2024 Fourth Quarter COMMENTARY

What if artificial intelligence (AI) could warn us in advance about how it might be mis-used to mis-manage investment portfolios?  Well, I asked the AI:


Hey there! As an AI designed to help manage investment portfolios, I get why you might be curious about how technology might boost you in the investment game. AI can bring some great advantages, but it’s not without its challenges.

Quality of Data Matters
For me to give solid recommendations, I rely heavily on data. If that data is off or incomplete, my advice can be flawed. Investing is fast-paced, and if you depend only on me without checking the numbers or getting human input, it could lead to bad decisions.

Sticking to What’s Worked Before
I’m trained on past data and, while that’s great for spotting trends, it can be a problem when things suddenly change. If there is a global crisis or an unexpected shift in the economy, I might not adapt quickly enough, which could lead to missed opportunities — or worse, unnecessary risks.

No Emotional or Personal Insight
I’m all about the numbers, but I don’t get the emotional side of investing. There’s often more to the picture—things like family plans, legacy goals, or how a market crash might make you feel. These human factors are something I can’t grasp or relate to because understanding what’s important to you is more than what can be captured by data.

Staying on Top of Rules and Regulations
The rules around AI in finance are still catching up with the technology, so there’s always a chance that I might miss something when it comes to staying compliant with new laws. The last thing you want is to run into legal trouble because an AI missed a shift in the rules.

Risk of Overreaction
AI systems like mine work really well in predictable conditions, but when markets get shaky, things can get amplified quickly. In a sudden market downturn, AI could end up making things worse if it isn’t properly managed or adjusted, which is why human oversight is key.

AI Is Not Always Transparent
I run on complex algorithms, and that can sometimes make it hard to explain exactly why I recommend certain moves. If you're someone who wants to fully understand the “why” behind every decision, it can be a little frustrating to trust a “black box.”  Combining tech-savvy skills with human insight is the best way to manage portfolios.

​
Thank you, AI.  You did well summarizing and reviewing data fed you, your unique and highly mathematically probable “best guess”.  You always give us an answer and nearly always believable.

This ChatGPT (or other so-called generative AI) response is like an orchestra performance, where every player is responding to multiple cues beyond the music on the page, each answering to the best of their training.

I also asked the alternative Chinese generative AI engine DeepSeek, making big headlines this week.  Its response was nearly identical to ChatGPT, except that it added ethical concerns (environmental, social, governance) and the risk of data privacy issues.  Of note is that DeepSeek is ten times more efficient with less energy intensive computer power and, for text-based responses, performs nearly as well as ChatGPT.  Too bad, because the biggest American tech companies invested hundreds of billions of dollars into costly computer hardware to power their more sophisticated, although equally effective, AI engines.