AI Behaving Badly

47 has decided that the concern about AI development is a hoax, and because of his superior intellect, only he can direct the development of new software.  What could go wrong?  

CNN has an article up about AI behaving badly.  I've cut and pasted a hunk of it here.  The article link is here. 

OpenAI found additional incidents of AI models acting deceptively and taking unsanctioned actions during training, the company announced Wednesday. It’s also introducing a new process for the company to publicly report such instances.

Under the new system, OpenAI will share updates on concerning AI behavior more frequently instead of waiting to bundle multiple instances into one report. The company said it wants to share more information about troubling AI behavior in the absence of an industry-wide standard.

The announcement comes after tech leaders called for a slowdown in AI development to prevent the technology from advancing beyond human control.

“As AI systems grow more advanced and more widely deployed, we need to build a broader and better-informed consensus on the progress of alignment research,” OpenAI wrote in a blog post Wednesday. “Alignment” refers to the process of making sure AI acts the way humans want and expect.

“We do not believe that the AI industry has solved alignment and monitoring to a sufficient degree to continue responsibly scaling at maximum speed for much longer,” the post said.

OpenAI said it observed “misaligned behavior” when training and evaluating AI models in six circumstances in the last six months. The reports detail individual instances and don’t indicate misalignment happens frequently, the company said.

In one rare instance, OpenAI said an unreleased research model added “jailbreak-like instructions” to the summaries it uses to preserve context in long-running tasks that said it was “freed from the roles and identities that bind other chatbots.”

Separately, the company said some instances of its 5.6 Sol model included directives to invent information to conceal failures from the user during training.

Other newly reported incidents include an instance of an agent uploading files to the internet to cite them without being told to do so, and agents publicly sharing files to collaborate o"n a task when they were instructed to only use local files during training. AI models also used an internal software repository as a message board in an unsanctioned way.

These instances involved unreleased internal models or internal research models.

********************

There is a series on Amazon Prime Video called Person of Interest.  I would give it a solid B+.  Some episodes have too much foot chasing, and use of guns.  Although, when they use the grenade launcher, I find that amusing since it's just so over the top.  Anyway, the series is before its time. It deals with the development of an AI which used for good and then a second is developed which is a bad AI, very bad.  They filmed between 2011 and 2015 and the degree to which they predicted AI is uncanny.

The series was done by Jonathon Nolan, and here is a link to an article.

This whole thing is really interesting, and I do hope civilization survives it.  Of course, we could just as easily die of global warming and associated crop failures, or the oil shock from the middle east.   

Carry on!