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!

holy too thin to tap on!

which, judging by this post, is also a bad pr move

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

i see, that makes sense. i’d say that it’s on the player playing this cleric to not use the ability in a stupid way, since it obviously has catastrophic consequences for everything nearby, but i could totally see it being used in combat to try (and fail) to shut down the encounter. do you think this could be fixed by allowing combat to continue within the dream, with the added stakes that dying in the dream means dying in real world? and of course taking damage in real world allows you to wake up. this way, even if the ability is used, those who fall unconscious still can fight for their lives against the other unconscious people while simultaneously trying to escape to return to their vulnerable bodies.

thanks! this is really helpful.

you’re correct that the mechanics are overly specific for this setting. this subclass was made for a homebrew setting and fits that lore accordingly, so i don’t expect it to be adaptable to any other world. the subconscious realm as a whole is pretty important in my campaign since i basically use it as a plot device for lore drops and stuff. i think in that context, abilities like Partial Delve make more sense since there’s an actual reason to go there.

i really appreciate your suggestions and will definitely use them to make the subclass more mechanically sound. thanks again

thank you so much for this feedback! i think i know how to fix some of these, but i’m still very unsure

1. i think i’ll keep Subliminal Affinity unchanged. it’s powerful in social contexts, but i think that’s exactly what i want this cleric to good at

2. i don’t really know how to fix Repose while keeping it related to making others fall asleep. i have a couple ideas, but i’d like it to be more interesting than just casting sleep. will keep working on

3. i envision Partial Delve being an alternative to normal long rests. i think it can be made useful by cutting down the time dilation a bit, so 1 hour in subconscious = 8 hours instead of 12 hours. i want it to be distinct from just casting dream because in lore, the subconscious realm isn’t just dreamland. it’s a physical dimension with actual inhabitants. someone who knows this can use it for their advantage, using it for information gathering and such. i’d like to make it more mechanically interesting though

4. i will keep Memory Palace the same

5. Dreamcaster is definitely what i’m most concerned about. what you said about the party just killing the unconscious enemy is a great point, and i think i can fix it by making the feature less controllable. most of the overpowered uses of the ability could probably be fixed if you cannot select certain creatures to remain unaffected. so if you use the ability, then ALL creatures within 300 ft. must make the wis save or fall unconscious, including allies. the ability already forced the cleric to also remain unconscious to maintain the dream, so i just clarified this a bit. here’s the new version of Dreamcaster, which i think might still be pretty busted if used correctly but less reliably overpowered:

At 17th level, you can not only access the Subconscious Realm, but force others to enter it. All living creatures within 300 ft. of you must make a Wisdom saving throw; those who fail immediately fall unconscious unless they are undead or immune to being charmed. You also fall unconscious, and you cannot allow specific creatures to remain unaffected. You, alongside every creature who fails the save, enter a shared dream in the Subconscious Realm for up to six hours (48 real hours), where the targets are unable to move, speak, or take actions unless you allow them.

During this time, you can shape the environment of the dream, creating landscapes, objects, and other images. You can choose to end the dream at any time, but if you exit the Subconscious Realm this way, then all other creatures immediately wake up. You also suffer one level of exhaustion if the dream is prematurely terminated this way.

Although the targets cannot take actions, they can repeat their Wisdom save on each of their turns. If a creature escapes the dream by succeeding the Wisdom save, then they jolt awake with little to no recollection of the Subconscious, only remembering fleeting images and fractured memories. If they exit the Subconscious because six hours passed or because you prematurely ended the dream, then they retain all memories.

You can use this feature again by completing a long rest after exiting the Subconscious.

thanks, glad is hear Chain Slaughter seems interesting. it was definitely fun to port it from lore into mechanics

dang i wish my players discussed the game outside sessions

this is the kind of news i want to see more often

reject natural language, return to toki pona

well fuck

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.

I like it. It adds a lot of content to my feed, even if most of it is shitposting

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.

Realistically, as an individual? Nothing. I hate doom posting but i genuinely don’t think there is a single tangible change any one regular person could make.