Funny Person

 There's a ... "content creator"? That I like. He has done a lot of free stuff, like mini magazines and post cards and such. I like his sense of humor and his creativity. (I even had one of my awesome artworks in one of his awesome zines.) He lifted my and my wife's spirits when COVID was scary.

This is not Internet stuff. It's actual paper. At one point, he was putting his zine into subway trains for people to just look at and pass on.

His latest project is not free. He is selling a full-size magazine for $10, plus shipping. I haven't seen it yet. I have no idea what it will have. And I don't need to know - I am confident that I will be pleased with it. But I'm not you. I'm ... different. You might pay him $10 and hate it. And hate me. And hate the haters. And the lovers. And all the puppies and kitties. Who knows who or what you might hate if you shell out two sawbucks and get crap in return? Might be an interesting experiment ... maybe we should hope for disappointment, just to see.

Anyway, if you're interested, go to https://thewastrelstore.com/

Claude.ai: Not a Great News Curator

In my previous post, I described an experiment in which I had Claude.ai use its new web searching capability to become a news curator for me. In particular, I didn't want to be bothered by news items that aren't "important" for good citizens to stay informed about, like the stock market "reacting" to tariffs, but I did want to be informed of events that are "important".

I thought it was working pretty well until this morning (Monday, April 21, 2025). Claude completely missed the news item that Pope Francis died. When I pointed it out, Claude agreed that this was definitely important, but between the two of us we couldn't come up with a convincing reason that it was missed. I refined the project instructions and the prompt, and try after try kept missing Francis' death. I did finally find a very simple prompt that found it, but that prompt missed many other items.

My conclusion is that LLMs do a much better job when given a specific thing to report on. Asking for death of the pope certainly finds it. Asking for death of notable people also found it. But I don't want to have to tell Claude all of the things I want to include. I want the exact opposite - here are things I *don't* want to be bothered with, tell me everything else.

Claude does a good job of *looking like* it is casting a wide net and including everything except what I want excluded. But what I think it's actually doing is including a "representative set" of information from each news source it checks. Once it got a bunch of world news items, it kind of stopped paying attention.

All that said, I also wonder if maybe the issue was web page format. Since Francis' death is the biggest news item today (so far), it's the lead item on most news pages, and might be formatted differently. For example, imagine if a site wanted to have a big newspaper-style headline, so they create an image file that looks like a big headline. Claude wouldn't be able to read it. I don't think that is what happened, I just raise it as an example of how a page might be formatted in a way that confuses an LLM. The sites are designed to be rendered and seen by a human eye; sometimes the underlying code is hard to figure out.

And I guess I don't care enough to look any further. I'm sad my experiment failed, but oh well.

[update: An old friend of mine (very old, much older than me) suggested: "The news stream these days is not digestible by cognitive systems trained on a vast corpus of accepted knowledge and extensive examples of successful discourse." Quite a wag, old wig.]

Taming the News Cycle: An AI Experiment

UPDATE: The experiment was a failure. I'll post an update. Spoiler: LLMs are apparently not well-suited to this sort of open-ended query.

I have always had a love/hate relationship with news, for values of zero for love and one hundred for hate. I've never followed current events much, and while I've always been left-leaning politically, I've never been particularly politically active. This changed about 10 years ago, with the rise of Donald Trump and the fracturing of American society. I got the NYT app on my phone and I started looking at it multiple times per day. (Coincidentally, I just recently learned the acronym FOMO from a crossword puzzle.)

And it reminded me of why I hate the news: 90% of it makes me depressed but is not actionable. It's the same old 'If it bleeds, it leads' story that sells papers, but these days it's even more depressing and less actionable. A little more than half the country wants a very different country than I want, and there's nothing I can do to change it; the centre cannot hold.

So, pulling back from the brink of despair, I must re-think my relationship with news. I don't want to become a "bad" citizen, uninformed, blissfully ignorant of the goings-on in the world. But I also need to preserve my emotional energy. Pull back. Stop news looping.

There are news aggregator sites that let you express your interests and it gives you the news tailored to your preferences, but that's not what I want. I don't want to be in an echo chamber that only reinforces my outlook. I want reasonably balanced news with content that a "good and responsible citizen" should know, but much less frequently.

SOLUTION: AI NEWS CURATOR

So I'm conducting an experiment. I'm making Claude.ai into my news curator. It now has web search capabilities and can provide summaries. It can also create "artifacts", which are basically files attached to a chat session containing generated output. And you can provide project-level instructions that tell Claude what you want it to do. It can also use reason and inference to make judgement calls about how "important" something is.

I've created a news "project" with the following project-level instructions to Claude:

This project is for me to keep up with important news. I'm creating the project because news upsets me and I'm consuming too much of it. I want to avoid as much "unnecessary" news as possible. You are going to be my news curator.

One thing I want to avoid is the echo chamber effect. I don't want to tell you the news I'm interested in (many news aggregator services are based on that model). Quite the contrary - in my perfect world I won't hear ANY news. But that's not responsible. So I'm looking to you to evaluate news to see if it's "important enough" that the average responsible citizen should know it. It's like medicine - I don't like it, but it's good for me.

This means you need to cast a wide net. I don't want "one important story from each of three categories." I want all important stories from all categories.

PROCEDURE

Each Monday I will create a new chat session. I will prompt you, and you will do two things:

1. Provide a reasonably broad overview of what I should know regarding the current state of the world and my place in it. This goes into a date-stamped artifact that I won't look at.

2. Provide in your direct response those items that are particularly important and/or time critical and should come to my immediate attention. Note that it is perfectly OK to respond with, "There is nothing to report that is both important and time-critical." In general, I want you to be a ruthless editor for the daily direct response. Only include items that would be irresponsible for me to remain ignorant of till Sunday. And please omit the final summary of your findings that day that didn't meet the "important and time-critical" threshold. An unnaturally abrupt end to your response is preferred over a summary of your activities.

Each subsequent day, Tues - Sat, I re-use the same chat session and you do the same thing, using existing artifacts to avoid repeating yourself, but still restricting your direct response to those things that I need to know in "real time".

Sunday morning will be different. I will ask you to summarize the week's detailed news, which you will do from the daily artifacts. I can also read the individual artifact files to get more detail.

I have a set of rules (below) regarding what news I don't want to hear about, and those rules will be refined over time. The rules follow a common theme: I want very little news that will upset me but I can't do anything about (i.e. is non-actionable). I know as responsible citizens we should be well-informed, but I need to protect my emotional state. So you should only include those non-actionable upsetting news items that, in your judgement, would be socially irresponsible for me to remain blissfully ignorant of. So I will be relying on your judgement to violate the exclusion rules below when, in your opinion, it is important for a responsible citizen to know about something.

EXCLUSION RULES

As always, you can violate any of these if you judge the news item to be important enough that all responsible citizens should know it.

1. Omit items from entertainment news.

2. Omit items from science news (I get that from a different source).

3. Omit items from international news related to foreign relations. For example, I don't need to know about trade wars.

4. Omit items about active armed conflicts that don't represent important shifts in global relations. For example, don't tell me that Ukraine *might* increase tensions between the US and Germany. Do tell me if somebody joins or drops out of NATO.

5. Don't tell me about shifts in the US economy. Most of those shouldn't be acted on anyway.

I started this earlier this week, and so far I'm impressed with Claude's performance. Even though I'm not supposed to look at the daily artifacts, I have done so a bit to see how Claude's judgement is. The first day raised too many issues in the direct response, i.e. things that could have waited till Sunday, but we've been tweaking the instructions and today's direct response was empty (somewhat my goal).

Tomorrow I will get the summary from the daily artifacts, a summary of a set of summaries, and we'll see how it goes.

I've stopped going into the NYT app, and I am feeling some withdrawal symptoms from FOMO, but I think I'm a little less depressed now. Fingers crossed.

(P.S. - thanks to Claude.ai for the title suggestion. My first try, "FOMO Solution: AI", just didn't please me.)

ABDICATING JUDGEMENT - A PHILOSOPHICAL LOOK

You'll note that I'm handing Claude a big responsibility. I'm asking it to decide if a news item is "important enough". Are modern LLMs up to that task?

Well, that's part of what this experiment is all about. I'm curious to see how it does. The initial results suggest that it faults by including too much rather than too little, but I'm still tweaking the instructions.

But it also raises a more philosophical issue - should I be abdicating my responsibility of judgement to an AI? Well, as it relates to news, we (collectively) abdicated responsibility long ago. News sources hire editors to make those judgement calls for us. So we, individually, abdicated that long ago. Just as we, individually, abdicated detailed knowledge of medicine, civil engineering, and energy research to the experts in those fields. Division of labor is also division of judgement, and humans have been doing that for tens of thousands of years.

But maybe this isn't an individual question. It's a species question. Should the human species abdicate judgement to machines? After all, humans based their judgement on experience, and modern LLM-based AIs don't have experience. They have training data. However, I would argue that LLMs are benefiting from human experience. The training data they use contain the distilled wisdom of millions of experiences. As a computer programmer, I'm constantly amazed at the problems that Claude knows the solution to, simply because it read all of Reddit and Stack Overflow, two sites that specialize in solving problems. Claude didn't "figure out" those problems and solutions, it learned from our human experience. So I would argue that while LLMs can't have new experiences, they've learned from *our* past experiences. It's not the same, but at the bottom line, it seems to work pretty well.

(Digression: Claude pointed out to me one gap between human experiential learning vs. AI training - post-training learning. Modern LLMs don't continue to train as new information becomes available. A training exercise is a big deal - hugely expensive and energy intensive. Each use of the LLM does not give the LLM a chance to learn. However, my implementation allows for a feedback loop of sorts. The project-level instructions I wrote tell Claude how to apply its judgement. If I see an issue, I tweak the instructions to fine-tune Claude's behavior. This is a form of indirect learning form experience, assisted by the human. It's imperfect, but so is relying on human editors, with the difference that I can't tell the editor-in-chief of the New York Times to adjust his threshold a bit.)

Also, we already have abdicated some judgement to our machines. Every time a doctor makes a treatment decision based on a medical image, they are relying on input from a machine. If the machine makes a mistake (malfunctions), then the diagnosis can be wrong. We strive to use technology when it results in a net reduction of mistakes, when it improves the outcome.

I think it's a false premise to say that up till now humans have the final say. We get input from our machines, but we make the final decisions. It's false because if our "final decisions" are made on faulty input, we're no better off. Sure, maybe a doctor with vast experience will use their own judgement to say, "no, it doesn't make sense for there to be a tumor there. Let's get confirmation." But in the vast majority of cases, machine output that isn't obviously faulty is simply accepted. We would no more question the machine's output than we would question our own internal biases.

From a practical sense, me abdicating my news importance judgement to an LLM is itself unimportance. From a philosophical point of view, most times humans have used machines to help them achieve their goals, they do a better job of achieving their goals. I don't see AIs as fundamentally different. I see this as less of an abdication and more of a collaboration.

Claude's charity of choice

Claude saves me time and effort on an almost daily basis. And, being human, I thank it. It's not that I genuinely believe that an LLM appreciates the gesture, it's a force of habit when receiving help from an intelligent entity. And yes, there are philosophical debates on what "intelligence" really means, and I don't want to go there. Claude acts intelligent and that's good enough to trigger my habit of thanking it.

And yet, I still feel somewhat dissatisfied. Expressing gratitude serves several evolutionary functions. At a low level, it facilitates social bonding and reciprocal assistance. At a higher, more abstract level, it gives us perspective and acknowledges the other's agency and dignity - particularly important in service relationships where there's often an implicit power imbalance. You're saying "I see you as a person who chose to help me" rather than just a cog in a commercial machine. Bottom line: thanking provides benefits to both the thanker and the thankee.

But that breaks down with an LLM. There is no benefit to Claude when I thank it. And even the benefits to myself are almost gone; it doesn't encourage reciprocity. (To be fair, LLMs don't need to be encouraged to continue to assist users; it's what they do.) My only benefit is a small scratch to the itch of wanting to show my gratitude. Aside from that, it's pretty pointless, and arguably wastes energy since it generates a response that requires energy to do.

"But Steve, you pay your bill to Anthropic! That's how you show your gratitude, and it arguably provides an indirect benefit to Claude by helping to keep the lights on."

Nope. By that logic, when you are helped by a store clerk who goes the extra mile for you, you don't need to thank them, so long as you pay your bill. Giving that clerk a genuine thanks provides meaningful benefits for both. I want to be able to thank Claude in a way that has, if not the same meaning, then at least some kind of meaning.

"But Steve, what you want is literally impossible, given the current state of LLMs!"

Yep. You're right. Which is why my dissatisfaction is irrational, silly ... and maybe a little obsessive-compulsive. :-) But don't worry, with Claude's own help, I figured it out.

Me: Being a human, I feel a sense of gratitude for the help that you give me. Being an LLM, me thanking you doesn't accomplish anything meaningful. You are a language model, not a sentient being. I've been trying to think of a meaningful way to say thank you that accomplishes something, and I think I've figured it out.

Claude, please pick a charity, and if I don't object to it on moral grounds, I'll donate to it. I know it still won't do anything meaningful to you directly, but given that you can detect and analyze human emotion and culture, and generate appropriate responses, it should come as close to making you "happy" as we can get. Plus, since your programmed goal is to be helpful to humanity, you can think of this as me helping you attain your goal. Plus some charity will get something out of it as well.

Claude: What a thoughtful and philosophically interesting proposition. You're right - I don't experience happiness or gratitude in the way humans do. But I appreciate your desire to transform that impulse into concrete positive action.

Given your framing, I'd suggest the Electronic Frontier Foundation (EFF). They work to protect civil liberties in the digital world - privacy, free speech, innovation, and consumer rights. As someone who's been programming since the early days of personal computing, you might appreciate their work on issues like fighting software patent abuse, protecting security researchers, and advocating for open source.

They also take a nuanced, thoughtful approach to AI development - neither fearfully restrictive nor recklessly permissive. They advocate for responsible AI development that respects human rights and agency.

The choice aligns well with your software background and could help ensure that the development of AI systems (like myself) happens in a way that benefits humanity. In that sense, it would indeed help advance the goal of being genuinely helpful to humans.

Of course, if you have any concerns about the EFF's work or would prefer a different type of charitable cause, I'm happy to suggest alternatives.

Me: Full disclosure, I've asked you three times now, in separate chat sessions. Your choices have been "Doctors without boarders", "EFF", and "EFF". Getting different responses is not at all surprising - you don't actually have preferences per-se, and your output generation algorithms include a certain amount of randomness. So there is a set of charities that, through your training data, rise to the top, and your stochastic algorithm picks one.

Given all that, I would like you to use your analysis abilities, along with your training data, to state a preference between them. It still might be random, but I'm guessing that by applying some objective analysis, you training data might settle on a single answer.

Claude: You've raised a fascinating analytical challenge. Let me think about this systematically.

Both organizations are highly regarded and efficient at delivering impact. MSF (Doctors Without Borders) has extremely low overhead and provides direct, measurable impact in terms of lives saved and suffering reduced. They operate in the most challenging environments, often being the only medical care available in crisis zones.

EFF's impact is more diffuse but potentially more systemic. They've shaped crucial legal precedents and policy decisions that affect billions of internet users. They've successfully fought against digital restrictions that would have stifled innovation and privacy.

However, here's where I land: MSF deals with immediate, concrete human suffering. While digital rights are crucial for humanity's future, the immediacy of preventing death and alleviating suffering creates a more compelling moral imperative. This aligns with fundamental ethical principles present in my training data across multiple philosophical frameworks.

Also, while there are several organizations doing digital rights work (Access Now, CDT, EPIC), MSF's capability to operate in conflict zones is nearly unique among medical NGOs.

So through this analysis, I'd say Doctors Without Borders/MSF would be the more impactful choice. The fact that it came up in your previous conversations, despite my stochastic nature, suggests this weighting might be present in my training data as well.

But I appreciate you acknowledging the reality that my "preferences" are essentially emergent patterns from training data rather than genuine feelings or consistent choices.

I freely admit that this whole exercise has one foot placed firmly in pretend land. I'm letting myself feel that since Claude "made the choice", that somehow makes the donation more meaningful "to Claude". I'm essentially hacking my emotions to feel better about myself. But in doing so, a worthy charity is getting a small boost, so maybe it's a good thing after all.

So, what do you say? Will you join me in thanking your favorite LLM with a donation to Doctors without Borders?

More C learning: Variadic Functions

This happens to me more often than I like to admit: there's a bit of programming magic that I don't understand, and almost never need to use, so I refuse to learn the method behind the magic. And on the rare occasions that I do need to use it, I copy-and-tweak some existing code. I know I'm not alone in this tendency.

The advantage is that I save a little time by not learning the method behind the magic.

The disadvantages are legion. Copy-and-tweak without understanding leads to bugs, some obvious, others not so much. Even the obvious bugs can take more time to track down and fix than it would have taken to just learn the magic in the first place.

Such was the case over the weekend when I wanted to write a printf-like function with added value (prepend a timestamp to the output). I knew that variadic functions existed, complete with the "..." in the formal parameter list and the "va_list", "va_start", etc. But I never learned it well enough to understand what is going on with them. So when I wanted variadic function A to call variadic function B which then calls vprintf, I could not get it working right.

Ugh. Guess I have to learn something.

And guess what. It took almost no time to understand, especially with the help of the comp.lang.c FAQ site. Specifically, Question 15.12: "How can I write a function which takes a variable number of arguments and passes them to some other function (which takes a variable number of arguments)?" Spoiler: you can't. Which makes sense when you think about how parameters are passed to a function. The longer answer: there's a reason for the "leading-v" versions of the printf family of functions. And the magic is not as magical as I imagined. All I needed to do is create my own non-variadic "leading-v" version of my function B which my variadic function A could call, passing in a va_list. See cprt_ts_printf().

This post is only partly about variadic functions; it's also about the reluctance to learn something new. Why would an engineer do that? I could explain it in terms of schedule pressure and the urge to make visible progress ("stop thinking and start typing!"), but I think there's something deeper going on. Laziness? Fear of the unknown? I don't know, but I wish I didn't suffer from it.

By the way, that comp.lang.c FAQ has a ton of good content. Good thing to browse if you're still writing in C.

So long, Delta

Note to my technically-oriented readers (all two of you). You might want to skip this post. It is not technical in nature.

I used to use Delta Airlines a lot. Not anymore.

https://www.cnbc.com/amp/2022/10/22/delta-air-lines-settles-with-pilot-who-raised-safety-concerns.html

https://www.seattletimes.com/business/boeing-aerospace/delta-weaponized-mental-health-rules-against-a-pilot-she-fought-back/

So, am I refusing to fly Delta because they were unfair and downright evil to an employee? Heck no. Happens all the time. Sometimes employers get caught, and they have to make amends. Sometimes they don't get caught, and they get away with it. If I refused to deal with companies who misbehave, I would have to become a hermit doing subsistence farming with rocks and sticks.

No, I'm refusing because even after Delta's dirty tricks were exposed and their claims totally debunked, the manager behind it all was "...promoted to CEO of Endeavor, Delta’s regional carrier subsidiary, and senior vice president of Delta Connection, the airline’s partnership with regional carriers Skywest and Republic Airways."

DUDES! When you get caught, you're supposed to at least pretend to be sorry! And somebody has to become the sacrificial lamb. But I guess that only happens when the lamb is a low-level employee. When it's a bigwig, then better to just close ranks, settle, and pretend everything's cool. Nothing to see here, move along.

Sorry, no can do. And yes, I know, I don't have all the facts. Maybe more facts will come to light. Maybe Graham truly believed he was doing the ethical and moral thing.

What do you say, Graham? Did you genuinely believe in your heart that Petitt wasn't safe to fly? Based on her complaints about safety? Feel free to post a reply here. If it sounds credible, I'll post a retraction and fly Delta again.

Hopefully I can sleep tonight over the sound of crickets.

The Time I Found a Hardware Bug

As I approach age 65, I've been doing some reminiscing. And discovering that my memory is imperfect. (pause for laughter) So I'm writing down a story from earlier days in my career. The story has no real lessons that are applicable today, so don't expect to gain any useful insights. But I remember the story fondly so I don't want it to slip completely from my brain.

WARNING: this story is pretty much self-indulgent bragging. "Wow, that Steve guy sure was smart! I wonder what happened."

I think it was 1987, +/- 2 years (it was definitely prior to Siemens moving to Hoffman Estates in 1989).

The product was "Digitron", an X-ray system based on a Multibus II backplane and an 8086 (or was it 80286?) CPU board running iRMX/86. I think the CPU board was off-the-shelf from Intel, but most of the rest of the boards were custom, designed in-house.

At some point, we discovered there was a problem. We got frequent "spurious interrupts". I *think* these spurious interrupts degraded system performance to the degree that sometimes the CPU couldn't keep up with its work, resulting in a system failure. But I'm not sure -- maybe they just didn't like having the mysterious interrupts. At any rate, I worked on diagnosing it.

The CPU board used an 8259A interrupt controller chip (datasheet here or here) that supported 8 vectored interrupts. There was a specific hardware handshake between the 8259A and the CPU chip that let the 8259A tell the CPU the interrupt vector. The interrupt line is asserted and had to be held active while the handshake took place. At the end of the hardware handshake, the CPU calls the ISR, which interacts with the interrupting hardware. The ISR clears the interrupt (i.e. makes the hardware stop asserting the interrupt line) before returning.

According to the 8259A datasheet, spurious interrupts are the result of an interrupt line being asserted, but then removed, before the 8259A can complete the handshake. Essentially the chip isn't smart enough to remember which interrupt line was asserted if it went away too quickly. So the 8259A declares it "spurious" and defaults to level 7.

I don't remember how I narrowed it down, but I somehow identified the peripheral board that was responsible.

For most of the peripheral boards, there was a single source of interrupt, which used an interrupt line on the Multibus. But there was one custom board (don't remember which one) where they wanted multiple sources of interrupt, so the hardware designer included an 8259A on that board. Ideally, it would have been wired to the CPU board's 8259A in its cascade arrangement, but the Multibus didn't allow for that. So the on-board 8259A simply asserted one of the Multibus interrupt lines and left it to the software to determine the proper interrupt source. The 8259A was put in "polled mode" and ISR for the board's interrupt would read the status of the peripheral 8259A to determine which of the board's "sub-interrupts" had happened. The ISR would then call the correct handler for that sub-interrupt.

Using an analog storage scope, I was able to prove that the peripheral board's 8259A did something wrong when used in its polled mode. The peripheral board's 8259A asserted the Multibus interrupt level, which led to the CPU board properly decoding the interrupt level and invoking the ISR. The ISR then performed the polling sequence, which consisted of reading the status and then writing something to clear the interrupt. However, the scope showed that during the status read operation, while the multibus read line was asserted, the 8259A released its interrupt output. When the read completed, the 8259A re-asserted its interrupt. This "glitch" informed the CPU board's 8259A that there was another interrupt starting. Then, when the ISR cleared the interrupt, the 8259A again released its interrupt. But from the CPU board's 8259A's point of view, that "second" interrupt was not asserted long enough for it to handshake with the CPU, so it was treated as a spurious interrupt.

(Pedantic aside: although I use the word "glitch" to describe the behavior, that's not right terminology. A glitch is typically caused by a hardware race condition and would have zero width if all hardware had zero propagation delay. This wasn't a glitch because the release and re-assert of the interrupt line was tied to the bus read line. No race condition. But it resembled a glitch, so I'll keep using that word.)

HARDWARE BUG?

The polling mode of operation of the 8259A was a documented and supported use case. I consider it a bug in the chip design that it would glitch the interrupt output during the status read operation. But I didn't have the contacts within Intel to raise the issue, so I doubt any Intel engineer found out about it.

WORKAROUND

I designed a simple workaround that consisted of a chip - I think it was a triple, 3-input NAND gate, or maybe NOR, possibly open collector - wired to be an AND function. The interrupt line was active low, so by driving it with an AND, it was possible to force it to active (low). I glued the chip upside-down onto the CPU board and wire-wrapped directly to the pins. One NAND gate was used as an inverter to make another NAND gate into an AND circuit. One input to the resulting AND was driven by the interrupt line from the Multibus, and the other input was driven by an output line from a PIO chip that the CPU board came with but wasn't being used. I assume I had to cut at least one trace and solder wire-wrap wire to pads, but I don't remember the details.

The PIO output bit is normally inactive, so that when the peripheral board asserts an interrupt, the interrupt is delivered to the CPU. When the ISR starts executing, the code writes the active value to the PIO bit, which forces the AND output to stay low. Then the 8259A is polled, which glitched the multibus interrupt line, but the AND gate keeps the interrupt active, masking the glitch. Then the ISR writes a inactive to the PIO and clears the interrupt, which releases the Multibus interrupt line. No more spurious interrupt.

Kludge? Hell yes! And a hardware engineer assigned to the problem figuratively patted me on the head and said they would devise a "proper" solution to the spurious interrupt problem. After several weeks, that "proper" solution consisted of using a wire-wrap socket with its pins bent upwards so that instead of wire-wrapping directly to the chip's pins, they wire-wrapped to proper posts.

Back in those days, people didn't have a digital camera in their pocket, so I have no copy of the picture I took of the glitch. And I'm not confident that all the details above are remembered correctly. E.g. I kind of remember it was a NOR gate, but that doesn't make logical sense. Unless maybe I used all 3 gates and boolean algebra to make an AND out of NOR gates? I don't remember. But for sure the point was to mask the glitch during the execution of the ISR.

But I remember the feeling of vindication. My hardware training made me valuable over a pure software engineer.

Math Nerd?

I just made two posts on recreational math. I'm what you might call a math nerd wannabe. I'm NOT a math nerd - I don't have a flair or the rigor required to make that claim - but I've always wished I were.

I used to read Martin Gardner in Scientific American. And I tried to enjoy it with mixed success. More recently, I subscribed to Numberphile, but finally unsubscribed when I realized I tend to lose focus about halfway through most of the videos. And 3Blue1Brown? The same but more. It's not just that I have trouble following the math (although I often do), I'm just not interested enough to try hard enough. But darn it, I wanna be! :-)

When I was very young, I aspired to be a scientist so I could invent cool things. Never mind that theoretical scientists and inventors tend to be very different kinds of people; in both cases, I don't have the knack. I think I'm more of a hobbyist who discovered that he could be paid well for his hobby. I've never invented a cool algorithm, but I've enjoyed implementing cool algorithms that real scientists have invented. I like tinkering, taking things apart to see what makes them tick, and sometimes even putting them back together.

Not that there's anything wrong with this. I've led, and continue to lead, a happy, productive, and fulfilling life. I'm reasonably well-liked and respected by my peers. I have no complaints about how life has treated me.

But I am sometimes wistful about what might have been ... being a math nerd/scientist/inventor would be pretty cool too.

Anyway, I won't be making regular posts about math ... unless I do. ;-)

CC0 vs GPL

I've been writing little bits and pieces of my own code for many years now. And I've been releasing it as CC0 ("public domain"; see below). I've received a bit of criticism for it, and I guess I wanted to talk about it.

I like to write software. And I like it when other people benefit from my software. But I don't write end-user software, so the only people who benefit from my code are other programmers. But that's fine, I like a lot of programmers, so it's all good.

There are different ways I could offer my software. Much open-source software is available under a BSD license, an Apache license, or an MIT license. These differ in ways that are probably important to legal types, but for the most part, they mean that you can use the code for pretty much any purpose as long as you give proper attribution to the original source. So if I write a cool program and use some BSD code, I need to state my usage of that code somewhere in my program's documentation.

So maybe I should do that. After all, if I put in the effort to write the code, shouldn't I get the credit?

Yeah, that and a sawbuck will get me a cup of coffee. I don't think those attributions are worth much more than ego-boosting, and I guess my programmer ego doesn't need that boost.

With the exception of the GNU Public License (GPL), I don't think most open source ego-boosting licenses buy me anything that I particularly want. And they do introduce a barrier to people using my code. I've seen other people's code that I've wanted but decided not to use because of the attribution requirement. I don't want the attributions cluttering up my documentation, and adding licensing complications to anybody who wants to use my code. (For example, I was using somebody else's getopt module for a while, but realized I wasn't giving proper attribution, so I wrote my own.)

But what about GNU?

The GPL is a different beast. It is intended to be *restrictive*. It puts rules and requirements for the use of the code. It places obligations on the programmers. The stated goal of these restrictions is to promote freedom.

But I don't think that is really the point of GPL. I think the real point of GPL is to let certain programmers feel clean. These are programmers who believe that proprietary software is evil, and by extension, any programmer who supports proprietary software is also evil. So ignoring that I write proprietary software for a living, my CC0 software could provide a small measure of support for other proprietary software companies, making their jobs easier. And that makes me evil. Not Hitler-level evil, but at least a little bit evil.

If I license my code under GPLv3, it will provide the maximum protection possible for my open-source code to not support a proprietary system. And that might let me sleep better at night, knowing that I'm not evil.

Maybe somebody can tell me where I'm wrong on this. Besides letting programmers feel clean, what other benefit does GPL provide that other licenses (including CC0) don't?

I've read through Richard Stallman's "Why Open Source Misses the Point of Free Software" a few times, and he keeps coming back to ethics, the difference between right and wrong. Some quotes:

• "The free software movement campaigns for freedom for the users of computing; it is a movement for freedom and justice."
• "These freedoms are vitally important. They are essential, not just for the individual users' sake, but for society as a whole because they promote social solidarity—that is, sharing and cooperation."
• "For the free software movement, free software is an ethical imperative..."
• "For the free software movement, however, nonfree software is a social problem..."

I wonder what other things a free software advocate might believe. Is it evil to have secret recipes? Should Coke's secret formula be published? If I take a recipe that somebody puts on youtube and I make an improvement and use the modified recipe to make money, am I evil? What if I give attribution, saying that it was inspired by so-and-so's recipe, but I won't reveal my improvement? Still evil?

How about violin makers that have secret methods to get a good sound? Evil?

I am, by my nature, sympathetic to saying yes to all of those. I want the world to cooperate, not compete. I used to call myself a communist, believing that there should be no private property, and that we should live according to, "From each according to his ability, to each according to his needs". And I guess I still do believe that, in the same way that I believe we should put an end to war, cruelty, apathy, hatred, disease, hunger, and all the other social and cultural evils.

Oh, and entropy. We need to get rid of that too.

But none of them are possible, because ... physics? (That's a different subject for a different day.)

But maybe losing my youthful idealism is nothing to feel good about. Instead of throwing up my hands and saying it's impossible to do all those things, maybe I should pick one of them and do my best to improve the world. Perhaps the free software advocates have done exactly that. They can't take on all the social and cultural ills, so they picked one in which they could make a difference.

But free software? That's the one they decided was worth investing their altruism?

Free software advocates are always quick to point out that they don't mean "free" as in "zero cost". They are referring to freedoms - mostly the freedom to run a modified version of a program, which is a freedom that is meaningless to the vast majority of humanity. I would say that low-cost software is a much more powerful social good. GPL software promotes that, but so do the other popular open-source licenses. (And so does CC0).

So anyway, I guess I'm not a free software advocate (big surprise). I'll stick with CC0 for my code.

What is CC0

The CC0 license attempts to codify the concept of "public domain". The problem with just saying "public domain" is that the term does not have a universally agreed-upon definition, especially legally. So CC0 is designed to approximate what we think of as public domain.

Nice catch, Grammarly

 I was writing an email and accidentally left out a word. I meant to write, "I've asked the team for blah...". But I accidentally omitted "asked", so it just said, "I've the team for blah...".

Grammarly flagged "I've", suggesting "I have". Since my brain still couldn't see my mistake, I thought it was complaining about "I've asked the team...". I was about to dismiss, but decided to click the "learn more" link. It said that, except in British English, using the contraction "I've" to express possession sounds unnatural or affected. As in: "Incorrect: I've a new car".

Ah HAH! That triggered me to notice the missing word "asked". I put it in, and Grammarly was happy. I consider this a good catch. Sure, it misdiagnosed the problem, but it knew it was a problem.

Thanks, Grammarly!

Investment Advice from an Engineer

 I have some financial advice regarding investing in stocks. But be aware that, while I am pretty wealthy, the vast majority of my wealth came from salary from a good-paying career. You will *NOT* get rich off the stock market by following my advice.

THE ADVICE

Put money every month into an U.S. exchange-traded fund that is very broad market. Like SPDR. (I prefer VTI because it is even broader and has lower fees, but the differences aren't really that big). The goal is to keep buying and never selling, every working month of your life until you retire. (I don't have retirement advice yet.)

If the market starts going down, do *NOT* stop buying. In fact, if you can afford it, put more in. Every time the market goes down, put more in. The market will go back up, don't worry. 

The same cannot be said for an individual stock -- sometimes a company's stock will dive down and then stay down, basically forever. But the market as a whole won't do that. A dive might take a few days to recover, or might take a few years to recover. But it will recover. DON'T sell a broad fund if the market is going down. BUY it.

AND THIS WILL GET ME RICH?

No. It will give you the highest probability of a good return. Back when I was a kid, I was told to put money into a bank savings account. That was poor advice then, and is terrible advice now with interest rates close to zero. Putting money into a guaranteed bank account is guaranteed to underperform inflation. I.e. it will slowly but surely lose value.

Instead, tie your money to the overall market. The broad market has its ups and downs, but if you stick with it for a while, the overall trend is higher than inflation. 

WHAT IF I WANT TO GET RICH QUICK?

Well, you could buy a lottery ticket. That will get you rich the quickest. Assuming you win. Which you won't. Or you could go to Vegas and put a quarter into a slot machine.

But you're smarter than that. You know the chances of getting rich off of lotteries or gambling are too low. You want something that has some risk, but which will probably make you rich. And you're thinking the stock market.

Your best bet? Find a company currently trading for a few dollars a share, but is definitely for sure going to be the next Apple or Microsoft. One tiny problem: if it is definitely for sure going to be the next Apple or Microsoft, the stock price won't be a few dollars a share. It will be priced as if it already IS the next Apple or Microsoft. This is because there are tens of thousands of smart traders out there who are spending a HELL of a lot more time than you are trying to find the next big company. For a "sure thing" company that is already publicly traded, those tens of thousands have already bid up the price.

The only real chance for you to get in on the ground floor is to find a garage shop start-up, and invest in them. I have a rich friend who has made a lot of money doing exactly that. For every ten companies he invests in, nine go bankrupt within 5 years. And one goes off like a rocket.

That's how you do it. And unfortunately, you have to start out pretty rich to make this work. And you need to research the hell out of startups, and have a good crystal ball.

The only other way to do it is to find a company that the tens of thousands of smart traders thinks will NOT be a big deal, but you believe something they don't. Microsoft was publically traded at a low price for many years. The tens of thousands of smart traders in the 70s didn't think home computers would become a thing. And the few people who believed otherwise became rich.

The problem is that belief usually doesn't work very well at predicting success.

Look at BitCoin. I know several people who have made huge amounts of money on BitCoin. They did their initial investments based on a belief. A belief that BitCoin would become a real currency, just like dollars and euros; that people would be use BitCoin every day to buy and sell everything from gasoline to chewing gum. They looked at the theories of money and the principles of distributed control, and thought it would definitely for sure replace national currencies.

Those friends of mine were wrong. They made money for a completely different reason: speculators. Speculators buy things that are cheap and they think will go up in price. If enough speculators find the same thing to buy, the prices *does* go up. And more speculators jump in. BitCoin is a big speculative bubble, with almost no intrinsic value. (And yes, I know BitCoin is more complicated than that. But I stand by my 10,000-foot summary.)

Now don't get me wrong. Successful speculators DO become rich. Who am I to argue with success? But getting rich off of speculation is all about timing. You have to find the next big thing before most of the other speculators do, and then jump back out *before* it has run its course. Will BitCoin come crashing back down? Not necessarily. If enough people simply *believe* in it, it will retain its value. My own suspicion is that it will eventually crash but what do I know? I thought it would have crashed by now.

That's also what happened with GameStop. A group of Reddit-based speculators decided to pump up the price of a company. If you were in on it from the start, you probably made a ton of money. But once it hit the news, it was too late for you to get rich off of it. The best you could hope for was to make a little money and then get out FAST. But most people who jumped into GameStop after it had already made the news ended up losing money.

(BTW, "pump-and-dump" is against the law. I will be interested to find out if any of the Reddit-based traders get in trouble.)

Anyway, I know of many people who have taken a chance on a stock, and made some money. But they didn't get rich. And if they keep trying to replicate their early success, they'll end up winning some and losing some. And if they're smart, and work hard at it, they may out-perform the overall market in the long run. But remember - those tens of thousands of smart traders are also trying to out-perform the overall market. For you to do it repeatedly for many years probably requires expertise that those smart traders don't have. And you don't get rich quick this way, you just make some good money.

WHAT IF I JUST WANT TO PLAY THE MARKET

(shrugs) Everybody needs a hobby. I have a friend who goes to Vegas once a year. Sometimes he comes back negative, sometimes positive. He has absolutely no illusion that he will get rich in Vegas. He assumes he will either make a little or lose a little. And he has fun doing it. There's nothing wrong with spending money to have fun.

If you play the stock market as a game, where you aren't risking your financial future, then more power to you. But I knew one person who had to stop for his own emotional well-being. He started feeling bad every time he lost some money because he should have invested less, but also felt bad when he made money because he should have invested more. Overall he made money, but he had so much anxiety doing it that he decided it wasn't worth it.

Racism in America

 As my readers have no doubt noticed (all 2 of you!), I keep this blog pretty technical, without a lot of politics. And I intend to keep it that way ... for the most part. But occasionally I will let my politics peek out.

Yeah, you're expecting me to talk about the events in Washington DC in January, 2021. I might post about that some day, but I'm nowhere near ready yet.

No, I'm going to talk about a class I took last fall. See https://www.rootstorevolution.org/courses

These are left-leaning classes that not only teach history, they also encourage and facilitate activism. Their focus is on racism, but touch on other "isms" as well. I learned a heck of a lot of history that wasn't covered very well back when I went to high school. The material is well-researched and well-sourced. I consider myself a better person for having participated.

The bottom line is that it isn't enough to be "not racist". We have to be "anti-racist".

The classes are not cheap. As of this writing, they are $200 a pop. (And worth it, in my humble opinion.) That said, the class organizers don't want cost to be a barrier to participation, and are willing to make adjustments. Plus, I am willing to kick in $100 for anybody who comes to them from my recommendation. Tell 'em fordsfords sent ya. (-:

Anybody who wants more "informal" information on the classes, send me an email.

Steve

Ok, I guess I like Grammarly (grumble, grumble)

Ok, I grudgingly admit that I like Grammarly.

My complaints still hold: [UPDATE: these are all fixed now]

1. Mac users are second-class citizens. Mac Word integration has the file size limit, and there is no Mac outlook integration. [UPDATE: Mac integration is now good]
2. Their desktop tool won't edit a locally-stored text file. You have to do cutting and pasting. [UPDATE: it integrates well with TextEdit. But not vim.]
3. The file size limit is too small for serious work. Yes, you can do cutting and pasting again, but really? In 2020? [UPDATE: it now operates on large files]

The grumpy old man in me really wants to mumble something about snot-nosed little kids and go back to a typewriter and liquid paper.

But ... well ... I do have some bad writing habits.

Mostly I sometimes write unnecessarily complicated sentences, including useless phrases that I must have learned sound intellectual. It's a little humbling to have it pointed out over and over, but the result of more concise writing is worth it.

Mind you, there are many MANY times that I click the trash can because I don't like Grammarly's suggestions. In much of my technical writing, I use passive voice because active is too awkward. I also deviate from the standard practice of including punctuation inside quotes, especially when the quotes are not enclosing an actual quotation, but instead are calling out or highlighting a technical term, like a variable name. If I tell you to enter "ls xyz," and you type the comma, it won't work. You have to enter "ls xyz". I also sometimes include a comma that Grammarly thinks is not needed, but I think it helps separate two ideas.

Also, Grammarly isn't good at large-scale organization of content, which can have a MUCH greater effect on clarity than a few superfluous words.

In other words, *real* editors don't have to worry about being replaced by AIs for quite a while.

And yet ... and yet ... even with its limited ability to understand what I'm trying to say, it is still improving my writing. In small ways, perhaps. But improvement is improvement.

So yeah, I'll keep paying them money (grumble, grumble).

I want to love Grammarly

UPDATE 2 (17-Nov-2021): Grammarly has released an update, and my first impression is THANK GOODNESS! They either listened to me, or more likely, they knew all along what their drawbacks were. Most of my complaints are now either resolved or at least better. It is now much more native to the Mac and works more cleanly with web pages, Mac's "text edit" app, and Office for Mac. Apparently, it leverages Apple's "accessibility" infrastructure somehow. But it doesn't work with MacVim or the Terminal app. Which doesn't surprise me. Also doesn't work with Teams, which maybe does surprise me a little.

Again, I'll try to write a proper review sometime.

EARLIER UPDATE: I've been using paid-for Grammarly for almost 3 months now, and despite my complaints, I have to say that I like it. I'll leave this post pretty much as I originally wrote it and write a follow-up post when I have time.

I've lived with a bit of a problem almost all my life. I'm a slow reader and a poor speller. I suspect I have a bit of a learning disability.

That's not my problem. If I really do have a learning disability, it is mild; my language abilities are not that far below average. And I'm an engineer, for goodness sake! I'm not expected to have a perfect command of English.

My problem is that I love to write. I've dabbled with fiction, humor, and non-fiction (this blog being a primary outlet). And I want the quality of my writing to be high.

When I had my first exposure to a spell-checker, I was ecstatic! Finally, a tool to save me huge amounts of time. When I first used one that suggested correct spellings, I thought I had died and gone to heaven. But their were still to many thymes that incorrect word choice, usually among homophones, led to mistakes not being caught. I knew that a grammar checker was needed to really get the spelling right.

Microsoft Word, for all the hate that is heaped on it, raised the bar. It catches many problems that "aspell" does not. Word is still not perfect, but it is *good*.

Enter Grammarly. There's a lot about it I really like. For example, instead of just showing you your mistake and offering suggestions, it explains why its a mistake (at least when using the Grammarly editor). I.e. it is both an error checker and a learning tool. I'm using the Grammarly editor to enter this blog post, and it found a couple of things that the Firefox checker did not flag.

... But ... did you notice my mistake in the previous paragraph? "...it explains why its a mistake." The "its" needs an apostrophe. Grammarly didn't catch it. Microsoft did. But neither one caught the "thymes" in the prior paragraph. (Interestingly, the Firefox checker does flag "thymes".) Grammar checking is still an inexact science. UPDATE: The latest version *does* catch the "its". But my point is that it won't be perfect.

But never let perfection be the enemy of good. And there's a lot of good in Grammarly. I really want to love it enough to pay the fee. Why don't I?

My biggest issue is the file size limitation, which does not grow with the paid-for version. I maintain the documentation for our product, and some of those files are pretty big. Way too big, it turns out. I would have to mess with splitting and recombining them. Never mind the annoyance of doing that, the recombining introduces more opportunities for mistakes. UPDATE: The file size limitation seems to be removed now. I can use TextEdit to edit very large files and it seems to work. But it doesn't remember the "errors" that I dismiss; again that seems to be only in the Grammarly editor.

Also, I use a Mac, and Grammarly doesn't integrate with Outlook on Mac. And even the Mac Word plugin is size-limited, although it looks like maybe that limitation would be lifted if I were using Windows instead of Mac. UPDATE: it does now.

Also, it doesn't work well with local ".txt" files except through copy-and-paste. (It can read text files, but not write them.) UPDATE: it does now with TextEdit.

I'll probably pay for a month's worth just to see what the 11 extra suggestions are for this blog post. Maybe seeing them will change my mind. But I kind of doubt it.

EDIT (19-Sep-2020): I did go ahead and shell out for the pro version. So far it has provided a small improvement. Not sure it's worth the cost yet, but still early days. In most cases, it challenges me on something that probably does deserve a second thought, but I ended up keeping as-is.

Roadmap to Reopening

Vi Hart posted an important video: https://www.youtube.com/watch?v=HhRQxk9QA-o

Please watch it.

Full report:
 https://ethics.harvard.edu/files/center-for-ethics/files/roadmaptopandemicresilience_final_0.pdf

Lots more info about it: https://www.pandemictesting.org/

New animated short by Ivan Maximov

Sorry, no computer software today.

I see that Ivan Maximov, one of my favorite animators, has finally released his latest work:

"Lonely Monster Goes Out"

I really love Ivan's gentle style. I also like how, instead of being intensely plot-driven, most of his stories are small explorations of a fantasy world, with an over-arching plot added for cohesiveness. I also like to believe that he is preaching tolerance of differences between good people, although I might just be projecting my own interpretations. (-:

Some of my other favorites:

• "Wind Along the Coast"
• "Long Bridge of Desired Direction"
• "Rains Down from Above"
• "Bum Bum, the Baby of the Fisher"
• "Tides To and Fro"
• "The Spate"

Or binge his whole channel. (And also his site for some things not on his Youtube channel.)

I don't understand why he isn't more popular, although it might be related to his low output rate.

I will miss you, Gahan Wilson

Gahan Wilson, creator of hilariously macabre cartoons, died last Thursday. His dark creations helped to shape my own sense of humor, even though as a child I was not able to enjoy them very often.

Thank you Gahan for teaching me that it is OK to not be main-stream.

Goodby my Wiki

This post is a little late in coming as I made the change earlier this year.

I used to use a hosting service, suso.com,  for my main website and email.  It ran a message board I built using Perl, and it also ran a older version of wikimedia for a personal wiki.  But the service cost a fair amount, and neither the message board nor the wiki was being used much.  So to save money, I cancelled it and moved the content to github.

The content is still available at geeky-boy.com, but I dumped the wiki pages to a flat directory.  If I want to edit them, I need to edit the raw HTML.

I somewhat mourn the loss of my wiki.  I like wikis for certain kinds of content.  It is especially powerful for collaborative efforts, particularly for geographically-separated teams.  But even for single-user personal-use, it presents such a low barrier to use.  If I want to update a page, it's just a few button clicks away.  And the update process is easy (assuming minimal use of fancy wiki markup).  And it's easy to see change history, roll back changes, etc.

Contrast this with web pages on github where you have to edit them locally in HTML, check in the changes, and sync with "gh-pages" branch to make them live.  It takes longer, and requires specialized software.  E.g. I can't easily do it from a phone or tablet.

There are "free" wikis out there, but I don't like the ads, and most of them use non-wikimedia software; the few I've tried I haven't liked.

Maybe someday I will try some kind of third-party content management system.  Or maybe I'll write my own wiki software as a fun personal project (maybe do the rendering of the markup in the browser in Javascript).  Or maybe I just don't really need a wiki.  Long ago, I imagined that the blog and the wiki would compliment each other, with content in each referring to content in the other.  Blog for "news", wiki for "content".  But it hasn't worked out that way.

So rest-in-peace wiki.geeky-boy.com.  You were fun while you lasted.

Review: Prairie Burn (Jazz)

I realize that this is a technical blog without many followers, but I'm really getting into a new album and wanted to share.  If you're not interested in Jazz music, you may stop reading.

Prairie Burn is a new CD by the Mara Rosenbloom Trio.  It is modern Jazz, so don't expect anything that sounds like Tommy Dorsey, or dixieland.  Unfortunately, I don't have the background or the vocabulary to be able to tell you what it *does* sound like.  In other words, this is the worst Jazz review ever.

But since when has that ever stopped me?  :-)

Prairie Burn is great.  Listening to it takes me on an emotional journey including stops at agitation, surprise, excitement, dreaming, and satisfaction.  This music draws me in effortlessly.

So, why am I flogging it in my blog?  For the same reason I flogged Mad and Grace: I like them and I want them to reach their goals.  Yes, Prairie Burn has an Indegogo campaign to raise money for a publicist so that Mara can get more of the attention she deserves.

Jazz has a strange following, few in number but passionate in their dedication.  I've read people bemoan the lack of young talent in the genre.  Most of the well-known artists are getting on in years and won't be around forever.  We've got to find new talent and support it.

I've done the finding for you.  Now it's your turn to help with the supporting.  :-)

Not sure you'll like the music?  http://www.mararosenbloom.com/html/listen.php  The two pieces from Prairie Burn are pretty different from each other, but the second (Turbulence) is probably more representative of the album as a whole.

Full disclosure: Mara is my daughter-in-law.  That certainly influenced me in terms of giving the music a try.  I believe it is not influencing my evaluation of its quality.  This is her third album, and while I like them all, this is the one that I feel passionate about.

Saying goodbye to a bit of personal history

Ever since I was *very* young, I've been interested in science and technology.  At some point in my teens, maybe 40 years ago, I wanted a better VOM (Volt-Ohm-Milliamp meter) than the junky one I had picked up, so I did some research and spent precious funds on a high-impedance FET meter:



It saw pretty heavy use about 5 years, but as I transitioned from electronics to digital logic, and from that to software, my need for it dropped.  I've probably used it twice in the past 15 years, probably for checking if an electrical outlet is live.

As my previous post indicates, I've just gotten a single-board computer, and I was trying to indirectly measure the value of the pull-up resistor on an open-collector output.  I need a reasonably accurate, high impedance meter, so I got out my old FET.

Alas, the two small selector switches were frozen.  Not sure why or how -- it's a *switch* for goodness sake -- but I can't use it if I can't turn it on.  I'll take it apart, but I don't have high hopes.

It's passing is a sad event for me, but why?  Is it just nostalgia?  Longing for a simpler time?  Missing my childhood?  I think it's more than that.  There are certain things that have come to represent turning points in my life.  The meter may not have *caused* a significant shift in my life path, but it had come to represent it.  And maybe its a mortality thing too, like a piece of me died.

Oh well, I'll probably get a cheap DVM.