Welcome to this edition of The Process, a free weekly newsletter and companion podcast discussing the future of technology and philanthropic work.
If you enjoy reading and listening, please consider subscribing and sharing with your community!
Thank you!
Philip
Over the last four days, my family and I drove our little red RV, Harvey, some 1,800 miles from Richmond, VA to the town of Peñasco, NM. We spent a night in a Walmart parking lot in Lebanon, TN and another beneath giant wind turbines in a dust-blown field in Jericho, TX on Route 66. We met Tony, proprietor of the nonprofit job training cafe, Java Spot, in Brinkley, AR, who wanted a tour of Harvey and chatted with us about the mission of his cafe to reinvigorate the collective imagination of his hometown. This week, these thousands of miles of American landscape helped my thoughts to fall upon all that is offline, all that is beyond the reaches of AI training sets, which is almost everything.
The size of the data sets used to train the latest large language models can be measured in petabytes, which is equivalent to 1,000,000 gigabytes and is enough to hold roughly 12,000 times the amount of text contained in the entire English language version of Wikipedia. While this is a staggering amount of information to assemble and process, this extremely large pile of data is most impressive so long as it is considered on the scale of human endeavors, things made by people, and not according to a broader accounting of things in our world.
One analogy would be to compare AI data sets to great pyramids constructed throughout the ancient world. We marvel at the grandeur of pyramids and admire the ingenuity of those who built them, and yet, if we compare the greatest pyramid to an average hill, our perspective may shift to recognize the modesty of our monuments relative to natural versions not created by our hand.
Without diminishing human achievements, like the innovation of generative AI technology, might we consider our great feats in a truer and more expansive light so as to see beyond our solipsism? Seeing beyond ourselves is not only an admirable practice to cultivate in general, in the case of AI it is also a helpful reminder of all that is beyond these powerful algorithms, and the yawning gap that still separates forms of intelligence arisen from eons of evolution, and those of the last 50 years.
I asked GPT-4, “What does water taste like?”, and this is what it told me:
The taste of water can be quite elusive to describe as it's often considered tasteless in its pure form. However, the perception of its taste can be influenced by several factors including its temperature, purity, mineral content, and the individual's own sensory abilities. Here’s a breakdown of how these factors affect the taste of water:
Temperature:
Cold water is often described as being more refreshing and pleasant to the taste, while warm or room-temperature water might not be as appealing.
Purity:
Pure water, which is H2O with no dissolved substances, is often described as tasteless. However, such purity is rare to come by in everyday circumstances.
Mineral Content:
The mineral content in water, such as calcium, magnesium, or sodium, can significantly affect its taste. For example, hard water, which has high mineral content, may taste metallic, alkaline, or even slightly sweet. In contrast, soft water with lower mineral content may taste salty or may still be described as tasteless.
Individual Sensory Abilities:
People have different levels of sensitivity to tastes, and individual sensory abilities can significantly affect how one perceives the taste of water. For instance, some individuals might be more sensitive to the metallic taste of minerals in hard water, while others may not notice it as much.
Other Dissolved Substances:
Other substances dissolved in water like chemicals from treatment processes or contaminants can also affect the taste. For instance, chlorine used in water treatment can give water a bleach-like taste, while organic matter or algae can create musty, earthy, or fishy tastes and odors.
pH Level:
The pH level of water, indicating its acidity or alkalinity, can also impact taste. Water that's more alkaline may taste bitter, while acidic water may have a sour taste.
TDS (Total Dissolved Solids):
The level of Total Dissolved Solids (TDS) can alter the taste of water. Higher TDS often contributes to a stronger taste, which could be salty, bitter, or metallic depending on the specific solids present.
Local Environmental Factors:
Environmental factors and local treatment processes can contribute to the unique taste of water in different geographic locations.
The taste of water is a complex interplay of its inherent characteristics and individual perceptions, which can make it a unique experience for each person.
Pretty thorough! Water here in the piñon covered hills of Peñasco tastes dry, a bit dusty, and precious. It tastes that way, not because of all the factors GPT-4 enumerated, but because I’m the one drinking it and describing it to you. I can’t even begin to imagine the “data set” I’m drawing upon, the infinitesimally intricate firing of my nervous system, the seamless fusion of information from all of my senses interlaced with subconscious memory of waters I’ve imbibed before, and the subtle euphoria of quenching thirst.
If a simple sip of water can contain that much information, try for a moment to stretch your imagination to consider the volume of humanity’s combined experience, and then further to what’s beyond our comprehension, conscious or otherwise. The sum is unimaginable, at least for me.
What I am able to grasp is my smallness in comparison to all of this, and this recognition has always been comforting for me. It’s comforting because zooming out lumps all of us together. The perceived differences between the greatest and the least of us is negligible on this scale of consideration. I’m small, but not in comparison to another person or a new technology on the rise.
None of this is to say things aren’t changing for us, and changing quickly. Rather, it is a reminder that this change takes place within a narrow field of view we sometimes forget to widen. We have the remarkable ability to live within either of these perspectives, to move back and forth between them, and we should practice this to build awareness of when each serves us.
It is important to understand how technology like generative AI is reshaping many of the ways we live and work, and how quickly this is happening. Discomfort with change can cause us to put up all kinds of defenses, like demonizing or dismissing new things we don’t yet understand. So, when the pace gets to be too much, don’t check out, zoom out instead. As everyone is gazing up at the latest pyramid society is constructing, look over at the timeless hills, and better yet climb it if you’re able to.
2023 Fundraising.AI Virtual Global Summit
Please check out the upcoming 2023 Fundraising.AI Virtual Global Summit taking place on October 23 and 24, 2023, which is free to register and I hope many readers will participate.
The Summit will virtually bring together more than 30 speakers to facilitate numerous tracks of thoughtful discussion, and for all of us to build this community as a force for good. Please join us!
Thanks for reading this edition of The Process. Please share and comment or you can email me at philip.deng@grantable.co
Philip Deng is the CEO of Grantable, a company building AI-powered grant writing software to empower mission-driven organizations to access grant funding they deserve.