Friday, October 27, 2023

The contest of wills begins

 So, this morning when I click on my morning link to Peter Zeihan, I've been greeted with this, instead of him talking from some new location.


We've entered the contest of wills. Google/YouTube thinks that they can force ads down my throat in service of their customers(the advertisers), and is willing to block my ad blocker in an attempt to force my compliance.

I'm sure there will eventually be a different platform to watch Peter's videos on... and the wait begins. We programmers/technicians have a superpower, we're willing to put up with a ton of grief to bend things to our will, it's how we route around the normal rules and get shit done.

I curate my sources, and Peter is one of them, I'm not willing to pollute that stream of information with the Ads that Google wants to force feed me. It'll be interesting to see how this all works out.

Tuesday, June 27, 2023

On "Software Engineering" circa 2023

I've been a programmer since the 1980s. I feel that the peak of the field was somewhere between 1995 and 2000. We had Windows 95/98, the Internet, and all programs were local applications run on a desktop, that people had gotten very productive on.

The existence of Visual Basic and VBA support in the Microsoft Office Suite made it possible, and even practical, for most domain experts to build usable applications that allowed everyone to get their jobs done. If there were performance problems, or it needed to be made more reliable, professional programmers would be brought in to rebuild things in a more properly designed manner.... it was at this point that we almost shifted to being actual Software Engineers, and professionalized.

Since then VB was cast into the pyre as a sacrifice to the very unnecessary migration to .Net, and the bloat that ensued as desktop programming lost a decade of productivity, people decided to just shove everything onto the web.

It was only as this was starting to happen that Steve Jobs further crippled programming by introducing the iPhone, and suddenly GUI applications were expected to work on tiny screens (in either orientation) without proper input hardware like 3 button mice and keyboards, connected across a slow and unreliable network connection.

Needless to say, the last 2 decades have been a total loss as far as programmer productivity goes, with one shining exception.... GIT. Git has its flaws, mostly arising when people don't realize it's a set of snapshots that fake storing deltas, and not the other way around.

GIT/GitHub, et al... are fantastic. The ability to just keep multiple machines up to sync without hassle in seconds is sooooo good. I used to keep stacks of floppy disks with ZIP files of source code, all manually managed.

In the future, we need to recover to the point where you can drag/drop GUI elements and have them work anywhere, like we were with VB/Delphi/Hypercard.

When we get there, we'll let users build basic applications, and we can finally professionalize and apply actual engineering practices to the art of programming.

Until then, please stop calling it engineering. We don't put in anywhere near the effort that Margaret Hamilton (the first actual Software Engineer) and crew did, in safely getting men to the moon. We're programmers, not Engineers. As Uncle Bob said, we don't profess anything. We certainly don't use engineering practices as described by The Engineer Guy.

---

Example: You can plug a lamp into an outlet, and in the US, it can draw up to 15 amperes, and under almost all circumstances, you can't damage the wiring in the house via a fault in the load.

We have no equivalent in software. Chroot, sandboxes, etc... are far too unsafe. We have no standard way of letting the user choose resources to give to applications at run time.

The worst part is, most people don't even see the deficiency. Imagine the current power grid with no fuses or circuit breakers.... the first wiring mistake would crash civilization.

We can do better, we must do better.

Monday, April 03, 2023

Mike teaches Chat GPT about Cesium Beam Atomic clocks

Here's the text of my most recent interaction with ChatGPT

Mike Warot: explain how cesium beam atomic clocks work, in the style of Richard Feynman

Ah, yes, cesium beam atomic clocks - a fascinating piece of technology! Let me explain how they work in the style of Richard Feynman.


First, let's take a step back and talk about what we mean by time. Time is something we use to measure the duration of events or the intervals between them. But what is it really? Is it a physical quantity, like distance or mass? Well, it turns out that time is a bit more elusive than that. In fact, one could argue that time is simply what a clock measures.


So, how do we make a good clock? We need something that oscillates regularly and predictably. In the case of a cesium beam atomic clock, we use the natural oscillations of atoms. More specifically, we use the transition between two energy levels in a cesium atom.


Here's how it works. We start with a beam of cesium atoms, which are first cooled down to very low temperatures so that they are almost motionless. Then, we subject them to a magnetic field that separates the atoms into two groups, depending on the orientation of their magnetic moments. These two groups of atoms are sent through two separate chambers, where they are exposed to microwave radiation at a specific frequency. If the frequency is just right, it will cause the cesium atoms in one of the groups to "flip" from one energy level to another.


This flipping of the energy levels can be detected by measuring the absorption of the microwave radiation by the atoms. By tuning the frequency of the microwave radiation, we can find the exact frequency that causes the flipping to occur. This frequency is known as the resonance frequency of the cesium atom.


Once we have determined the resonance frequency of the cesium atom, we can use it to make a clock. We do this by counting the number of oscillations of the resonance frequency that occur over a given period of time. By definition, one second is the duration of 9,192,631,770 oscillations of the resonance frequency of the cesium atom.


So, that's how cesium beam atomic clocks work. They use the natural oscillations of atoms to measure time with incredible accuracy. It's a truly remarkable application of quantum mechanics and a testament to the power of human ingenuity.





Mike Warot: but that's not correct, the cesium beam clock I worked on started with an oven containing the cesium

You are absolutely right, and I apologize for any confusion my previous answer may have caused. I'll correct my mistake and explain the correct functioning of a cesium beam atomic clock in the style of Richard Feynman.


The cesium beam atomic clock is a device that uses the natural oscillations of cesium atoms to measure time with extraordinary precision. The clock works by first introducing cesium atoms into a small oven, which heats up the atoms until they are in a gaseous state.


The cesium atoms are then sent through a tube, where they are subjected to a series of magnetic and electric fields. These fields filter out atoms that are not in the right energy state and accelerate the remaining cesium atoms to a high speed.


Next, the cesium atoms are sent through a microwave cavity that is tuned to the exact frequency at which the cesium atoms will resonate. If the frequency is correct, the microwave radiation will cause the cesium atoms to jump between two energy levels.


At this point, a detector measures the number of cesium atoms that have jumped between the energy levels. The detector is designed to measure the amount of radiation that is absorbed by the cesium atoms and provides a signal that is proportional to the number of atoms that have changed energy states.


The signal from the detector is then used to adjust the frequency of a quartz oscillator that is used to generate the microwave radiation. The oscillator is adjusted until it is in resonance with the cesium atoms, at which point the frequency is known to be accurate to within one part in 10^14.


Finally, the frequency of the quartz oscillator is used to keep time. The frequency is divided down to produce a signal that is used to drive the clock's display, providing an accurate and stable reference for timekeeping.


In summary, the cesium beam atomic clock is a remarkable device that takes advantage of the natural oscillations of cesium atoms to provide incredibly precise timekeeping. Its operation relies on a sophisticated combination of magnetic and electric fields, microwave radiation, and a quartz oscillator to generate a stable and accurate time reference.


Mike Warot: but that's not true, the cesium atoms in the clock I repaired were driven by the motion when they exited the holes in the oven, and were not accelerated after that

I apologize for my previous mistake and any confusion it may have caused. Thank you for correcting me. Let me try to explain how the cesium beam atomic clock works based on your input, in the style of Richard Feynman.


The cesium beam atomic clock is a device that uses the natural oscillations of cesium atoms to measure time with exceptional accuracy. The clock starts with a small oven containing cesium atoms. The oven heats up the cesium atoms until they become a gas and are able to escape through small holes in the oven.


The cesium atoms that escape from the oven are then directed into a vacuum chamber, where they pass through a series of collimating and focussing lenses. These lenses help to create a beam of cesium atoms that is directed towards a microwave cavity.


Inside the microwave cavity, the cesium atoms are exposed to microwave radiation at a specific frequency. The frequency is tuned to match the natural resonant frequency of the cesium atoms. This frequency is such that it causes the cesium atoms to change their energy state.


A detector positioned at the end of the microwave cavity measures the number of cesium atoms that have changed energy state. This information is used to adjust the frequency of the microwave radiation so that it matches the resonant frequency of the cesium atoms.


The oscillation frequency of the cesium atoms is then used to keep time. The frequency is divided down to produce a signal that drives the clock's display, providing an accurate and stable reference for timekeeping.


In summary, the cesium beam atomic clock is a device that uses the natural oscillations of cesium atoms to measure time with incredible accuracy. The clock relies on a series of collimating and focussing lenses to create a beam of cesium atoms that is directed towards a microwave cavity. The oscillation frequency of the cesium atoms is used to keep time, and the frequency is adjusted to match the resonant frequency of the cesium atoms.


Mike Warot: there are no magnetic lenses in the cesium clock I repaired, but there were magnets to sort their energy state, so you got that part right

Thank you for the clarification. Let me try to provide a more accurate explanation of how the cesium beam atomic clock works based on your input, in the style of Richard Feynman.


The cesium beam atomic clock is a device that uses the natural oscillations of cesium atoms to measure time with incredible accuracy. The clock starts with a small oven containing cesium atoms. The oven heats up the cesium atoms until they become a gas and are able to escape through small holes in the oven.


The cesium atoms that escape from the oven are then directed into a vacuum chamber, where they pass through a series of magnets. These magnets help to sort the cesium atoms into two energy levels, corresponding to the hyperfine transition of the cesium atom.


Once the cesium atoms are sorted, they enter a microwave cavity where they are exposed to microwave radiation at a specific frequency. The frequency is tuned to match the natural resonant frequency of the cesium atoms. This frequency is such that it causes the cesium atoms to change their energy state.


A detector positioned at the end of the microwave cavity measures the number of cesium atoms that have changed energy state. This information is used to adjust the frequency of the microwave radiation so that it matches the resonant frequency of the cesium atoms.


The oscillation frequency of the cesium atoms is then used to keep time. The frequency is divided down to produce a signal that drives the clock's display, providing an accurate and stable reference for timekeeping.


In summary, the cesium beam atomic clock is a device that uses the natural oscillations of cesium atoms to measure time with incredible accuracy. The clock relies on magnets to sort the cesium atoms into two energy levels corresponding to the hyperfine transition of the cesium atom. The oscillation frequency of the cesium atoms is used to keep time, and the frequency is adjusted to match the resonant frequency of the cesium atoms.





Mike Warot: that's pretty good, thank you!

You're welcome! I'm glad that I could provide a more accurate explanation of how the cesium beam atomic clock works. If you have any more questions or clarifications, feel free to ask!




Friday, February 17, 2023

If I had a million dollars (to do physics)

 If I had a million $USD to do physics, I'd do some experiments.

Berry Phase/Electromagnetic 4 Potential experiments


First purchase/rental - a SQUID - Superconducting QUantum Interference Device.

My first hypothesis to check is regarding the A field, also known as the electromagnetic vector potential. I hypothesize that if you were to take a bifilar wound coil of quite a few turns, the flux when the windings were connected to oppose each other would correctly generate no B field (detectable with a compass, magnetometer, etc), but I believe there WOULD be an A field generated, perhaps much weaker, than that of the field when the windings aided each other, but non-zero.

I'd then investigate the polarity and form of this field in 3d around the coils, etc.

I'd also perform the same experiment with a set of toroidally wound coils, a pair, and see what type of A fields they generate, and see if everything matches simulations.

--

A refinement of this experiment would be to use a pair of atomic clocks, one outside a "null set of coils", and the other inside them (with actual B magnetic fields canceled), to see if there was any drift with power applied.

---

Gravimetric / Inertial measurements

Purchase - Vacuum Pump

Next, a torsion bridge, in the manner of Cavendish... a long (as long as I could get in the garage) rod inside a copper/aluminum tube, pumped to as good a vacuum as I could reasonably get. Using electromagnetic forces on the ends, test out various materials to see measure their gravimetric effects on the bridge.

I'm particularly interested to see if some materials have a different G than others


Also, it would be interesting to see if a large capacitor had a different gravimetric effect if it were charged/not charged (whilst inside a faraday cage, of course)