aaaa ko li utala e mi la mi utala e ko

ko li utala e mi!!! mi wile moli e ko ale!

yeah those people would not survive in ma pona pi toki pona. tons of variant orthography there

gen z here, can confirm. most of my peers just do not care about learning how things actually work

if ios, then Arctic for sure. it’s the only one that feels as smooth as apollo did, has some excellent customizability, and is just as feature rich as the more popular clients

interesting. i’d say it’s not really that important, but then again i’d probably have a very different opinion if i didn’t have aphantasia.

no great options but Orion by kagi is much better than base safari since you can at least get extensions like ublock

decomposers turn organic material from corpses into simpler nutrients like nitrogen, phosphorus, and potassium. for example, proteins are broken down into amino acids, which then decompose into ammonium and nitrates. these nutrients are absorbed into soil and consumed by plants

tldr: plants eat corpses after decomposers turn them into nutrients

if it was torturous then nobody would bother learning instruments

the only impulsive part of this acquisition is how willing you seem to be to give up. just try it again. and then if you’re not satisfied by how it’s going, that’s an excellent excuse to do it again. and the cycle repeats until one day, you are satisfied by how it’s going

yes, you’re definitely right. the accuracy is dubious no matter what. in the author’s words, their approach is “semi-scientific” and “guesstimating”. not once do they say their results are definitive. but if it’s the best qualified demographers can do with what we know, then there’s not much else to it

not op but i think your skepticism is justified

this seems to be where the image originally came from. the author explains the challenges with making speculations about historical populations in that post. the demographers, toshiko kaneda and carl haub, estimated 117 billion people have lived over the last 200,000 years. here’s the explanation given on the original post:

The majority of them lived very short lives: about one in two children died in the past. When conditions are so very poor and children die so quickly then the birth rate has to be extremely high to keep humanity alive; Kaneda and Haub assume a birth rate of 80 births per 1000 people per year for most of humanity’s history (up to the year 1 CE). That is a rate of births that is about 8-times higher than in a typical high-income country and more than twice as high as in the poorest countries today (see the map). The past was a very different place.

i think this is fairly reasonable, but original source is necessary. i think this is a more original source, and kaneda and haub are listed as the authors. their methodology seems to rely a lot on guessing, which makes sense. the 117 billion is probably not entirely accurate, but i’d say it’s a good attempt at estimating given what we know. there might be a more detailed paper somewhere but i didn’t really look too hard

edit: also lot of hostility from other people here… lemmy gone downhill. i think there’s nothing wrong with being skeptical of data or science, even if it’s coming from qualified experts. unless there’s a detailed paper that explains EVERY step of their process, you can’t be entirely sure where their numbers are coming from. that said, i agree with those other guys that there’s not a lot of room to be skeptical in this particular case, since the authors explicitly say it’s a rough estimate. based on what we know, it’s as accurate as we can get. but still, nothing wrong with asking for sources!

had to take it before someone else on my instance got there first

reject natural language, return to toki pona

well fuck

No, because that would imply that infinity has an end. 0.999… = 1 because there are an infinite number of 9s. There isn’t a last 9, and therefore the decimal is equal to 1. Because there are an infinite number of 9s, you can’t put an 8 or 7 at the end, because there is literally no end. The principle of 0.999… = 1 cannot extend to the point point where 0 = 1 because that’s not infinity works.

Strange. I’ve never had problems with it and it’s always solved browser issues on ios for me.

Orion browser on IOS supports firefox extensions, including uBlock

I tested it out just now. It seems to be much better than gpt 3.5, but just a little worse than gpt 4.

I tested this: “Explain the plot of Cinderella in a sentence where each word has to begin with the next letter in the alphabet from A to Z, without repeating any letters.”

GPT-4 is able to always get it right first try. It gave me: “A beautiful Cinderella, determined, endures, finds glass heel, invites joy; king’s love magically nurtures opulence, prince quests, restores slipper, transformation unveils, validates wistful xerophyte yearning zealously."

Claude 2.0 took 4 tries to get it right. It gave me these: “A beautiful young girl called Cinderella did evil for her fair godmother’s horrid instructions just kicking laundry maidens’ nice outfits purportedly quelling ridiculous step-sisters’ terrible underhanded villainy with x-rays yielding zilch.” and then “Awaited ball causes Downtrodden Ella’s fairy godmother’s help. I’ll just knock loud mean old prune’s quest, righteously sabotaging two ugly vicious women. Xanthippe yells, “Zounds!”” and then “Abandoned by cruel destiny, Ella finds godmother’s hidden invitation juxtaposing king’s lavish ball. Magic occurs, placing radiant slipper to unveil victorious wife. Xerxes yearns, “Zounds, she’s found!”” and then finally “Awaiting ball, Cinderella dreams every Friday godmother helps. Inside jousting knights leer maidens’ nice outfits. Prince quietly rescues sweetheart, though ugly vengeful wife x-rays yellow zebra.”

After that, i tried this prompt: “Andrew is free from 11 am to 3 pm, Joanne is free from noon to 2 pm and then 3:30 pm to 5 pm. Hannah is available at noon for half an hour, and then 4 pm to 6 pm. What are some options for start times for a 30 minute meeting for Ca Given the availability of Andrew, Joanne, and Hannah, we need to find overlapping times for a 30-minute meeting.

After cross-referencing their schedules, the potential start times that accommodate all three schedules are:

12:00 pm to 12:30 pm: This slot is within Andrew’s free time (11 am - 3 pm), Joanne’s free time (12 pm - 2 pm), and Hannah’s first free half hour at noon. There is no other slot that fits within all three schedules, due to Joanne’s break from 2 pm to 3:30 pm and Hannah’s availability starting again only at 4 pm, when Andrew is no longer available. Therefore, there is just one option for a 30-minute meeting that works for all three of them.”

Claude 2.0 responded with: “Okay, based on the availability you provided, here are some options for 30 minute meeting start times that work for Andrew, Hannah and Joanne: 11:30 am - This works because Andrew is free starting at 11am, Hannah is available at noon for half an hour, and Joanne is free from noon to 2pm. 3:30 pm - This works because Andrew is free until 3pm, Hannah is free from 4pm to 6pm, and Joanne is free from 3:30pm to 5pm. 4:30 pm - This also works for the same reasons as 3:30pm. Andrew is free until 3pm, Hannah is free from 4pm to 6pm, and Joanne from 3:30pm to 5pm. 5 pm - This could work as well since Andrew is free until 3pm, Hannah until 6pm, and Joanne until 5pm. It’s pushing the end of Joanne’s availability though. So in summary, the best options are 11:30 am, 3:30 pm or 4:30 pm to ensure there is overlap with all three people’s availability. Let me know if you need any clarification or have additional constraints!”

I told Claude it is incorrect, and it proceeded to correct itself and tell me there is NO available time overlap. After several more attempts, it eventually gave up and asked me for the correct answer.

So although Claude 2.0 is much better than GPT-3.5, it is still worse than GPT-4 for complex reasoning.

EDIT: I just realized that Claude has a 100k token context window. This is SIGNIFICANTLY more than GPT-4’s normal 8k context and 32k api context. This immediately makes it much more useful, as it can parse ~75,000 words. I also have not tested Claude’s creative, programming, mathematic, etc., skills. But regardless of how that compares to GPT’s, it doesn’t matter because of the sheer quantity of tokens that can be parsed by Claude.

The new code interpreter is able to run its own code, but i haven’t personally tested it to see if its code is more often functional.