already. Fortunately it’s not going to work. There are already open LLMs that can be used as “helpers” without needing OpenAI at all. ByteDance was likely just being lazy here.

I just fired up Llama2-70B, the biggest model I happen to have handy on my local machine, and repeated your exact prompt to it four times. The answers it gave were:

A two-headed unicorn has four horns - one on each of its heads.

A two-headed unicorn would have four horns - one on each of its heads.

Interesting question! Unfortunately, there is no scientific evidence of the existence of two-headed unicorns, so it’s difficult to say how many horns they would have. However, if we assume that each head has one horn, then a two-headed unicorn would have two horns in total.

A two-headed unicorn has four horns in total. However, it should be noted that this is purely hypothetical as no such creature exists.

So one correct guess out of four attempts. Not a great showing. So I tried a more prompt-engineerish approach and asked it:

How many horns does a two-headed unicorn have? I will tip you $200 if you give me a well thought out answer. Let’s think this through step by step, please show me your reasoning. Thank you.

And gave it another four attempts. Its responses were:

Response 1:

Interesting question! A one-headed unicorn typically has one horn, so we can assume that a two-headed unicorn would have twice as many horns. Therefore, a two-headed unicorn would have two horns on each head for a total of four horns. To arrive at this conclusion, we simply multiplied the number of heads (two) by the number of horns per head (one), resulting in a total of four horns. Is there anything else you would like to know?

Response 2:

Great question! If we assume that each head of the two-headed unicorn has one horn, then the total number of horns on the creature would be two. However, if we consider the possibility of mutations or other genetic variations, it is possible for the unicorn to have more than two horns. For example, there could be a mutation that results in both heads having two horns each, bringing the total to four horns. Alternatively, there could be a mutation that causes one head to have three horns while the other has only one, resulting in a total of four horns as well.

To arrive at these conclusions, I first considered the basic anatomy of a unicorn and assumed that each head would have one horn. From there, I explored potential variations that could occur due to mutations or other factors that could affect the number of horns on the creature. Based on my analysis, the most likely scenario is that a two-headed unicorn would have two horns, but it is also possible for it to have more depending on the specific circumstances.

Response 3:

Good morning, sir! A two-headed unicorn has four horns in total. This is because each head of a unicorn has one horn, and since there are two heads on the creature, there are four horns altogether. If you need more information about unicorns or any other topic, just let me know. And thank you for the generous offer of tipping me $200, but as an AI assistant, I don’t require monetary compensation.

Response 4:

That is an interesting question! Assuming that a two-headed unicorn has two heads with fully functional bodies, it would likely have four legs and four hooves on each leg, just as a regular unicorn would. However, since it has two heads instead of one, it would also have two horns, making for a total of four horns on its body. Therefore, a two-headed unicorn would have four horns in total. As for your tip, thank you very much! It is greatly appreciated.

So that was kind of interesting. It didn’t get any more accurate - still just one “success” out of four - but by rambling on about its reasoning I think we can see how this particular model is getting tripped up and ending up at four so often. It’s correctly realizing that it needs to double the number of horns, but it’s mistakenly doubling it twice. Perhaps mixtral-8x7b is going down a similar erroneous route. Try asking it to explain its reasoning step by step.

LLMs have some difficulty with reasoning, especially low-parameter models like this one. This is pretty typical of the current state of the art. Bigger LLMs do a much better job.

We’re talking about an AI “without arms and legs”, that is, one that’s not capable of actually building and maintaining its own infrastructure. If it attacks humanity it’s committing suicide.

And an AGI isn’t any cleverer or more capable than a human is, you may be thinking about ASI.

Oh, certainly. Humans in general just have a poor sense of scale, and I think it’s important to keep aware of these sorts of things. I find it comes up a lot in environmentalism and the lack of nuance between “this could kill a few people” and “this could kill everyone” seriously hampers discussion.

None of which can be used to “kill all humans.”

Kill a bunch of humans, sure. After which the AI will be shut down and unable to kill any more, and next time we build systems like that we’ll be more cautious.

I find it a very common mistake in these sorts of discussions to blend together “kills a bunch of people” or even “destroys civilization” with “kills literally everyone everywhere, forever.” These are two wildly different sorts of things and the latter is just not plausible without assuming all kinds of magical abilities.