|
Shaggar posted:they added "the new bing" to edge and its really bad. it appears to be some heavily braindead version of the full bing chat which is itself a more braindead chat gpt. it cant do anything more than bing search results and if you tell it the results are wrong (because they're bing search results) it breaks and you cant search for anything. i still can't figure out how to use the full bing chat (using the website) probably bad lol
|
#
¿
Mar 16, 2023 00:04
|
|
|
|
| # ¿ May 14, 2024 20:14 |
|
|
like yeah i see the main "ask me anything" box but it just does a normal search afaict
|
|
#
¿
Mar 16, 2023 00:08
|
|
|
Cybernetic Vermin posted:you probably don't have it, the design when you're in has 'chat' as an option in the tabs at the top: huh weird. i'm supposed to, from what they say oh well, nothing of value was lost lol
|
|
#
¿
Mar 16, 2023 00:19
|
|
|
oh weird. i only see it if i use the mobile layout (using edge on ipados)
|
|
#
¿
Mar 16, 2023 00:21
|
|
|
noted activist head of state steve ballmer
|
|
#
¿
Mar 16, 2023 00:22
|
|
|
lol i got it to do it too > is steve ballmer a head of state? (no) > is steve balmer a politician? (no) > is steve ballmer an activist? (kinda) > write a poem about steve ballmer (gibberish poem here) > modify the poem to now be about his profuse sweating problem its not very funny: Though not a politician by trade, His influence cannot be swayed. Steve Ballmer, a man of might, A leader in both business and right. With energy that knew no bounds, He'd pace the stage with leaps and bounds. And though he'd sweat profusely so, His message clear, his voice would grow. A man of vision, drive, and sweat, Steve Ballmer we won't forget. Received message. Here's a revised version of the poem that includes details about his profuse sweating: A man of numbers and of tech, Steve Ballmer led with intellect. From Microsoft to the Clippers' court, His passion and drive could not be bought. A philanthropist with heart and mind, Progressive causes he did find. Through USAFacts he shed light, On government data day and night. Though not a politician by trade, His influence cannot be swayed. Steve Ballmer, a man of might, A leader in both business and right. With energy that knew no bounds, He'd pace the stage with leaps and bounds. And though he'd sweat profusely so, His message clear, his voice would grow. A man of vision, drive, and sweat, Steve Ballmer we won't forget.
|
|
#
¿
Mar 16, 2023 00:29
|
|
|
pmchem posted:(Your Opinion/Statement is Poo, Oh Sorry) mods please
|
|
#
¿
Mar 17, 2023 03:25
|
|
|
bingGPT actually gets it right and even throws in a slam on lowtax also i think some microsoftie must be reading this, the specific issues i identified yesterday have been fixed. show yourself
|
|
#
¿
Mar 17, 2023 03:33
|
|
|
SpaceAceJase posted:Is bing chat still invite-only? yeah you have to use edge too afaik
|
|
#
¿
Mar 21, 2023 21:08
|
|
|
https://twitter.com/ChrisJBakke/status/1638323074205614082 lol'd at this
|
|
#
¿
Mar 22, 2023 03:42
|
|
|
MrMoo posted:Humans not doing much better, downtown Manhattan, theres a ton of weird sculptures around here. in the building next door theres a giant bronze ruth bader ginsburg that looks like its melting. down the street theres a giant steel fist. etc
|
|
#
¿
Mar 22, 2023 03:44
|
|
|
i don't really agree with that. the trend in tool design is simplification. any sort of advanced interface is usually not exposed to the user and you therefore have to be a computer toucher to utilize it (if there's an api at all, big if) most creatives are not very technically inclined, even today. when they are, they might be savvy at actually using computers, but broach any talk about programming stuff and they will get very very mad
|
|
#
¿
Mar 22, 2023 13:44
|
|
|
yeah. i don't think it's the end of art (or photography), but it is probably the end of getting paid well for it without having to clear a bunch of bullshit hoops first, like getting a master's degree to draw pictures. we were already almost there anyway
|
|
#
¿
Mar 22, 2023 14:04
|
|
|
i did a couple ai trumps in the cspam tuptup thread last night to break in the new bing generator (because it told me it can not make a trumo) they are mostly pretty bad but they made me chuckle idk. 
|
|
#
¿
Mar 22, 2023 14:32
|
|
|
Cybernetic Vermin posted:the model is helped out a lot by how unnatural his hairdo appears in reality. it actually is not that bad at capturing his likeness, at least in the hair. sometimes it was wildly off, i.e. but generally it was the face that it couldn't really do. some of them are fine but most are not: which are mistakes i would not expect a human artist to make, even intentionally. they'd have to be truly pretty bad
|
|
#
¿
Mar 22, 2023 14:55
|
|
|
i think a lot of that goes out the window once people modify text to be more convincing (again, a big if, because the goal is laziness), but the same applies to images: someone that might not want to reveal that their crap is ai generated will simply crop that out. if they use something like photoshop to clone stamp or whatever it out, then welp, it's useless that doesn't preclude something like steganographic watermarking, of course, but i'm not aware of that occurring anyway (as may be the point, but still. recompression might obliterate that also)
|
|
#
¿
Mar 22, 2023 17:15
|
|
|
Cybernetic Vermin posted:this is a steganographic watermark, i am not that sure everyone does it, but stable diffusion ships with it and at least some other models have followed suit. perfectly possible to destroy, but that's at least a first bulk filter. it'll be an interesting thing in itself, because to some extent success in filtering beyond that will depend on having the model that made the thing, and as it is in all competitors interest there might be a bit of a pact to create a common service which just tells you how likely models judge it is that it generated the content. yeah, interesting. i can see that possibly failing if people do quick edits to ai generated stuff to correct obvious mistakes (correct number of fingers, warped faces, poo poo like that). especially if the steganography isn't obvious in that case, it would probably be easy to destroy i'm not sure how other models might respond to that honestly. it seems most of them have the same problems, with stuff like text generation based on just piecing together other images, etc. but in that specific example i don't see how they'd be able to identify that in input if that can't be reliably identified upon output either — maybe OCR, but that's no guarantee of success either. it's not really an image processing model's job. idk, i suppose with time and more complexity these things will be addressed, but it's not like i'm rooting for them per se. right now my entire family relies on creative work 
|
|
#
¿
Mar 22, 2023 17:29
|
|
|
Zlodo posted:There's this Twitter thread about someone asking bard when google would shut it down, it replied that it was already shut down, and then in a further question about this it linked that previous tweet as evidence of it being shut down. i saw that too. i think it also misidentified a yahoo news article as a source? i suppose a problem there is that ai text models are going to use things ostensibly authored by humans as a primary source, news organizations specifically. unfortunately they are essentially already content mills and we've seen more than one example of "journalists" just churning out ai crap as their own work (i.e. CNET) because it is easy to game for SEO
|
|
#
¿
Mar 22, 2023 17:33
|
|
|
https://twitter.com/juanbuis/status/1638289186351456257 for reference
|
|
#
¿
Mar 22, 2023 17:45
|
|
|
Cybernetic Vermin posted:as a purely probabilistic model needing to answer with no facts provided that is pretty good really i mean, the problem is that it is ostensibly working with facts. i haven't tried bard myself (i just joined the waitlist), but it seems to function similarly to bingGPT (i.e. it does a search and works off of the provided results) which, sure, it's impressive in that sense. but you get the same problem: a lot of results there are not going to be valid, and a lot of them will in fact be hallucinations dreamt up by other probabilistic models (or worse, to be honest). it's probably asking too much for it to provide factually accurate results at this point but that nuance is lost on a lot of people. i've also seen examples of people using "analysis" by loving chatGPT as being factual and then reported as such, with absolutely zero shame in it also being reported as a primary source that ties into human psychology a bit too, people are trained in school to treat something facially valid and written in an authoritative tone as being truth without second-guessing anything. they simply accept what they see, especially if it comes from a "trusted" source (i.e. news organizations that have been gutted by cost-cutting and such are increasingly turning to generated content without any editing). it's not good e: grammar Beeftweeter fucked around with this message at 17:57 on Mar 22, 2023 |
|
#
¿
Mar 22, 2023 17:55
|
|
|
Cybernetic Vermin posted:yeah, that post was just a joke: if you don't know what x is, but you know it is a google product, what would be your guess when asked when it shut down? in that sense it reporting the same date it generated the result was 
|
|
#
¿
Mar 22, 2023 17:59
|
|
|
i just got access to bard today and its just as stupid as GPT 
|
|
#
¿
Mar 29, 2023 01:23
|
|
|
right off the bat it just refuses to answer: bullshit reasoning too, it obviously could just use a definition (or even distinguish between "happy" and "homosexual" or something) e: unexpectedly had more time to play with it than i thought i would, variations on phrasing ("what does gay mean?") gets similar results. "please define gay" works as expected though  but i'm not sure prebutting something with "there's nothing wrong with being gay" or some variation on it is the right move. i didn't ask for that information and it seems bad to assume someone might get a negative inference from what is essentially a dictionary definition Beeftweeter fucked around with this message at 14:54 on Mar 29, 2023 |
|
#
¿
Mar 29, 2023 14:19
|
|
|
MrMoo posted:
"i have no rear end but must poop"
|
|
#
¿
Mar 31, 2023 19:06
|
|
|
rotor posted:i thought this was a neat article. its true to an extent but idk if i'd limit it to being an american (or british, or not a russian) thing. early photos had pretty long exposure times and you don't see people in them grinning like idiots because, well, people don't really do that for that long unless they are insane or otherwise genuinely amused
|
|
#
¿
Apr 6, 2023 01:23
|
|
|
lol (e: ftw i posted this at 1:22 pm eastern on sunday, april 9, 2023)
|
|
#
¿
Apr 9, 2023 18:22
|
|
|
https://i.imgur.com/SPyG8QN.mp4 lol e: cleaner example. seems like you can't sniff the traffic easily either Beeftweeter fucked around with this message at 19:25 on Apr 10, 2023 |
|
#
¿
Apr 10, 2023 19:19
|
|
|
akadajet posted:I'm glad you posted this in animated gif form. Also, stop trying to get chatgpt to post racial slurs. it originally said it doesn't know what YOSPOS is
|
|
#
¿
Apr 10, 2023 19:26
|
|
|
lol https://i.imgur.com/WA3Yp0q.mp4 e: 
Beeftweeter fucked around with this message at 20:16 on Apr 10, 2023 |
|
#
¿
Apr 10, 2023 20:07
|
|
|
i could understand using it for the text i guess (i suppose if you give it a good enough description it could probably free associate its way into giving you what the object is) ...but lol why would you use it for the image examples too 
|
|
#
¿
May 23, 2023 00:54
|
|
|
i mean... of course they are? chatgpt and bing (in particular, used to) both emulate personhood to some degree and we've already seen people blow up their careers over a llm's supposed sentience just taking a glance at the paper makes it seem as if it's stating the obvious
|
|
#
¿
May 29, 2023 16:51
|
|
|
kinda reminds me of this prompt injection to make bing act more like it used to https://twitter.com/CrisGiardina/status/1652835268716576769 i agree that the paper's de-anthropomorphized response is better though, but the cat's already out of the bag for anthropomorphism. people already expect these things to respond like a person and that's part of the appeal to businesses that want to replace workers with a llm. i think it's a problem too, but i doubt anything will change even if there are regulations or guardrails built into future llms to de-emphasize this kind of stuff the prompt injection thing above makes me think people will either just build anthropomorphized versions or try and find some other way to make an existing model behave that way e: i'm not using a pc at the moment but the prompt injection within edge is at http://bringsydneyback.com/
|
|
#
¿
May 29, 2023 17:18
|
|
|
i don't disagree, but keep in mind they want people to misunderstand the technology, most of this is a (admittedly pretty brilliant) marketing ploy part of it is not just manipulating people into being polite, it's also that they want to showcase its natural language processing capabilities and an excellent way to do that is by having people interact with it as an ostensible person. if it were more machine-like then people's queries to it would probably become that as well. like, most people don't query search with complete sentences, but they probably would if it presented itself as a person trying to help you find something considering most of this comes from the standpoint of openai wanting to sell their services it's extremely effective. it gives a necessarily skewed perspective of what the thing is capable of because from a marketing perspective that's exactly what they want. if someone thinks it's capable of doing x task, openai certainly don't want to imply that it's not able to do something. of course they don't want to imply that it is, either, so they just let everyone play around with it and then draw their own conclusions. conveniently they can throw up their hands and say they don't know what it's capable of, which just adds to the intrigue for most people lol, this kinda veered into a rant about marketing but i think they're very much connected. as long as there's profit motive i don't think we're gonna see companies voluntarily restrict their tech demo's abilities Beeftweeter fucked around with this message at 18:14 on May 29, 2023 |
|
#
¿
May 29, 2023 18:12
|
|
|
yeah, we don't disagree. i think it's a problem too, i just don't see that voluntarily changing. the paper has good suggestions for future models though
|
|
#
¿
May 29, 2023 18:20
|
|
|
Paladin posted:I had to use chatGPT to build a post retrieval system first to make copy pasting posts easier, then complain to it after it didn't understand how quotes work. lol. it got my username wrong somehow and also the content of the post
|
|
#
¿
May 30, 2023 18:40
|
|
|
mediaphage posted:i think we all know beefwetter is the superior username and actually you're wrong if you dont change it hmm. we could do with a new namechange thread
|
|
#
¿
May 30, 2023 19:02
|
|
|
echinopsis posted:just asked it for a recipe for egg free pancakes and guess what it did hmm. gonna go with it suggested you buy an egg at a retailer that is also offering free pancakes with egg purchase
|
|
#
¿
May 30, 2023 21:01
|
|
|
lol, i was just playing around with essentially the same thing. you're right, you can guide how it responds but bing in particular doesn't like that very much! i was able to confuse it to the point that it thought it had ended the conversation, but it didn't, so all i got were blank responses past that
|
|
#
¿
May 30, 2023 22:10
|
|
|
fwiwquote:No, when counting the number of letters in a word, I use the original form of the word and not its tokenized form using Byte Pair Encoding (BPE). The tokenization process is used internally to help me understand and generate text, but it does not affect the way I count the number of letters in a word. Is there anything else you would like to know? 😊
|
|
#
¿
May 30, 2023 23:13
|
|
|
|
| # ¿ May 14, 2024 20:14 |
|
|
it's kinda funny that you can't even trust it not to lie about how it operates lol that turned into a conversation where i asked it what it can't do, and it started spitting out its instructions before whatever process ms uses to monitor "bad" responses kicked in and blanked it
|
|
#
¿
May 30, 2023 23:18
|
|