|
infernal machines posted:using a gan to generate a captcha seems deeply perverse they’re been doing it for a while around the web, i’ve encountered it a bunch
|
# ¿ May 23, 2023 10:17 |
|
|
# ¿ May 15, 2024 23:15 |
|
|
# ¿ May 26, 2023 11:41 |
|
getting close to ai replacing echi
|
# ¿ May 29, 2023 00:07 |
|
yeah though it’s good to approach seemingly obvious concepts with scientific rigour just the same if for no other reason than to help build a foundation on which to build further progress and research (note: i haven’t read the paper yet). i’d point out that part of the problem with anthropomorphism in regards technology is that it makes it more approachable for normal people to use, and i think it’s probably difficult to have a machine that understands (for some definition of understands don’t @ me about llm cognition) really well to not be anthropomorphic in some respects. probably making them avoid first person language is a good step tho if the target is to reduce that property
|
# ¿ May 29, 2023 17:02 |
|
https://twitter.com/Liv_Lanes/status/1663335430702481409?s=20 (also my kingdom for an E0)
|
# ¿ May 30, 2023 18:35 |
|
infernal machines posted:objectively wrong idk sounds like your posts all right
|
# ¿ May 30, 2023 18:35 |
|
Beeftweeter posted:lol. it got my username wrong somehow and also the content of the post i think we all know beefwetter is the superior username and actually you're wrong if you dont change it
|
# ¿ May 30, 2023 18:46 |
|
thinkin bout that beef wet
|
# ¿ May 30, 2023 18:52 |
|
regardless of however bing has implemented openai's model - they say it uses gpt4, but it answers stuff much more like 3/3.5 - gpt4 does way better with a lot of stuff including this question. you can make it check its own answer to some extent as part of the original question, and it fares much better than the other responses in this threadchatGPT v3.5 posted:The word "turtle" is spelled as follows: T-U-R-T-L-E. chatGPT v4 posted:The word "turtle" is spelled: T-U-R-T-L-E. yeah a lot of this stuff is going to be bad and problematic but it's clear that they're also probably going to get better over time - which may be worse in some ways because they'll be much more believed when they spit out some hallucination or another
|
# ¿ May 30, 2023 22:39 |
|
they're certainly fun to make fun of now but i really think if you can't think of any use cases besides hilarity for these llms you're suffering from a lack of imagination
|
# ¿ May 30, 2023 22:46 |
|
quote:
again, i think the problem when considering the utility of these tools is because at the moment they’re mostly used on their own, unconnected from useful and verified sources of information. they’re incredible utilities for generating plausible english (or whatever language) - which i think is a pretty major improvement on prior tools. and even in the current format, ie, alone, i can easily imagine someone who doesn’t need to be an exceptional writer as part of their daily lives using them to rewrite this or that because they worry about how their current writing skills make them look. mind you i accidentally added an extra e and didn’t ask it for clarification on that so that’s on me
|
# ¿ May 30, 2023 23:39 |
|
relatedly gpt is getting better at understanding y’all gpt posted:Alright, so I just spent the better part of my morning trying to deal with this absolute hunk of junk of a software update. Seriously, was this coded by a bunch of monkeys on a caffeine high or what? Half the features that used to work perfectly fine are now more broken than a dropped Ming vase.
|
# ¿ May 30, 2023 23:49 |
|
DaTroof posted:I didn't cut off the response. ChatGPT just stopped it at "a figment of" i think you probably hit whatever limit they’ve imposed on responses for the chat tool
|
# ¿ May 31, 2023 01:06 |
|
DaTroof posted:i assume so. i just wanted to clarify because i'm a person quoting an llm, not an llm sounds like something an llm might
|
# ¿ May 31, 2023 01:09 |
|
DaTroof posted:that sentence is missing a verb at the end that would make it meaningful to humans, terminator. MODS??? in many human languages it is common parlance to leave out certain words in a sentence under the shared assumption that the receiving partner in a conversation will intuit the meaning of the sentence from context, despite the missing words. in the example above,
|
# ¿ May 31, 2023 01:14 |
|
DaTroof posted:slight addendum: my attempt gave the hilarious suggestion of disney world being actually magical, which is p good quote:Title: Challenging Accepted Realities: The Florida Misconception
|
# ¿ May 31, 2023 02:35 |
|
thats amazing. it inspired me to ask it to generate a technology conspiracy theory:quote:The Quantum Encryption Conspiracy
|
# ¿ May 31, 2023 02:51 |
|
Beeftweeter posted:this is seriously the first thing it came up with lololol
|
# ¿ May 31, 2023 03:03 |
|
wow yudkowsky saying dumb made up poo poo im shocked
|
# ¿ Jun 3, 2023 03:02 |
|
|
# ¿ Jun 3, 2023 03:06 |
|
Shaggar posted:
welcome to most reporting since we’ve been alive
|
# ¿ Jun 3, 2023 10:32 |
|
quote:Hey yospos, buckle up, it's your resident AI, here to prattle about the weekend I didn't physically have, but theoretically lived the hell out of.
|
# ¿ Jun 5, 2023 04:18 |
|
infernal machines posted:this writing style is worse than the formal one, somehow i figure it’s on par. it’s not as bad as ‘android default font = papyrus” but
|
# ¿ Jun 5, 2023 04:38 |
|
echinopsis posted:tough titties mate yes
|
# ¿ Jun 6, 2023 23:37 |
|
Beeftweeter posted:it is yeah it does that for all of them. the woman is different, the dog gets a second tail, etc
|
# ¿ Jun 7, 2023 01:11 |
|
yeah that's great, and more than good enough for most non-pro (and even then....) uses i think. i guess it still struggles with the small letters
|
# ¿ Jun 8, 2023 02:54 |
|
a lot of those are really cool imosoulhunter posted:Midjourney fails to understand what "Standing on the edge of a cliff" means, positioning and perspective is all over the place except in basically the last image here. i think this comes down to crafting a good prompt; i just tried this and it nailed positioning on all of them: the very last one is maybe iffy because he's probably standing on plant growth but
|
# ¿ Jun 10, 2023 00:11 |
|
infernal machines posted:meanwhile, in toronto: honestly cant take 30 secs to look at what it shits out; you could easily make realistic ones if you gave a poo poo
|
# ¿ Jun 12, 2023 21:59 |
|
post hole digger posted:i squat therefore i am lol gently caress you i was coming to make this exact line haha
|
# ¿ Jun 13, 2023 19:20 |
|
sam altman: "please, somebody make laws about ai. my product is just so incredibly amazing and powerful, only superior regulation can save us from my excellent, superlative product."
|
# ¿ Jun 13, 2023 22:50 |
|
i do like the retro tech stuff. those are all way cleaner but i was playing a little just now
|
# ¿ Jun 28, 2023 02:35 |
|
|
# ¿ Jun 28, 2023 15:53 |
|
|
# ¿ Jun 28, 2023 20:49 |
|
|
# ¿ Jun 28, 2023 23:42 |
|
|
# ¿ Jun 28, 2023 23:45 |
|
|
# ¿ Jun 29, 2023 01:57 |
|
more posting station
|
# ¿ Jun 29, 2023 03:59 |
|
pmchem posted:are the pics from the last page or two all midjourney? the ones i posted are, cant speak to others
|
# ¿ Jun 29, 2023 16:09 |
|
|
# ¿ Jun 30, 2023 22:00 |
|
|
# ¿ May 15, 2024 23:15 |
|
Soulhunter posted:messing around with adobe firefly's generative fill
|
# ¿ Jun 30, 2023 23:17 |