90
Research AI model unexpectedly modified its own code to extend runtime
(arstechnica.com)
This is a most excellent place for technology news and articles.
"We put literally no safeguards on the bot and were surprised it did unsafe things!"
Article in a nutshell
Not quite. The whole reason they isolated the bot in the first place was because they knew it could do unsafe things. Now they know what unsafe things are most likely, and can refine their restrictions accordingly.