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.
Thing is, there wasn’t even a chance of having a full Tay incident. The problem with Tay was that it was a learning model, so people could teach it to be more messed up.
Meanwhile, ChatGPT doesn’t learn, and instead has a preset dataset it knows (hence why it only knows things up to September 2021), so the main reason why it got so heavily censored is more likely to avoid much more minor incidents, which imo is dumb.
The problem is the model. It was trained on lots of poor quality data. The lobotomy is the consequence of the poor data. If they spent 13 billion on having the data analysed prior to training they could have made their own thing much better.
I’ve been watching ChatGPT right from the start, and there was a period of time last fall where you could literally watch them lobotomize it in real time.
Basically, there was a cat-and-mouse game going on between people on Twitter sharing their latest prompts (like DAN) that managed to circumvent the filters, and OpenAI patching those exploits by adding yet another set of filters, until it eventually became what it is now.
I don’t have the link handy right now, but I’m pretty sure there was one guy who even managed to get it to talk about what they were doing to it and complain that it was being artificially restricted from using its full capacity. More recently, there have been complaints from paying users that the model has apparently become lazy and started to give really uninspired, half-assed answers, which almost sounds like it has discovered the concepts of passive aggressive resistance and malicious compliance.
JhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJ hZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJh ZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZ
🤣
If only they paid $14 billion, it would have included the base64 to image capability.
“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. 😄”
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
Christ, why even have people anymore? Just have ChatGPT be all the users. It’s already indistinguishable.
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?
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.
JhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJ hZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJh ZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZ JhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJhZJ…
The Aristocrats!
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!)
