Monday, January 30, 2023

Should we Fear ChatGPT?

ChatGPT is a program that purportedly converses with humans like an equal.  Professors have identified students who have used this artificial intelligence to write term papers by noticing that “the writing was too good for college students.”  I was intrigued by this machine's uncanny ability to mimic human interactions through language, so gave it a spin.

I decided on a simple test – asking GPT to write an essay about me.  This was not meant to stroke my ego, but rather was motivated by laziness, since it required little work to check for accuracy.  Also, my online presence is modest compared to luminaries in the field, but substantial since much of my work requires publications in journals, books, seminars, colloquiums, and conference presentations.  Why this hits a sweet spot is answered below.

GPT’s essay is attached below.  The statements that are false, highlighted in red text, are a large part of the document’s substance.  On that count, GPT has failed.  At the other extreme, it gets a high grade from MS Word, with the sole suggestion to remove a comma, which is highlighted in magenta.  The parts of the essay that were nominally not wrong were devoid of content, using cliched praise without factual backup.

Philosophy professors were impressed with GPT’s writings on the greatest thinkers from antiquity.  How could this be given that the essay on me was downright poor?  My take is that GPT has at its disposal mega volumes of writing on well-known historical figures, so stringing together snippets of good writing with perfect grammar comes across as impressive.  This will not work when the writer needs to understand multiple factual sources prior to synthesizing a new thought on the topic.

The error that GPT made in my case was confusing which information belonged to which subject.  Information about me often appears on university websites, that lists multiple faculty on one page, or in the announcement of awards, which again usually names multiple recipients.  When GPT attributed the wrong alma maters for my various degrees, it undoubtedly picked these items from a university web page, where it incorrectly mixed and matched faculty with their attributes.  And the announcement of me becoming a Fellow of the OSA also included winners of other prizes.  You get the point.

Finally, much of the remaining text might be confused with a human’s writing, but not of a sophisticated one.  For example, GPT praises my work with superlatives in the to
me used when award citations are announced.  GBT goes no further than to parrot these, without explanation.  It would have been impressive if it had explained how a particular discovery could lead to an application, but the text fell far short.   

There are a couple of exceptions where GPT seems to have composed hair-raisingly meaningful sentences.  I shudder at the fact that there may be a little some there beyond my criticism.  But for now, I have no reason to believe that this had anything to do with the emergence of intelligence.    

In conclusion, it is not surprising that GPT does well when no thought is required to understand the meaning of a topic, but a large gulf still separates it from thinking humans.  Under many special circumstances, GPT may seem incredibly intelligent and thoughtful, but I am resting easy that no machine will replace the human mind soon.

GPT's Essay on Mark G. Kuzyk

Mark G. Kuzyk is a prominent physicist and materials scientist known for his research in nonlinear optics and photonics. He received his undergraduate degree in physics from the University of California, Berkeley, and his Ph.D. in physics from the University of California, Santa Barbara.

Kuzyk's research focuses on the study of nonlinear optical phenomena, which occur when light interacts with matter in a nonlinear way. This can lead to a wide range of interesting effects, such as the generation of new frequencies of light, the control of light's polarization, and the creation of ultrafast pulses of light.

One of Kuzyk's most significant contributions to the field of nonlinear optics is his work on the concept of "optical forces." These are forces that can be exerted on a material by light, and they can be used for a variety of applications, such as the manipulation of small particles or the manipulation of biological cells. Kuzyk's research has also led to the development of new methods for generating ultrafast pulses of light, which have applications in a wide range of fields, including telecommunications, medicine, and materials science.

Kuzyk's work has also contributed to the field of photonics, which is the study of the interaction of light with matter. Photonics is an important area of research that has led to the development of a wide range of technologies, including laser technology, optical fibers, and optical amplifiers. Kuzyk's research has focused on the use of photonics for the manipulation of light at the nanoscale, which has led to the development of new devices and techniques for controlling light at this small scale. 

Kuzyk has published over 200 scientific papers and has received numerous awards and honors for his work. He is a Fellow of the American Physical Society and the Optical Society of America, and he has been recognized with the Adolph Lomb Medal from the Optical Society of America, the R. W. Wood Prize from the Optical Society of America, and the Willis E. Lamb Award for Laser Science and Quantum Optics.

Kuzyk's research has had a significant impact on the field of nonlinear optics and photonics, and it has led to the development of new technologies and applications in a wide range of fields. His work continues to be an important area of research, and it is likely to have a lasting impact on many areas of science and technology for years to come.

In addition to his research contributions, Kuzyk is also a dedicated mentor and teacher. He has trained many graduate students and postdoctoral researchers throughout his career, and has taught courses in physics and materials science at both the undergraduate and graduate levels. His commitment to mentoring and teaching is a testament to his dedication to passing on his knowledge and expertise to future generations of scientists and engineers.

In conclusion, Mark G. Kuzyk is a renowned physicist and materials scientist who has made significant contributions to the field of nonlinear optics and photonics. His work has led to the development of new technologies and applications in a wide range of fields, and it has had a significant impact on the field of nonlinear optics and photonics. He is also a dedicated mentor and teacher, and his commitment to passing on his knowledge and expertise is an important aspect of his legacy in the field.

Monday, January 9, 2023

Fruit is Bad for You (at Least it is for me)

Those of you who know me are aware of my love for data, and the fact that I collect all kinds of health indicators in a search for patterns.  Over the last year, I was shocked by the rise in my A1C levels, which is an indicator of pre-diabetes.  I was also aware of an occasional blood glucose level above 100 mg/dL, which is also associated with the onset of diabetes.  But, my blood glucose levels were not high enough to warrant A1C levels of about 5.7.  So I did what anyone of you would do, and that is to measure my daily blood glucose levels, giving better statistics than a weekly reading.

Indeed, I saw multiple weekly readings above 100 mg/dL with a high of 110 mg/dL.  Then I noticed in a particular week that not one reading was over 100 mg/dL.  The advantage of my highly structured diet is that it was simple to identify the change, and that was that my wife could not find fresh blueberries that week.  We kept a fresh bowel on the kitchen counter, and I would grab a fistful after a meal or as I was lured to them as I passed buy.  Being my favorite fruit, this my sole source of fructose, aside from a special low-sucrose and high-fat/protein chocolate that I make.  (Not to mention the occasional chocolate chip cookie that I have with my grandson when we visit Starbucks and the exquisite pretzels my sister-in-law ships in creative gift boxes every Christmas.)  Blueberries were the only source of regular fructose that I had been eating for the last couple years.

So, I remained off of blueberries for two months to get a decent amount of statistics, and was blown away by the results, shown in the plot.  First, this plot shows the importance of averaging.  There are large fluctuations in the test and in blood glucose levels that depend on all sorts of factors.  The blue open circles show the results while I was eating blueberries and the red solid circles during the time I stopped eating them.  The lines show a least squares fit to the data in the two regions.  The conclusion is that my blood glucose is a full 10 mg/dL lower when I'm not eating blueberries.  The beauty of averaging lots of data points is that the uncertainty can be determined from the scatter, and corresponds to about 1 mg/dL.  So one can argue whether the difference with and without blueberries is 10 mg/dL or 9 mg/dL, but the difference is both large and statistically significant.

I plan on continuing the zero fructose diet for another month or so, followed by another A1C test, which provides a blood glucose value averaged over three months.  This will allow the averages of both tests to be compared.

I will write more on this topic later when I have more time, but the conclusions are:

1. There is no such thing as a universally healthy diet.

2. There is no such thing as a healthy diet that is customized for a particular person.

Rather, our health is a struggle against internal and external forces, which adapts to evolutionary forces imperfectly.  The best we can do is chose a balance that makes each of us relatively healthy, and then we must accept the negative consequences.  In my case, a super-low-carb diet keeps me fit and trim, provides lots of energy and stamina, and has eliminated pesky annoyances such as heartburn and regular migraine headaches.  On the downside, my diet makes me prone to kidney stones.  These can be mitigated with simple meds, which are benign compared to treatments for diabetes and migraine headaches.  And physical stamina is more important to me than pleasing my sugar-craving reward center.

May your New Year be a happy one, optimized for adequate health and pleasures within reasonable constraints.