24

Alright, it was a long shot :laughing:

Just got done reading the research paper, and I’m really impressed so far, it’s much better than I expected.

1 Like
25

After giving it a shot I can confirm that the results are not spectacular.
It mostly goes on and on about the document being medieval, takes a stab at the style (Gothic, 12-15th century) but never really makes any interesting statements.

PS. Sharing links with images is not yet supported. @PaulBellow

1 Like
26

No worries. Thanks for taking a stab at it! Was curious what it would “guess”… there’s been a lot of theories over the years.

ETA: Saw another screenshot on Discord but it wouldn’t guess… It seems like it’s relying on textual stuff rather than the image… or taking what it “knows” about the image “it’s the Voynich” document but is just gathering vectorized data about the “image”? hrm…

1 Like
27

It does make one wonder exactly how the prompting and context of images works in GPT-4. Can it be trained by example images? Does it have the context required to hold image data or is this processed by a different sub-model of the architecture that only returns language?

28

Thought it would be rolled out together with Dalle3 until I failed to find it in my chatgpt UI. No?

29

Yeah perhaps one needs to prod GPT-4 using some prompts and not just ask it to describe what is the document. Ask it to find patterns or whatever and maybe it can tell us more. I think like for us human, you show one a picture of Mona Lisa and the person will just tell you it is Mona Lisa. But if you tell the person about the smile, scenery, etc. and perhaps the person might give their interpretation.

1 Like
30

It’s something worth trying and if it locates Wally, I will be impressed.

31

634×900 125 KB

2 Likes
32

Bonus question: ask for the precise bounding box, then feed the results and the image to the advanced data analysis tool and ask it to draw it :cowboy_hat_face:

2 Likes
33

I wonder if there’s any way to generate an attention heatmap of the image and, if so, how well that would correlate to locating Waldo?

4 Likes
34

Still waiting here. Anything else cool you’ve tried? Give it some history stuff?

2 Likes
35

I’m also waiting, that was appropriated from twitter.

2 Likes
36

Ah, thought it looked familiar!

Hope your weekend is going okay.

1 Like
37

Yup, all good. Just watched Sam Altman chatting with Joe Rogan, was a fun interview.

39

Another,

Screenshot_20231007_152519_Chrome
Screenshot_20231007_152519_Chrome1440×3579 421 KB

Adobe_Express_20231007_1445590_1
Adobe_Express_20231007_1445590_11920×1200 599 KB

20231007_153159
20231007_153159647×648 235 KB

1 Like
40

I’ll trade my vision for your painting :smiling_face_with_tear:.

Here’s to hoping some powerful API capabilities. Bounding boxes and labels would be sweet as well

1 Like
41

Still haven’t received access. Is it only on the phone app? (I checked both)

42

There is currently a limited number of beta testers with access, this will be increased in time, please be patient while testing is being done.

43

Hi
I haven’t got the picture symbol on mine to add a photo, yet I’ve got the paid version?

44

I just got it on phone (android) and web. It popped up as a notification when I opened GPT, but after that it may be easy to overlook - it’s part of base GPT-4 mode and the only difference is that there is an image icon next to the message field.

I’d rather have DALLE3 than this - I really don’t see much practical use for this.

2023-10-12 00_32_16-Can Draw Simple Illustrations and 2 more pages - Personal - Microsoft​ Edge
2023-10-12 00_32_16-Can Draw Simple Illustrations and 2 more pages - Personal - Microsoft​ Edge794×135 3.14 KB

1 Like