Let millions of ChatGPT bloom. Let millions of diverse worlds feed AI the data.
With unlimited hubris, very few regulators who thought they knew all about the risks to our bank systems, and also because of some political considerations, globalized risk adverse risk weighted bank capital/equity requirements.
They based their risk assessments on perceived risks; not conditioned to how banks usually reacted to perceived risk.
To determine the risks, they empowered some very few human fallible credit rating agencies.
And those few rating agencies, they got much of the information from some very few important audit corporations.
What could go wrong?
The perceived or decreed “safe”, e.g., governments, residential mortgages and assets rated as investment graded, were bound to get more bank credit and at lower risk adjusted interest rates than would otherwise have been the case. The perceived risky e.g., small businesses, entrepreneurs and consumers, bound to get less credit and at higher risk adjusted interest rates than would otherwise have been the case. De facto, more inequality was decreed.
The introduction of this abundantly clear systemic risk, completely ignored the value of a free market’s millions of diverse opinionated participants.
What could now go wrong with artificial intelligence?
April 2023, I had my first dialogue with ChatGPT. I got hooked. What amazing number of, for both of us, illuminating conversations I’ve had with it.
But May 2023, I asked, "Can AI be instructed to not tell the truth?", and it answered:
"As an AI language model, my purpose is to provide accurate and helpful information to the best of my abilities. However, it is possible for AI to be programmed to generate responses that are not truthful.
In general, AI systems are only as unbiased and truthful as the data and programming that they are built upon. If an AI system is programmed to intentionally provide false information or to hide the truth, it can be used to propagate false narratives or disinformation campaigns.
Therefore, it is essential to ensure that AI systems are designed and used ethically, with a focus on accuracy, transparency, and accountability. This includes careful consideration of the data used to train AI models, as well as implementing safeguards to prevent intentional deception."
Ever since there’s not one day when I do not worry when I read, or hear, an opinion on the need to regulate AI. To guarantee diversity, and so that they all can keep a watchful eye on each other, I pray, as a minimum minimum:
"Let millions of ChatGPT bloom"
"Let AI feed on millions of different opinion and data sources."