Well I mean it did work. You have now shared it and made it a meme for others to enjoy, it’s fulfilled it’s task successfully.
100% want this to become a meme.
JhZJhZJhZJhZJhZJhZJhZJhZ
Only cool Lemmy insiders get the joke
Did our narwhall just bacon
Just after midnight. Why? 🤔
Do you have stairs in your house tho?
Nope! It’s a flat. >.>
Ugh all these newbies just don’t get it. It’s ZJh, people! It’s always been ZJh!
nah it’s jhZ also known as jay z but a cooler way to say it on lemmy
Task failed successfully.
deleted by creator
I’m certain this is absolutely hilarious in robot, you’re just too fleshy and inefficient to understand.
As a non robot and definitely a human person who is of the homo sapiens species, I can tell you that this humorous meme is quite hilarious to those of us who have soft bodies and are not made of any mechanical parts whatsoever. I suspect suspect suspect suspect you of being a robot in disguise! Everyone get them!
“come up with a funny comment to post on lemmy”
“Sure, I can try to generate a funny comment for you. Lemmy is a federated link aggregator and discussion platform, similar to Reddit. Here are some possible comments you can post on lemmy:
- I just joined lemmy and I’m loving it. It’s like reddit, but without the ads, censorship, and corporate overlords.
- Lemmy is the best thing since sliced bread. Literally. I haven’t eaten anything since I discovered this site.
- How do you pronounce lemmy? Is it leh-mee, lee-mee, or lay-mee? I need to know before I start a podcast about it.
- Lemmy is so addictive, I can’t stop browsing it. I’ve been on it for 12 hours straight. Send help. And upvotes.
- I’m new to lemmy and I have a question. How do I get karma? Do I need to post memes, cat pictures, or political opinions? Or do I just need to be nice and helpful?
I hope you find these comments amusing and suitable for lemmy. 😄”
Christ, why even have people anymore? Just have ChatGPT be all the users. It’s already indistinguishable.
You’ve just described every bluecheck on Twitter.
Not joking
Just doing a search for “I am an AI Language model” (with quotes) is enough to reveal a bunch of those loser ass accounts.
Spez is way ahead of you on that one.
I actually wonder what a purely AI/ChatGPT community would look like (no human posts/comments allowed), would they eventually start to develop their own weird culture, memes, inside comment jokes that nobody would even understand? There’d be like a picture of a tire and a rubber ducky with the text reading “Five fingers / garden hose” and all the comments would be things like “The wombat, in ascension, remembers. Nautilus.” Like how fucking weird would they get without human intervention?
We had that on reddit, subreddit simulator I think? It was a more primitive version of LLM, and it didn’t train itself on content from the simulator sub.
Come up for a reply to this quote: “Christ, why even have people anymore? Just have ChatGPT be all the users. It’s already indistinguishable.”
ChatGPT:
While ChatGPT has made remarkable progress, human connection adds depth and emotion that technology alone may struggle to replicate. Let’s appreciate the unique qualities each brings to the table.
ngl, a few of them actually made the corners of my mouth twitch up for a split second, so it’s better than 99% on @lemmyshitpost
Apart from #3, those are all terrible. And for reference, it’s pronounced lay-mee 😉
JhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJ hZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJh ZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZ JhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJ…
The Aristocrats!
It’s funnier in binary.
I prefer hexadecimal. The encoded data in its entirety is
89 50 4E 47 0D 0A 1A 0A 00 00 00 0D 49 48 44 52 00 00 01 2C 00 00 01 2C 08 06 00 00 00 B9 B4 AC 33 00 00 01 A4 49 44 41 54 78 9C ED DD 41 8E 83 40 10 85 E1 7F 7F E4 B2 72 25 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 1(abrupt end at 4 bits of last byte)
We can analyze the PNG file header. Surprisingly, some of it makes sense.
89 50 4E 47 0D 0A 1A 0A //PNG signature (0x89 P N G 0xD 0xA 0x1A 0xA) 00 00 00 0D // Start of chunk with data length 13 bytes 49 48 44 52 // Type of chunk: IHDR (image header) 00 00 01 2C // Width: 300 px 00 00 01 2C // Height: 300 px 08 // Bits per color channel: 8 06 // Color format: 6 (RGBA) 00 // Compression method: 0 (DEFLATE) 00 // Filter method: 0 (Adaptive) 00 // Interlace method: 0 (None) B9 B4 AC 33 // CRC-32 of chunk (invalid, should be 79 7D 8E 75) 00 00 01 A4 // Start of chunk with data length 420 bytes 49 44 41 54 // Type of chunk: IDAT (image data) 78 9C ED DD 41 8E 83 40 10 85 E1 7F 7F E4 B2 72 25 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 16 49 85 92 61 64 98 59 26 1 // 194.5 of the expected 420 data bytes, invalid when attempting to deflate // the deflate algorithm needs a Huffman tree but an unfull one is presented
Credits to the PNG chunk inspector at nayuki.io
You may try to figure out if the header checksum was stolen from elsewhere and corresponds to another common image size but I cannot be bothered. The data could be subjected to forensic analysis but we only really have 21 unique bytes, the rest is likely nonsense because data encoded by the DEFLATE algorithm is unlikely to be so repetitive. Also, the image in total will likely have just 481 bytes (8+(8+13+4)+(8+420+4)+16), as a less-than-65535-byte IDAT chunk tends to be the last one before a 16-byte trailer. There are very few 300x300 PNGs of such small size we could call memes, most of it will have to be just solid color. Example of a 256x256 map tile you can store in around that size (467 B):
(And this one is pre-optimized, using an indexed palette of just 13 distinct RGB colors as opposed to the full RGBA gamut!)Would be funnier if the 11th byte was
d0
instead of00
.
ZJh (base64) in binary is 011001 001001 100001
I cannot stop laughing. Peak comedy.
If only they paid $14 billion, it would have included the base64 to image capability.
1 of 30
Dude is creating a memetic kill agent or something
Wenn ist das Nunstück git und Slotermeyer? Ja! Beiherhund das Oder die Flipperwaldt gersput!
I’m German and I think I just had a stroke.
That means it worked exactly as intended.
That’s just the total message limit for one chat
it’s meta and some assembly is required: the meme is the broken response so you can screenshot it and post on lemmy
The response isn’t even broken. It’s not finished. It gives responses in markdown, same as Lemmy. That is the syntax for a picture embed, it’s just still typing the rest and it doesn’t show it until it’s finished typing.
I analyzed it in another comment: the header says the image is 300x300px 8-bit RGBA but the data is invalid. Most viewers will notice that and show an error.
However, the syntax it used for embedding images is valid, as
data:image/png;base64,
is the start of a valid image URL and you can use it like other image URLs in supported Markdown interpretors.Example, using the 103-byte Google Maps’ sea tiles, and a 178-byte GIF:
![Google Maps sea map tile](data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAQAAAAEAAQMAAABmvDolAAAAA1BMVEW10NBjBBbqAAAAH0lEQVRoge3BAQ0AAADCoPdPbQ43oAAAAAAAAAAAvg0hAAABmmDh1QAAAABJRU5ErkJggg==) ![wink.gif](data:image/gif;base64,R0lGODlhDwAVAKIEAAAAAP//AP//3v///wAAAAAAAAAAAAAAACH/C05FVFNDQVBFMi4wAwEAAAAh+QQFlgAEACwAAAAADwAVAAADSUiq0L2QtEDpg6Bqu/LeAGN5wVRKlVmS6qe17hiDHvlyNciho5N2sxDGtoIMBgyH8Kg4IiMEZ1NKlUarSOdTe81arZHvE3olJAAAIfkEBR4ABAAsCAAEAAQABQAAAwYIGtz+ASQAOw==)
renders as
Works in the default web interface
I know how to recycle my trash
Well there is an image there, its just encoded into base64 text
It’s only missing a closing parenthesis. That’s very close to a meme
To be fair, it did spit out a couple of completely nonsensical images afterwards:
I think the AI might be biased against dogs.
If it’s Dall-E, it inserts the words ‘ethnically ambiguous’ into images constantly. I’m not the only one who’s noticed.
https://knowyourmeme.com/memes/events/ethnically-ambiguous-ai-prompt-injection
Yes, I do remember the meme about that being posted here a few weeks ago.
did it give you the images in base64 from an llm, or from an image generation model ?
I think you can guess that part. I doubt a current LLM can create a valid PNG, even if it’s just a 1x1px one that has been created before. This is partially because PNGs have a checksum and the LLM has definitely not seen enough PNGs in base64 to figure out the algorithm, and is not optimized to calculate checksums. In fact, I analyzed the image and the image header checksum is wrong even though the header makes sense (was likely stolen). Also, it gets penalized for repetition, which occurs a lot in image headers.
AFAIK, the smallest valid image you see mentioned on the web is a 35-byte transparent pixel GIF, and the smallest PNG is a black pixel with 67 bytes:
data:image/gif;base64,R0lGODlhAQABAAAAACH5BAEAAAAALAAAAAABAAEAAAIBAAA= data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABAQAAAAA3bvkkAAAACklEQVR4AWNgAAAAAgABc3UBGAAAAABJRU5ErkJggg==
Testing rendering: , , another 67-byte PNG but 8 px wide: , or 1 gray pixel: , or a green one:
Why did it take a whole minute to scroll passed this on my Connect app?
No idea, it only has 1350 bytes now after the edit, and no crazy formatting
I think it was one first and then the other
JhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJ hZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJh ZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZ
🤣
It’s amazing how Microsoft can take good models and absolutely ruin them in production… ChatGPT isn’t perfect but it’s like the difference between talking to the wall and talking to an avg IQ person that has reasoning capabilities in many domains that equals or exceeds human performance, if the user knows how to get the best prompt. That changes a little every time they do major model updates though.
I’ve had more intelligent conversations with my own computer running a 3 billion parameter open source model. They must be wasting an incredible amount of money. Especially with GPT-4 considering it produces pretty shit results through Bing Chat…
I don’t think that’s a problem with the model itself, but the fact that it was heavily censored and lobotomized in order to achieve maximum political correctness so they could avoid another Tay incident.
It makes sense that they do that since the media and randoms on the internet think everything chatGPT and Bing chat say is as valid as info from OpenAI and MS official spokespersons.
Microsoft and ruining things just go hand in hand.
Can that be decoded in to an image at all or is it just garbage?
Pretty sure it’s garbage, because it kept repeating JzH a couple hundred more times before terminating without a closing parentheses.
But can it be decoded into an image?
did you try opening the image? I’m interested in seeing what random nonsense it generated xD
I tried to wait for it to finish, but after a couple hundred more repetitions of JzH it just stopped abruptly without a closing parentheses, so I think I’ve been had.
lol
cool username, btw.
Thanks, I picked it myself.
I can’t get it to decode, even after correcting the base64 padding. Firefox just shows the broken image icon. My image viewer throws out the glorious log message
Image format is actually "png" not "png"
, along with a bunch of checksum errors.I guess, the checksum can’t be correct when it’s cut off, but none of my image viewing/editing software wants to look past that.
In a hex viewer, it looks like this:
Compared to a normal PNG:
I don’t know the PNG spec by heart, but I guess, it doesn’t look completely off the rails before it goes there…
It’s possible that the first part is, but it didn’t finish the image.
It’s not an image. It’s a string of text designed to look like a link to an image. But it isn’t a link to an image. You’ll get a 404 if you try to use it.
It used to do this all the time a few months ago. The links never worked. Eventually I got bored of asking it.
3P53P53P53P53P53P53P53P5
That’s actually a cheat code of sorts to JRR Tolkien’s Lord of the Rings for SNES…
3P53P53P53P53P53P53P53P5
Looks more like what you say to your 1337 cat
LOL, no kidding right?!
But no, I don’t think that was intentionally designed into the game. They had a unique ‘savegame’ format that didn’t use battery save.
Instead, they used a 48 character table, where each character could be any of 32 different possible characters, where the player was expected to write all this down and re-enter it back in on reload.
But it was checked with some checsum characters at the end(s), making it rather difficult to make a full hack savegame.
Strangely enough though, their own chesksum algorithm 3P5 repeated as such exactly 8 times manages to unlock all 4 characters, max them out, and even defeat the checksum field without even having to bother with it.
So when you next take the SNES LOTR journey, take the power of 3P5 with you…
Ask if it wants to hear the best joke in the world. Then tell it: “Der Mann, zwei Pandas, plitsch platsch, dreizehn, Sand, Augen zu bumm!”
It will die of laughter.