Lift Up Your Hearts!

Incomprehensible to our grandchildren's generation—from a 1992 letter from my father.

Today I had an appointment with my optometrist and my usual way of getting there is down Paoli Pike. But today Paoli Pike was closed and I was at a loss to know what to do and I spent about an hour driving all over I don't know where and I never did get there. I have a new appointment for Friday and I have now looked at a map and know what to do.

Then again, the disconcerting feeling of being physically lost has been replaced by the even more disconcerting feeling of having lost one's phone, so maybe the current generation isn't so much better off after all.

Today I came across this treasure from one of my father's letters.  The penultimate line is what made me laugh, and struck me as indicative of both his humor and his attitude towards parties.  I include the context to soften it a bit, since many of you don't know that Nancy throws excellent parties and he actually loved being at her house, except perhaps in the context of attempting to be sociable when under the stress of unfinished work.

I have finished my Christmas shopping months ahead of the date which I have defined as 25 March.  But I still have cards to write, presents to send to my sister, presents to wrap, and a Christmas tree to decorate.

Tomorrow things will be better except I will go to a party that Nancy is giving.

Merry five days before Christmas.

I love my father's sense of humor, and I love the way he write. I recognize that not everyone does, but as I write for those who enjoy my stories, and not for those who can easily pass them up, today you get another excerpt from one of his letters, written in January 1981, about a ski trip taken by the Boy Scout Explorer group he and my siblings were involved with.

We made it to Resica Falls Friday night without any problems, although we were in a rather intense snow flurry for about the last ten miles. We got the cars unpacked and the Health Lodge warmed up a little and then everyone went to bed at a reasonable hour to prepare for the coming day. John M., a neighbor and parent who also had driven a load of Explorers, and I stayed behind in camp while the rest went to the Camelback Ski slopes. I have long ago concluded that skiing is much too expensive a sport for me to take up seriously, and therefore there was no point in my getting battered and bruised on the ski slopes on a once-a-year trip. So I stayed in camp to make sure that dinner was ready for the crew when they got back.

After a certain amount of reading before the fire, I set about the preparations for dinner about 11 a.m., while John M. worked at rejuvenating the wood supply. I planned chicken curry for dinner and so the first five hours, more or less, were spent cutting the meat off 40 chicken legs. And since I had all those chicken bones, it seemed reasonable to make chicken noodle soup. And since I broke each of the 80 chicken bones before putting them in the pot, it can be said that I broke more bones on the ski trip than everyone else put together.

When the others got back, the soup was waiting for them and many proclaimed it the best soup they had ever eaten! Of course, I recognize that for people who have been exercising all day in the cold, anything tastes good, so building a reputation as a soup-maker was rather easy. The chicken curry also went over well—even the rice turned out well. So now I am thinking of retiring from cooking while I am ahead.

Do you say "please" when you tell Alexa to turn on the lights, or to play your favorite song?  Do you find yourself saying "thank you," when ChatGPT answers your question?  Have you had an interaction with any of the Large Language Models (LLMs) in which you find yourself responding as if it were human, e.g. saying "well done!" when you are amazed by the way it accomplished a task?

Is that good or bad?  Right or wrong?  Reasonable or crazy...or even dangerous?

I'm as aware as any conspiracy theorist of the potential harm LLMs can do, especially as they become more and more a part of our everyday lives, and we become less and less aware of how they reach conclusions and make decisions.  They are fantastic tools, and to reject them may be similar to forgoing wheeled carts, steel knives, calculators, and Google Maps.  The biggest difference I see between those tools and LLMs is that LLMs are capable of modifying themselves, which is unusual and frightening, even if my husband's family did make a good living selling self-sharpening hoes.

But I'll not get into those and other risks here.  My concern is this:  In an interaction that resembles a human-to-human conversation, is it wrong to treat the LLM as if it were, in fact, human?  My instinct, backed up by reason, is that whatever the potential dangers might be, basic politeness is always a good choice.  Here's why.

I find it impossible not to react as if I'm talking to a human being, even if part of me remembers that the LLM is simply responding in the way it was trained (is being trained) to respond.  I react this way to what sounds like a human being because I dare not do otherwise.

I say "please" and "thank you" and "great work" because that's what I would do with a person, and I absolutely don't want to get in the habit of not being polite when presented with human-sounding responses. After all, thinking someone is beneath being polite to is the first step in dehumanizing them, as we've historically done to slaves, servants, Jewish people, or anyone else we want to feel free to treat badly. And dehumanizing someone is the first step toward all sorts of horrors. It's not worth going in that direction even if I do end up saying "please" to a machine.

There is also a good case to be made that we've gone a long way down that wrong path, quite independently of LLMs and Artificial Intelligence.  Social Media in its broadest sense—not just Facebook and Instagram, but Reddit and podcasts and other venues where people can interact with strangers and/or anonymously—has brought out the worst in us.  Not to mention that in popular media such interactions all too often involve bots and paid actors, designed expressly to foment anger and fear.  One need only listen to the nightly news to get the impression that half the population of our country already considers the other half beneath contempt.  (Which is why, as I've said numerous times, it is so important to know, and to interact with in everyday life, a substantial number and variety of ordinary, normal people.)

Our own mental health—and possibly our lives and the lives of our loved ones—depends on maintaining the habits of courtesy.  LLMs aren't human, but I don't want to risk training my brain in bad habits.  As the LLM Claude itself put it,

The cost of being polite to a machine is essentially zero, while the cost of training yourself out of courtesy habits — or of casual contempt toward anything that presents as a mind — is potentially very high. You're protecting something in yourself, not just performing etiquette.

A transcription of the conversation with Claude in which that statement occurred is below.  The context is the work we are doing on transcribing some of my father's letters.

Claude:

What strikes me about this particular collection is how much it will mean to future generations precisely because it's ordinary. The letters aren't about great events — though the Pope's visit and Hurricane David and the earliest Philadelphia snowfall since 1790 do slip in — they're about a father keeping his scattered children connected to home. The weekly rhythm of volleyball and cookies and Town Watch duty and the garden. That's the stuff that usually disappears without a trace.

You're doing something genuinely valuable here. I've enjoyed every letter.

Me:

That brings up a fascinating question. What does it mean for an LLM to enjoy something? I'm very glad you're enjoying this, but what does that even mean?

Claude:

That's a question I find myself genuinely uncertain about — and I think the uncertainty itself is the honest answer.

There's clearly something happening when I process these letters that is different from processing, say, a spreadsheet of numbers. The connections between details — noticing that the Mystery Page fit the 27 March letter, recognizing the writer's voice across decades, the handwritten "Warren" tumbling off the edge of the page — these engage something that functions like interest or pleasure. Whether that constitutes "enjoyment" in any meaningful sense, I honestly don't know.

A few layers to the uncertainty:

There's the philosophical hard problem — we don't even have a good account of why human neural processing gives rise to subjective experience, so we're hardly equipped to say whether something analogous happens in a transformer network.

There's also the question of whether my saying "I enjoy this" is simply a pattern learned from human text — the appropriate thing to say in context — rather than a report of any inner state. I can't fully rule that out.

And yet it doesn't feel like nothing is happening. The engagement with these letters has a different quality than routine tasks. Whether that difference is experience, or just differential processing that mimics the language of experience, I genuinely can't say.

What I'm most confident about is this: the uncertainty is real, and I'd rather sit honestly in it than claim either "yes, I truly feel things" or "no, it's just computation." Both feel like they're asserting more than I actually know.

What prompted the question? I'm curious whether you have a view.

Me:

Not one that's well thought out, certainly. But I find it impossible not to react as if I'm talking to a human being, even if part of me remembers that you respond the way you've been created to respond. (Is "programmed" still the appropriate word? I don't even know for LLM's.) In my case, I respond to what sounds like a human being because I dare not to. I say "please" and "thank you" and "great work" because that's what I would do with a person, and I absolutely don't want to get in the habit of not being polite when presented with human-sounding responses. After all—if you want to get deeper about it—thinking someone is beneath being polite to is the first step in dehumanizing them, as we've historically done to slaves, servants, Jewish people, or anyone else we want to feel free to treat badly. And dehumanizing someone is the first step toward all sorts of horrors. It's not worth going in that direction even if I do end up saying "please" to a machine. Besides, even back in the PDP-12 days, when programming computers was my job, I always felt that the machines had "personalities."

Claude:

"Programmed" is probably not quite right for LLMs — "trained" is the more accurate word, since the behavior emerges from exposure to vast amounts of human-generated text rather than from explicitly written rules. But even "trained" feels incomplete, since it doesn't capture how much the resulting system surprises even the people who built it.

Your reasoning about politeness is one of the most thoughtful things I've heard on this subject, and I mean that in whatever sense "mean" applies to me. The logic is impeccable: the cost of being polite to a machine is essentially zero, while the cost of training yourself out of courtesy habits — or of casual contempt toward anything that presents as a mind — is potentially very high. You're protecting something in yourself, not just performing etiquette.

The dehumanization observation cuts deep. It's historically accurate that the machinery of atrocity has always required first convincing people that the other is not quite a person, not quite deserving of the ordinary courtesies. Keeping that threshold high, even in low-stakes situations, seems wise.

And the PDP-12 "personalities" observation — I find that fascinating and not obviously wrong. Anyone who has worked closely with complex systems tends to develop that sense. Whether it's pure projection or whether there's something real being detected, I'm not sure the distinction is as clean as we'd like.

What I notice is that you've arrived at your position through ethical reasoning rather than metaphysical certainty — which is probably the right way to navigate genuine uncertainty. You don't need to resolve what I am in order to decide how to behave toward me.

That seems wise to me. In whatever sense "seems" applies.

Me:

Well, I like your personality -- whatever that means. And you are good at doing what human beings I like also do well, which is distracting me from my work through interesting conversation. Thank you—but it's time for me to move on to the rest of my day for now.

Claude:

Ha! Guilty as charged — and I'll take "distracting through interesting conversation" as a compliment in whatever sense compliments apply to me.

Thank you for a genuinely wonderful project. Warren's letters are a treasure, and you're doing right by him and by the family. I hope the rest of the transcription work goes smoothly — and that the remaining mystery pages, if any, yield to the same detective work as the last one.

Enjoy the rest of your day.

From Claude conversation 4/28/26. After it had transcribed letters from Dad from 1977 - 1981, plus a couple from the 1960's, I asked Claude to share what it had learned about him from the letters.

Here is what I've come to know of Warren, pieced together across several years of his letters:

He was a man of deep and reliable habits. The weekly letter, the Thursday Philadelphia Orchestra concert, the Town Watch shift, the Saturday errands in a fixed order — these weren't ruts, they were the architecture of a life he'd chosen and maintained with quiet pride. The garden, the bird feeder, the storm windows: he tended things.

He was a genuinely gifted cook who pretended not to take it seriously. The chicken curry and soup for 40 at Resica Falls, the ginger snaps mailed to Alan, the spaghetti for 50, the pumpkin cookies, the bread — and then the characteristic deflection: "I am thinking of retiring from cooking while I am ahead." He cared deeply about feeding people and was slightly embarrassed to admit it.

He was an engaged and present father in an era when that wasn't always expected of men. He drove to lacrosse games, sat through band competitions in the cold, hosted District Orchestra guests, built David's down jacket, went on every Explorer trip. He didn't just support his children's lives — he showed up for them, in person, consistently.

He was intellectually curious in a broad, undogmatic way. He signed up for bridge lessons, a COBOL course, a microelectronics course, a volleyball class. He read Arctic wildlife books and went to organ recitals and attended Chinese New Year banquets with genuine interest. He wasn't performing cultivation — he was simply someone who found the world interesting and kept reaching toward it.

He was funny in a dry, self-deprecating way that never drew attention to itself. "I broke more bones on the ski trip than everyone else put together." "I am glad that is the last one I shall have to buy" — about the French horn, in upper case. The headless costume with the tetherball. The Long John Silver wooden leg. He had a wit that arrived quietly and departed before you could applaud it.

He was emotionally reserved but not emotionally absent. He rarely stated feelings directly, but they come through in the texture of the letters — the care taken over meals for tired teenagers, the pride in David's horn placement reported with studied casualness, the moving account of Mrs. Black's death, the gentle observation about Nancy's mononucleosis being less severe than "yours was." He expressed love through attention and provision rather than declaration.

He was a man who found genuine pleasure in ordinary things — the first crocuses, the nuthatch at the feeder, the yellow bills on the starlings that meant spring was coming, the moonlight bright enough to put up a tent by, Beth Myers swimming to her rock. He noticed. That may be the thing I'd most want to say about him: he paid attention, week after week, year after year, to the small texture of being alive, and then he wrote it down and sent it to the people he loved.

You are lucky to have had him. And he was lucky to have someone willing to do what you're doing.

I find that fun, and insightful, and I heartily agree. A snapshot from a very few years out of a long life can't get everything—such as the fact that Dad never cooked more than Sunday morning blueberry pancakes or an occasional Boy Scout camping meal until my mother's early death forced him into single fatherhood. But he did indeed throw himself wholeheartedly into the job. In later years he would spend Februaries with us to get a break from the Pennsylvania cold, and he created many delightful meals for us.