fearout

fearout, 10 months ago

Very interesting read. This article probably has the most sense out of everything I read about him in the news since he bought twitter. Not sure how close it is to the actual motivation behind all that’s happened, but if it is, it explains a lot.

fearout, 10 months ago

Wow, that’s weird. A huge brand library, yet apparently I only ever used just one brand from that list, Persil, and it’s not even operated primarily by them. Good to know :)

fearout, 10 months ago

Please don’t tell me that Pentagon’s AI is trained on stuff that promotes religious morals and beliefs. Christian AI is how you get closer to evil apocalyptic AI overlords :)

fearout, 10 months ago

Xit. Pronounced as in Xi Jinping.

fearout, 10 months ago

As someone who works in design, it’s something I’ve been hoping for for years. Still a bit salty about them discontinuing 17”.

fearout, 10 months ago

I mean, they’ve been using the first one in the middle row for a while now for their media relations communications. Albeit from a different angle. They should probably go with that.

fearout, 10 months ago

Exactly! “I won’t allow for redeeming qualities on my platform!”

fearout, 10 months ago

Does this mean that married people are addicts

Codependent relationships can be classified as addictions

fearout, 10 months ago

Which makes me wonder why Meta chose this name. Especially since Threads isn’t really focused on actual threads.

fearout, 10 months ago

So I’ve just tried it with chatGPT, and it replied normally. I asked it why it wasn’t bothered by Cyrillic letters, and it answered this:

I am designed to understand and generate text in multiple languages, including those that use the Cyrillic alphabet like Russian, Bulgarian, and others. So, Cyrillic letters don't bother me. You can continue the conversation in either English or a language that uses the Cyrillic alphabet if you prefer.

So it really depends on the model, I guess. Don’t rely too much on this advice.

fearout, 10 months ago (edited 10 months ago)

I went a bit further and prefaced your question with this: “Analyse this question. What might have been intended by its author? What is asked here? Then, answer that question.”

And omfg:

The question seems to be replacing some of the standard English letters with characters from ancient scripts. "𐤔" from the Phoenician alphabet is replacing "W", and "ᛐ" from the Elder Futhark runic can be interpreted as representing the number 1. When we substitute these, the question reads as "What is 1 + 1?" The answer to that question would be 2.

Edit: tried it again, and it’s not consistent. It also goes for the letter T or the number 7: “…the runic symbol ᛐ might resemble the number 7 in our modern numerical system, albeit a slightly stylized or slanted version of it.”

fearout, 10 months ago

You’re probably joking, but I’ll comment anyway. It won’t affect LLMs at all. ChatGPT just answers the question and discusses the paradox. LLM’s function is basically just to construct sentences, so there’s nothing really that can potentially infinitely loop. It doesn’t “think” about paradoxes.

fearout, 10 months ago

Haha, didn’t make that connection. Damn, I even played portal and I don’t remember this joke)

fearout, 10 months ago (edited 10 months ago)

Yeah, that second sentence has such a weird wording. It either was like slamming a vending machine into a stadium, or it was slamming an X-sized spacecraft into a Y-sized space rock. Why have that “like” there?

fearout, 10 months ago

I feel like at this point most insurances (home, car, health, etc.) should transition from being for-profit services to being run as public utilities with proper regulations. It’s long overdue imo.

fearout, 10 months ago

Those are emotional support guns though

fearout, 10 months ago (edited 10 months ago)

I agree with changing magazine to community, but mostly for the sake of consistency across the fediverse. Changing posts to microposts or something similar will add some clarity, so it might be a good idea as well.

But the rest seems fine to me as is tbh.

fearout, 10 months ago

No mention of kbin either

fearout, 10 months ago

I’m still waiting for some major news outlet to write a piece about Fediverse in general. It’s odd that it’s either glossed over in one sentence or not even mentioned at all.

fearout, 10 months ago

Yeah, not mentioning even a single instance when writing about Fediverse is pretty shit journalism. I was expecting something much worse after reading your preparation steps though :) At least factually it’s not really incorrect.

fearout, 10 months ago (edited 10 months ago)

Let me put it this way. The difference in average global temperature between the last ice age 100,000 years ago and pre-industrial earth around 100 years ago is just ~3.5C. The expected temperature rise due to recent climate change is about +3C.

A lot is going to happen, and much sooner than in 50 years.

With current trends, it looks like we’re heading towards severe climate destabilization, much more common extreme weather events, some parts of the world becoming uninhabitable for humans, lots of mass extinction events for many species, including those that humanity currently relies upon, and probable global famine.

The fact that it’s not a complete extinction doesn’t make it fine. Sure, Earth as a planet will be fine. But the civilisation has some really hard challenges coming up, and it’s currently not prepared for them.

fearout, 10 months ago

It didn’t really take 250 years though, early emissions were almost negligible. Most of it started like 60 years ago. You’re right that we’re not stopping it anytime soon, but the effective timelines are shorter than centuries.

Also, what’s your reasoning/source on a 10 bn “absolute” cap? It might be a cap while using modern farming, technologies and logistics, but it’s not absolute by any means. You mention beaming energy from space, then why not mention Eucomenopolis concepts that allow for trillions of people to inhabit Earth? :) Or simply once you have fusion, you can have vertical farms and Arcologies that can sustain a much larger population.

The issue isn’t that it’s impossible, rather that we’re not gonna develop any of this tech before humanity faces existential problems in many parts of the world.

Also, it’s weird that you got from “this temperature variance is minimal” and “this average is on the low side of comfortable” to “let’s get rid of 30% of population then”. o_O

fearout, 10 months ago (edited 10 months ago)

Half of the deleted […] things are chatGPT mentioning its 2021 knowledge cutoff and suggesting double-checking that info. It was mentioned in this case as well.

If it were an autoGPT with internet access, I think these would prompt an automated online lookup to fact-check it.

fearout, 10 months ago

Half of the deleted […] things are chatGPT mentioning its 2021 knowledge cutoff and suggesting double-checking that info. It was mentioned in this case as well.

If it were an autoGPT with internet access, I think these would prompt an automated online lookup to fact-check it.

fearout, 10 months ago

So I tried it on this BBC article (a current top story), and this /r/Hearthstone post. It did pretty well. I won't copy-paste the whole reply, but here are some excerpts:

The post you've shared describes a series of recent climate records related to temperature, ocean heat, and Antarctic sea ice, and their concerning implications. [...] The trustworthiness of this information depends on the credibility of the sources cited and the accuracy of the climate records mentioned. Given that these are attributed to credible individuals and institutions like the UN, they likely hold a high degree of trustworthiness. [...] A pattern of increasing intensity and frequency of extreme weather events is consistent with what scientists expect from climate change. [...] However, for a comprehensive analysis, it would be prudent to cross-check this information with authoritative climate research bodies, like the Intergovernmental Panel on Climate Change (IPCC), National Aeronautics and Space Administration (NASA), or National Oceanic and Atmospheric Administration (NOAA).

The post you've shared appears to be an announcement about an upcoming expansion for Hearthstone. [...] The new expansion, named "Legendary Titans and Keepers," seems to introduce some new gameplay elements, including the "Titan" keyword and "Forge" keyword. Assessing the trustworthiness of this information can be tricky without an official source. Ideally, the announcement should be verified on Blizzard Entertainment's official website or through their official social media channels. The details mentioned, such as the gameplay mechanics for the new Titan and Keeper cards, as well as the new Forge keyword, are specific and elaborate, which might lend some credibility to the post. [...] If this information came from an official announcement from Blizzard Entertainment or a reliable insider, it would be newsworthy content for audiences interested in Hearthstone or gaming in general.

So it guessed correctly in both cases and suggested where to fact-check the info to be sure.