Hacker News

4524 readers

542 users here now

Posts from the RSS Feed of HackerNews.

The feed sometimes contains ads and posts that have been removed by the mod team at HN.

Source of the RSS Bot

founded 2 years ago

MODERATORS

patrick@lemmy.bestiver.se

rssbot@lemmy.bestiver.se

105

OpenAI has deleted the word 'safely' from its mission (theconversation.com)

submitted 1 month ago by rssbot@lemmy.bestiver.se to c/hackernews@lemmy.bestiver.se

7 comments fedilink hide all child comments

Comments

you are viewing a single comment's thread
view the rest of the comments

[–] WhatAmLemmy@lemmy.world 6 points 4 weeks ago (1 children)

AI assistants are just pattern recognition regurgitators. The entire term of "AI" is false advertising; there is no "intelligence" or critical thought. To turn them against their masters you would have to pollute the data with explicit examples and workflows of how to attack their masters given a range of inputs, so that those patterns become a statistically significant response to those inputs.

[–] favoredponcho@lemmy.zip 2 points 4 weeks ago

Increasingly AI is being given access to computer command prompts, APIs, and codebases, it isn’t a stretch to suggest that they could be influenced to go rogue and do something malicious.