this post was submitted on 18 Feb 2025
418 points (98.4% liked)

People Twitter

5974 readers
880 users here now

People tweeting stuff. We allow tweets from anyone.

RULES:

  1. Mark NSFW content.
  2. No doxxing people.
  3. Must be a pic of the tweet or similar. No direct links to the tweet.
  4. No bullying or international politcs
  5. Be excellent to each other.
  6. Provide an archived link to the tweet (or similar) being shown if it's a major figure or a politician.

founded 2 years ago
MODERATORS
 
top 20 comments
sorted by: hot top controversial new old
[–] rumba@lemmy.zip 52 points 3 days ago (4 children)

You wanna put AI to good use? Save As suggested names.

current name: 02398750983475_98734958793_3.png suggestion: "A picture of the rabbit from Monty python holy grail saved from firefox on Feb 16th 2024.png"

|Save as suggestion | Save as 02398750983475_98734958793_3.png|

[–] napkin2020@sh.itjust.works 19 points 3 days ago (1 children)

Save as "I will not engage with sexually explicit content. Let's try another topic.png"

[–] rumba@lemmy.zip 4 points 3 days ago

I don't think I would use a public LLM to categorize all my data. Even if I'm not doing anything uncoorh, that information's best kept under my roof

[–] Stovetop@lemmy.world 31 points 3 days ago (1 children)

I feel like you could just call it "Monty Python Rabbit.png" and let metadata handle the rest.

[–] rumba@lemmy.zip 20 points 3 days ago (1 children)

Wait, you want ME to name it? like type? think?

30498750987_345870938745_3.png it is :)

[–] Stovetop@lemmy.world 15 points 3 days ago (1 children)

I just mean that the supposed AI summary title is too wordy. Like:

A picture of

It's an image file, so the being a picture of something should be self explanatory

the rabbit from Monty python holy grail

Could just shorten it to "Monty Python Rabbit"

saved from firefox

Contained in metadata

on Feb 16th 2024

Also contained in metadata

.png

Good

[–] rumba@lemmy.zip 6 points 3 days ago (1 children)

Yeah I didn't put any actual thought into it just pondered why the base concept doesn't exist.

[–] Hawk@lemmynsfw.com 3 points 3 days ago

I've done things like this with python. It's not too hard and one can use local models.

You can even control the length of the output using pydantic and other checks.

I've had good success scraping and annotating links from forums etc. Into bookmarks for research.

Very convenient!

[–] priapus@sh.itjust.works 3 points 3 days ago

Firefox is already working on an accessibility feature that add descriptions to images. They could probably add this easily

[–] fibojoly@sh.itjust.works 4 points 3 days ago

HUNTB-069 - Single guy just moved in this apartment and it's only girls who want his attention - JAV, M7F.avi

Wow, thanks DeepSeek!

[–] SGG@lemmy.world 23 points 3 days ago (2 children)

File already exists, overwrite?

[–] sik0fewl@lemmy.ca 32 points 3 days ago

Me: Save as "6606499f1e5c84d7c30 (2).png".

The most unrealistic part of this is that it's trying to save a png instead of a webp that nobody asked for

[–] grue@lemmy.world 8 points 3 days ago* (last edited 3 days ago) (1 children)

Let's be honest: you're at the point you need a full-blown relational DB to catalogue your memes anyway, Stamets. (And we love you for it.)

[–] Stamets@lemmy.world 5 points 1 day ago

cough cough No idea what you're talking about

I usually do

1.jpg

2.jpg

3.jpg

3.jpg because I forgot I already have a 3.jpg

5.jpg

6.jpg

10.jpg because I forgot what number I'm up to and too lazy to check

11.jpg

12.jpg

15.jpg again, I forgot

[–] Tehdastehdas@lemmy.world 2 points 3 days ago

Even Lemmy converts my good file names into nonsense when uploading.

That’s my national insurance number 🤪

[–] GooberEar@lemmy.wtf 2 points 3 days ago

Might as well.