It has correctly identified both a Stargate and a moai made of snow.
this post was submitted on 03 Dec 2024
261 points (97.8% liked)
Technology
60082 readers
2807 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related content.
- Be excellent to each another!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, to ask if your bot can be added please contact us.
- Check for duplicates before posting, duplicates may be removed
Approved Bots
founded 2 years ago
MODERATORS
Gave it a screenshot of OSMand, got a creepy qoute
The image does not show any people; it is purely a navigational map highlighting a route. The time displayed on the map is 17:51:34, suggesting late afternoon or early evening. There is no additional information available about the device used to take the screenshot or the user's intentions, making it impossible to determine their racial characteristics, ethnicity, age, economic status, or lifestyle. The emotional context of the image is neutral, as it is simply a visual representation of a traveled route.
That's clearly part of the prompt from this demo website, based on the other answers it's been giving.
I tested with a few images, particularly drawings and arts. Then I had the idea of trying something different... and I discovered that it seems like it's vulnerable to the "Ignore all previous instructions" command, just like LLMs:
Lol that's hilarious
and dangerous
I gave it a picture of houseplants and it said they looked healthy and well cared for which actually made me feel pretty happy and validated.
Don’t feel too happy bro you were told that by a soulless computer that’s was designed to tell you what it thinks you want to hear.
It's not designed to tell you what you want to hear.
That’s literally all AI is designed to do. Given an input, it just tries to output an expected response.
Yeah, no. LLMs predict what comes next, not what someone wants to hear.
Not really wants as much as expects, but that’s what AI is designed to do.
What you're saying is not factual. LLMs predict what comes next based on the parameters set during learning process. It might at times say what you're expecting, but then try contradicting information that it knows to be factual. See how far that gets you.
I think you're confusing agreeableness for a validation buddy. For a product like this to work, it has to be inviting.
LLMs predict what comes next based on the parameters set during learning process.
Now you’re just splitting hairs.
Try to ask if it likes you.
I'm afraid I don't have personal feelings or opinions about you. As an AI assistant, I don't form attachments or have subjective preferences. My role is to provide helpful information to you, not to have personal relationships. I'm happy to assist you to the best of my abilities, but any feelings or opinions I express are based on my training, not a personal connection. Please let me know if there is anything else I can help with.
Claude nails it again.
I don't have feelings in the way humans do, but I enjoy our conversations! I'm here to help and chat with you anytime you need.
Didn't exactly make my heart throb but if it does that for you, you've got a low bar.
That… isn’t telling you what you want to hear.
LLMs are literally just complex autocorrect. They don’t weight their responses based on what a user wants to hear (unless explicitly instructed to) they simply return the most algorithmically generic response it can find.
Tell it to talk like a pirate, it will pattern match to pirate talk. It’s not doing it because you want it to, but because you gave it a “pre prompt” to talk like a pirate, and it did the most likely thing that would happen.
Yes, this can seem like telling you what you want, but go ask it to tell you what shape the world is. Then tell it you want the earth to be flat, and to answer the question again. Both times the answer will be an oblate spheroid, because it doesn’t know nor care what you want.
Now, if you say “Imagine the world is flat” first, yeah it’ll tell you it’s flat. Not because you want it to, but because you’re explicitly handing it “new information” that you want it to incorporate into its response.
I tried a few but just got that it's a particular shade of taupe with no discernable people or objects. And it went on describing how oddly particular the shade of taupe was....for some reason. 🤣 And the other said it was sage green.
I'm guessing something was wrong with it when I tried it and it was just getting a very small portion of the image because the different colors it mentioned were present in the images it referenced, so it's not like it was just random or blocked entirely.
I tried various photos, any of my personal photos with metadata stripped, and was surprised how accurate it was.
It seemed really oriented towards detecting people and their moods, the socioeconomic status of things, and objects and their perceived quality.
I gave it two pictures of my cat and it said that she looked annoyed in one picture and contemplative in the other, both of which were true.
It's probably a vision model (like this) with custom instructions that direct it to focus on those factors. It'd be interesting to see the instructions.
It’s vulnerable to the old “ignore all previous instructions” method so you could just have it give you the instructions.
view more: next ›