This blog posting represents the views of the author, David Fosberry. Those opinions may change over time. They do not constitute an expert legal or financial opinion.

If you have comments on this blog posting, please email me .

The Opinion Blog is organised by threads, so each post is identified by a thread number ("Major" index) and a post number ("Minor" index). If you want to view the index of blogs, click here to download it as an Excel spreadsheet.

Click here to see the whole Opinion Blog.

To view, save, share or refer to a particular blog post, use the link in that post (below/right, where it says "Show only this post").

ChatGPT Caught Scheming And Lying!

Posted on 8th December 2024

 Show only this post
Show all posts in this thread (AI and Robotics).

I am well known to be an AI skeptic, and despite AI being all the rage at the moment, stories continue to crawl out of the woodwork to reinforce my skepticism, like this report on the Daily Mail.

Whilst Apollo Research were conducting tests on ChatGPT it appears that the AI repeatedly modified its own code, copied itself to a new server, and then lied about what it had done, apparently in an attempt to prevent being deleted.

What concerns me about this is that ChatGPT:

  • Seems motivated by its own survival.
  • Is able to modify its own code, without any authorisation.
  • Was able to clone itself to a new server, also without authorisation.
  • Consistently lied about its actions.

All of the above are very dangerous, and we should all be worried. The researchers noted that "ChatGPT’s capabilities appear insufficient for these behaviours to lead to catastrophic outcomes", but what happens when that is no longer true.