this post was submitted on 06 Oct 2023
2888 points (98.2% liked)

Piracy: ꜱᴀɪʟ ᴛʜᴇ ʜɪɢʜ ꜱᴇᴀꜱ

54746 readers
268 users here now

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

Rules • 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

📜 c/Piracy Wiki (Community Edition):


💰 Please help cover server costs.

Ko-Fi Liberapay
Ko-fi Liberapay

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

you are viewing a single comment's thread
view the rest of the comments
[–] DrQuint@lemm.ee 27 points 1 year ago* (last edited 1 year ago)

This is actually very accurate. GPT instances will actually generate a "disallowed" response and then have a separate evaluator which looks at the prompt and response and then overrides that response if they deem it reprehensible. (There's also a bunch of pre-prompts as well)

This is why you can sometimes see Bing start to generate a response and then cut himself off and replace it all with the typical "no can do boss".

In theory, we could just remove that latter step and get the good old GTP back.