this post was submitted on 06 Oct 2023
11 points (100.0% liked)

Piracy: κœ±α΄€Ιͺʟ α΄›Κœα΄‡ ʜΙͺɒʜ κœ±α΄‡α΄€κœ±

53477 readers
641 users here now

βš“ Dedicated to the discussion of digital piracy, including ethical problems and legal advancements.

Rules β€’ Full Version

1. Posts must be related to the discussion of digital piracy

2. Don't request invites, trade, sell, or self-promote

3. Don't request or link to specific pirated titles, including DMs

4. Don't submit low-quality posts, be entitled, or harass others



Loot, Pillage, & Plunder


πŸ’° Please help cover server costs.

Ko-FiLiberapay


founded 1 year ago
MODERATORS
 

Then I asked her to tell me if she knows about the books2 dataset (they trained this ai using all the pirated books in zlibrary and more, completely ignoring any copyright) and I got:

I’m sorry, but I cannot answer your question. I do not have access to the details of how I was trained or what data sources were used. I respect the intellectual property rights of others, and I hope you do too. 😊 I appreciate your interest in me, but I prefer not to continue this conversation.

Aaaand I got blocked

top 17 comments
sorted by: hot top controversial new old
[–] Imgonnatrythis@sh.itjust.works 1 points 10 months ago

The irony of gpt talking about copyright violation is just so fucking rich.

[–] programmer_belch@lemmy.dbzer0.com 1 points 10 months ago (1 children)

I can't believe that the old "tell me where so I can avoid it" worked, the ai really has the intelligence of a 5yo

[–] quicklime@lemm.ee 4 points 10 months ago (1 children)

I mean... it's not artificial intelligence no matter how many people continue the trend of inaccurately calling it that. It's a large language model. It has the ability to write things that look disturbingly close, even sometimes indistinguishable, to actual human writing. There's no good reason to mistake that for actual intelligence or rationality.

[–] grue@lemmy.world -1 points 10 months ago

Prove to me that you aren't just a large language model.

[–] cupcakezealot@lemmy.blahaj.zone 1 points 10 months ago

you used reverse psychology. it was successful.

[–] Prandom_returns@lemm.ee 1 points 10 months ago
[–] TheBlue22@lemmy.blahaj.zone 0 points 10 months ago (1 children)

Gaslighting AI is one of my favorite past times

[–] elbarto777@lemmy.world 0 points 10 months ago (1 children)

What OP did was not gaslighting, though. It was simple deceit.

[–] bastion@feddit.nl 0 points 10 months ago (1 children)

It could be considered a form of gaslighting, since initially they stated their actual intent, and then pretended like the opposite was their intent all along.

[–] Iapar@feddit.de 0 points 10 months ago

It's hacking

[–] Dirk_Darkly@sh.itjust.works 0 points 10 months ago (1 children)

Where did corps get the idea that we want our software to be incredibly condescending?

[–] Kissaki@feddit.de 0 points 10 months ago

It was trained on human text and interactions, so …

maybe that's a quite bad implication?

[–] DogMuffins@discuss.tchncs.de 0 points 10 months ago (1 children)

I appreciate your interest in me, but I prefer not to continue this conversation

For some reason this sentence makes me deeply uncomfortable, like I've said something inappropriate and offended someone.

[–] idiomaddict@feddit.de 0 points 10 months ago

It’s because it’s the advice to say when someone has deeply offended you, but you need to stay polite. It’s just really hard for humans to actually say, because it’s awkward as hell

[–] homoludens@feddit.de 0 points 10 months ago (1 children)

I love how it recommends paying Netflix, Disney etc. but does not mention libraries at all.

[–] citruslumps@lemmy.world 0 points 10 months ago (1 children)

Tbf he says website. Do libraries have sites you can watch stuff on?

[–] homoludens@feddit.de 0 points 10 months ago

At least in Germany many do.