@Revlac

The other thread was locked out after you suggested I "have a coffee and calm down"

In that message, you referenced the "ping pong ball through a bat" Myth buster video as if it was proof of something.

Do you even have a clue about this?
Did you see a spherical object pass through the bat as a sphere?

Did you pay attention to the proximity of the muzzle of the air cannon to the bat?

This is the downright ignorance that prevails today.

All that needs to happen is a misleading video to "prove" something.

Hint: there is a German product "Alarmo" that is totally devastating and all it shoots is 5000PSI of air...no projectile.

You DID NOT see a spherical object pass through that bat...watch again and let's start talking real physics here(?)

  PhenixRising said  

My latest AI debate is about Concorde: where did it store 7,000 gallons and provide a range of 4,000 miles at mach-2

How can one explain something that isn't true?

According to my sources, "Concorde’s total fuel capacity was about 26,300 Imperial gallons".

Perhaps you were thinking of the WW II B-29 (approx. 7,859 Imperial gallons).

So I kinda doubt you actually did ask AI about it.

~
Edited 2025-11-29 11:48 by lizby

You must be thinking liters

Try applying some logic instead of accepting horse sh*te.

Look at the Concorde....26,000 gallons???

But you know what, they might as well state 26M gallons and you'd still accept it....because they told you.

Are you denying that "typical London–New York Concorde flights took about 3 to 3.5 hours gate‑to‑gate" and that "likely on the order of 1.5–2 million people—flew on some combination of London–New York or New York–London sectors"?

And herein lies the problem:

The critical thinker: Well I have analyzed the structure and calculated the required volume of the tanks and to be honest, I really can't see how this could even work. I mean, 0.57 miles/gallon with those Olympus turbo fans just doesn't add up.

Non critical thinker who is happy to be told what to believe: Are you saying that the plane didn't fly from London to NY.


Of course the plane flew. My friend used it several times, only for bragging rights.

But how was it really propelled at mach-2?

WHOA!....
I know I drift off track, but I do try not to for too long. :)
Lizby does have a valid point. This thread was started to continue the AI discussion after the previous one drifted too far out. It would be rather nice to keep this one running now. :)

Would you like to start some sort of "critical thinking" thread, PhenixRising? It could be interesting.

Failures as well as successes should be reported.

I asked Gemini if it could design circuits. It said yes. I prompted with something quite simple--a simulation PCB for testing control of my 3 boiler zones with a Tasmotized Sonoff 4CH Pro R3, with the PCB having only connections to that, a 2-pin 5mm terminal block for 9VAC input, and 4 10MM LEDs with appropriate resistors--all in EasyEDA format.

It produced a file, but was unable to tell me how to import it successfully. Everything I tried got error messages. It said it would do better with a Kicad file, but that, while imported with no errors, showed no circuit.

There was quite a bit of it telling me how I could lay it out, but I repeatedly said that was not the point: if I just wanted the circuit, I would do it with perfboard--what I wanted was for Gemini to do it.

After faffing about for over an hour, I gave up. Maybe Gemini 4 will be able to do it.

On the other hand, it has provided some very valuable and time-saving code about hardening my Seagate Dockstars running openWrt, and providing more logging and reporting. That interaction has been very satisfactory, and I've learned a lot.

But I also had a HAL moment. It lost context, and got stuck on a previous prompt, repeating itself over and over (regarding the circuit design). I had to close the browser page and start a new one.

~
Edited 2025-12-03 12:19 by lizby

"I'm sorry, Lizby, I can't do that."

It probably can design circuits in the form of schematics, possibly as a netlist, but it may not be able to convert the netlist into a pcb. Netlists aren't easy for humans to understand either, and I don't think there is a defined standard for them. You'd have a job finding a netlist-pcb converter to suit a weird netlist.

  Mixtel90 said  

"I'm sorry, Lizby, I can't do that."

It produced schematics in a number of formats, but EasyEDA couldn't import any of them. This is just another of those things which it can't do now, but probably soon will be able to do.

On the advice of Gemini, I purchased a Sonoff 4CHPRO R3 4-relay module to provide additional control of the 3 zones on my boiler. I won't be present to do the installation until May, but I flashed it with Tasmota and wired up 4 LEDs on a perfboard to emulate it. I gave this prompt to Gemini:

  Quote  

Write a bash script. For the Sonoff 4CHPOW R3, using for Power1, Power2, Power3, and Power4 with, e.g., curl "http://192.168.1.185/cm?cmnd=Power1%20On". Turn on each relay in sequence at 1 second intervals. Pause 3 seconds. Turn them off at 1 second intervals. Turn them all on, pause 5 seconds, then turn them all off. Then continuously at random turn one on or off every 2 seconds.

It took one adjustment, but this is the code it produced:


Youtube Video: Sonoff 4CHPRO R3 exercised

~
Edited 2025-12-08 04:09 by lizby

I took another step; to Gemini:

  Quote  

In simple and straightforward html, produce code for a page entitled, "Boiler Zone Thermostat Bypass", with 3 lines containing the line titles "Kitchen", "Livingroom", "Upstairs", an on/off button, a circle to be red or green depending on off or on, an editable text box for the number of minutes to be on, and a non-editable text box for the number of minutes remaining. Provide an automatic update once a minute. Runtime will be limited to 60 minutes. In a subsequent prompt I'll ask you for the backend code and setup procedure for running this on a Seagate Dockstar flashed with openWrt.

It did this and I brought it up in the browser from the local drive.

I asked it how to set it up on my Seagate Dockstar (16-year-old gear) running openWrt, and it told me and provided the code: html in /www, script in /www/cgi-bin, monitoring script in home directory, crontab entry. All worked very straightforwardly.



In years past I have been ready to tear my hair out over this stuff. Now I'll be able next May to upgrade my control of the 3 zones of my boiler, in parallel with the thermostats so they still work.

The Sonoff 4CHPRO R3 cost me $25 on Amazon ("Black Friday" price). The boiler manufacturer wants $800 for gear of similar capacity ($800 Canadian--about $600 USD).

I've been using various AI tools/LLMs since November 2022. Regarding AI use, a few things to remember:

1) The AI you use today is the poorest-performing it will ever be! Tools/LLMs like ChatGPT, Grok, Claude, and Gemini continue to improve daily. I've seen significant improvement in these models this year alone (2025). ChatGPT couldn't even access the internet back in March 2025.

2) Some models are better than others at certain tasks. If you don't get the results you expected, copy-and-paste the same prompt into a different AI model. For example, I've found Gemini to be the best for image generation.

3) Feed in helpful data. If you have a Word/PDF of your notes, thoughts, electrical data, diagrams, etc., include that as an attachment to your prompt. The AI's reply will be much better.

I personally like to take the AI's response and add selected points into my research notes document. Then I'll run the prompt again, sometimes in a different AI model, just to gain other insights.

4) Once recursive self-improvement begins (expected in 2026), AI will be better than anyone on the planet in any field. It's going to be scary times!

China Talk

  Quote  

Dmitri Alperovitch: The interesting thing about AI is not that it’s going to make tasks easier and faster, but that it’s going to make other things that you would never, ever do before accessible.

Prompt for ChatGPT-5:

  Quote  

Consider Saul Griffith's assertion: "In every possible future of this planet, the cheapest electricity will always be your rooftop solar." ( Rooftop Solar  )

What are the chances that some other technology (like fusion or deep geothermal) will make solar a transition technology?

tl;dr:

  Quote  

Saul Griffith’s assertion is likely correct in all plausible futures short of post-scarcity civilization: while other technologies may dominate bulk, firm, or industrial power, rooftop solar’s combination of free input, local delivery, modularity, and manufacturing learning curves makes it extraordinarily unlikely to be displaced as the cheapest marginal electricity for end users.

Long form:

  Quote  

This is a profound question, because Saul Griffith’s statement is not a casual slogan—it’s a claim about **physics, economics, and political economy** taken together. The right way to answer it is not “is fusion possible?” but **what would have to be true for rooftop solar to stop being the cheapest electricity at the margin**.

I’ll proceed in layers:

1. What Griffith *really* means by “cheapest electricity”
2. Why rooftop solar has structural advantages that are very hard to beat
3. What it would take for another technology to displace it
4. A sober assessment of fusion, deep geothermal, and others
5. The most realistic futures: replacement vs. coexistence
6. A bottom-line probability judgment

---

## 1. What Saul Griffith actually means by “cheapest”

Griffith is **not** saying rooftop solar is the cheapest *bulk* electricity.

He is saying it is the cheapest **marginal, delivered, retail electricity** for an end user.

That’s a crucial distinction.

When you put solar on your roof, you avoid:

* Transmission
* Distribution
* Grid losses
* Retail markups
* Capacity charges
* Some regulatory overhead

So the comparison is not:

> “Can fusion generate electricity cheaply at a power plant?”

It is:

> “Can anything beat electricity generated exactly where it is used, with no transport?”

That sets a very high bar.

---

## 2. Why rooftop solar has structural, not temporary, advantages

### A. It exploits a universal free input

Sunlight:

* Arrives everywhere
* At predictable intensity
* Without fuel cost
* Without geopolitical risk

Any competing technology must:

* Either beat **free**
* Or deliver something solar cannot (e.g., 24/7 firm power)

---

### B. It rides exponential manufacturing, not infrastructure buildout

Solar improves via:

* Learning curves
* Manufacturing scale
* Materials science
* Automation

This is **Silicon Valley–style progress**, not **utility-style progress**.

Fusion, geothermal, fission, CCS:

* Improve through projects
* Regulation
* Capital deployment
* Construction learning

Those scale much more slowly.

---

### C. It benefits from avoided-cost accounting

Rooftop solar is often installed when:

* A roof is being replaced
* A home is being built
* Electrical upgrades are happening anyway

That means:

* Incremental cost is lower than headline cost
* Payback is often measured against *retail* prices, not wholesale

This advantage never goes away.

---

## 3. What would it take to make solar “just a transition technology”?

For rooftop solar to lose its position, **one of three extraordinary things must happen**:

### Condition 1: Electricity must become so cheap everywhere that location no longer matters

If grid electricity fell to, say:

* $0.01/kWh retail
 Then:
* Rooftop solar wouldn’t be worth installing

But this would require:

* Generation near-zero cost
* Transmission near-zero cost
* Distribution near-zero cost
* Financing near-zero cost

That implies a world where:

* Capital is almost free
* Infrastructure is trivial
* Regulation is frictionless

That world would already be post-scarcity.

---

### Condition 2: A technology must deliver firm, local, ultra-cheap power at household scale

To beat rooftop solar, a competitor must be:

* As local
* As modular
* As cheap
* As safe
* As maintenance-free

That’s an *extraordinarily* narrow target.

---

### Condition 3: Solar must hit a hard physical or economic wall

Solar would need to:

* Stop improving
* Become materially scarce
* Face insurmountable land/area limits
* Be eclipsed by something strictly superior at small scale

There is no evidence of this yet.

---

## 4. Assessing the main contenders

### A. Fusion

Fusion’s strengths:

* Dense energy
* Firm power
* Potentially cheap fuel

But for rooftop displacement, fusion fails on multiple axes:

* Centralized, not distributed
* Gigantic capital intensity
* Long development cycles
* Requires grid delivery
* Political/regulatory complexity

Even **perfect fusion** would likely produce:

* Very cheap *wholesale* electricity
* Still not cheaper *delivered* than rooftop solar in many cases

Fusion competes with:

* Gas
* Nuclear
* Coal
 Not rooftops.

**Probability fusion displaces rooftop solar:** *Very low*

---

### B. Deep geothermal (EGS, superhot rock)

This is more interesting.

Strengths:

* Firm, 24/7
* Local in some regions
* High capacity factor

Limits:

* Highly site-specific
* Requires drilling
* High upfront capital
* Still grid-connected

Deep geothermal could:

* Displace fossil baseload
* Reduce need for storage
* Lower wholesale prices

But it does not:

* Appear on every roof
* Avoid distribution costs
* Scale modularly to households

**Probability it displaces rooftop solar globally:** *Low*
**Probability it complements and reduces storage needs:** *High*

---

### C. Advanced fission (SMRs, microreactors)

Similar story:

* Capital-heavy
* Centralized
* Regulatory overhead
* Long timelines

Even microreactors are:

* Orders of magnitude more complex than PV
* Not consumer-installed technologies

They compete with:

* Grid generation
 Not rooftop solar.

---

### D. Space-based solar

Ironically, this is still **solar**—just with extra steps and losses.

If it worked:

* It would still deliver via the grid
* Still incur distribution costs

It does not beat rooftop solar at the margin.

---

### E. Something genuinely unknown?

This is the strongest counterargument:

> “What if a technology we don’t yet imagine appears?”

To displace rooftop solar, it would need to:

* Be modular
* Be safe
* Be cheap
* Be local
* Beat sunlight + silicon + mass manufacturing

At that point, it would likely look like:

* Some form of *even cheaper solar*
* Or *direct ambient energy harvesting*

In other words, it wouldn’t negate Griffith’s claim so much as **generalize it**.

---

## 5. The most realistic future: solar as the floor, not the ceiling

The most likely outcome is:

* Rooftop solar sets the **price floor** for electricity
* Other technologies compete to:

 * Provide firm power
 * Provide seasonal balance
 * Serve dense urban/industrial loads
 * Reduce system-wide costs

In that world:

* Solar is not “transitional”
* It is **permanent infrastructure**
* Other tech stacks on top of it

Much like:

* TCP/IP didn’t get replaced by faster networks
* It became the substrate

---

## 6. A probabilistic judgment

If we’re forced to put rough odds on it:

* **Rooftop solar remains cheapest marginal electricity for end users through 2050:** ~80–90%
* **Another tech beats it everywhere, including rooftops:** <10%
* **Solar becomes secondary but still widely used:** ~10–20%
* **Solar becomes obsolete:** ~1–2% (catastrophic or post-scarcity futures)

Griffith’s claim is not that solar is *the best* electricity—
it’s that **nothing else can so easily undercut “free photons + local conversion.”**

---

## 7. One-sentence synthesis

Saul Griffith’s assertion is likely correct in all plausible futures short of post-scarcity civilization: while other technologies may dominate bulk, firm, or industrial power, rooftop solar’s combination of free input, local delivery, modularity, and manufacturing learning curves makes it extraordinarily unlikely to be displaced as the cheapest marginal electricity for end users.

Thanks, Lance, for that question! But doesn't the answer assume a cylindrical Earth?    


(Image: ChatGPT)

At my location in northern Germany, I hardly get any yield from my solar panels in winter.
Kind regards and Happy New Year to everyone on this cylindrical planet!  
Michael

Re: Consider Saul Griffith's assertion: "In every possible future of this planet, the cheapest electricity will always be your rooftop solar", I would add, "but not everywhere, and not at every season".

It's interesting (to me) that about 65-70% of Canada's population (and virtually all of the U.S.'s except Alaska), live at a lower latitude than Munich (Germany's largest southernmost city). And about 93% of the world's population lives closer to the equator than Munich.

Netherlands gets about 17% of its electricity from solar, Germany 14%, and even Denmark 11% (probably highly seasonal).

So northern Europe is out of luck for solar--93% of the world's population is better situated. But you've got wind--just not on your rooftop.

So even without the cylindrical world, Saul Griffith's statement might be true in northern Europe--but only in the summer.

Let's hope that deep geothermal proves to be economical--local baseload, but not residentially local.

And Happy New Year to all.

~
Edited 2026-01-01 01:24 by lizby

IMHO the main problem with AI is that it will increase bureaucracy.
To get permission for anything, AI product-of-the-month will simply generate all possibilities that have to be satisfied and the hapless citizen then has to jump through every hoop. Department by department, form by form, site by site...on and on...we will be driven mental by
red-tape robots !!  .

[off-topic - I don't think geothermal is a goer...at the high temperatures and  
pressures, water dissolves silica (rock) big time - when the water cools the
silica drops out as goopy sludge, choking pumps, heat exchangers and
everything else. Maybe if they use natural gas as a medium and recirculate it,
but that is way different.]

  zeitfest said  

IMHO the main problem with AI is that it will increase bureaucracy.

I haven't seen that concern voiced before. It's certainly possible, but in the U.S., bureaucracy/regulation/NIMBYism is already a major throttle on development, and there are efforts on both sides of the political isle to reduce that (but I don't know if they are bi-partisan or just differently focused). For the individual, I think AI will help figure out a path through bureaucratic impediments--but on the other side it may increase them.

  Quote  

[off-topic - I don't think geothermal is a goer...at the high temperatures and pressures, water dissolves silica (rock) big time - when the water cools the silica drops out as goopy sludge, choking pumps, heat exchangers and everything else. Maybe if they use natural gas as a medium and recirculate it, but that is way different.]

We'll see. There are both deep "closed loop" and "open loop" experiments ongoing. For closed loop, with cemented casings as the paths through the heat-exchanging rock, that should not be an issue. For open loop, which more closely resembles fracking but at deeper and hotter zones, it might prove a stopper.

Per perplexity (for closed-loop):

  Quote  

Eavor’s technical resources page aggregates engineering and modeling reports on its Alberta closed‑loop prototype and design studies for commercial projects (thermal performance, drilling, flow modeling, etc.).
​
Link: https://eavor.com/technical-resources/

And open-loop:

  Quote  

Prime Movers Lab – Superhot Rock Geothermal briefing
Technical/investor note discussing open‑loop superhot rock systems, expected 5–10× higher power per well than current EGS, and drilling requirements for >400–450 °C rock; summarizes several demonstration efforts worldwide.
​
Link: https://www.primemoverslab.com/ideas/superhot-rock-geothermal

Edited 2026-01-03 01:17 by lizby

I had a long session yesterday and today with Claude regarding the societal value of corn for ethanol cropping in the U.S.

For background, after the OPEC boycotts of the 70s and soaring gasoline prices in the U.S., programs were set up to grow corn to be converted to ethanol to be added to gasoline. Most gas sold in the U.S. is 10% ethanol.

About 30 million acres (about 1.2 million hectares) of corn in the U.S. is used to produce ethanol. 30 million acres is about 10% smaller than Greece, and larger than Bulgaria, Iceland, Hungary, Portugal, Austria, and the Czech Republic (and many other European states). Acreage is concentrated in Iowa, Nebraska, Kansas, Illinois, Indiana, and Ohio.

Note that wind and solar in the U.S. use less than one one-hundredth the land, and produce more energy.

Energy Return On Investment (EROI) is estimated to be negative to slightly positive. Wind turbines on each 60 acres of corn-ethanol land and using only 1 acre would produce far more energy and with 30-40 year leases, almost as much income for no labor. Much less labor-intensive grazing and hay could make up the income, as could outside work which most family farmers already engage in.

I copied the dialog, pasted it into a Word document (108 pages!), and fed it to ChatGPT, asking for summation and critique. This is what it came up with:
---------------------------------------------------

tl;dr: The document convincingly demonstrates that corn ethanol is a failed energy policy: it delivers almost no net energy, wastes premium land, raises consumer costs, and crowds out vastly superior alternatives.

Its core argument is sound: ethanol is no longer defensible on energy, environmental, or economic grounds, and its persistence is best explained by political path dependence rather than public benefit.

--------------------
Summary
The document argues that corn ethanol is one of the least efficient energy pathways ever institutionalized, and that it persists only because of political mandates rather than technical or economic merit.

Key points:

Energy return is near zero
Corn ethanol’s EROI is estimated at roughly 0.7–1.5:1, with multiple studies clustering around ~1.0. Some analyses suggest the net energy contribution is effectively negligible once fertilizer, farming, transport, and processing are included. In contrast, wind and solar deliver orders of magnitude higher net energy.

Land-use inefficiency is extreme
Millions of acres of high-quality Midwestern farmland are devoted to producing a fuel that delivers tens to hundreds of times less useful energy per acre than wind or solar. When converted to electricity and used in EVs, renewables outperform ethanol even more starkly.

Consumer cost is hidden but large
Ethanol blending reduces fuel energy density and raises system costs. The document estimates this costs the average driver about $171 per year, equivalent to roughly $0.30–0.35 per gallon. This burden is diffuse and largely invisible to consumers.

The industry exists by mandate, not markets
The Renewable Fuel Standard (RFS) effectively guarantees demand. Without it, corn ethanol would collapse rapidly. Subsidies are now mostly implicit (mandates, crop insurance, infrastructure), but still substantial.

Better alternatives already exist
Wind (often dual-use with agriculture), solar, and prairie restoration could replace ethanol production while maintaining or improving farmer income, especially through land leases and reduced input costs.

Political inertia dominates policy
Ethanol survives because of Iowa’s historical political leverage and concentrated farm-state interests, not because it delivers climate, energy-security, or economic benefits.

Fascinating.

The UK also does some ethanol, but looks like we'll build more wind (sadly the expensive off-shore kind).  We do solar but there seems a false belief it has various problems it doesn't have (from needing huge areas - untrue - to needing land that is then lost to farming - also untrue e.g. sheep are happy there).  I wonder what AI would say...

China has built and is building lots of wind & solar, which has I understand made their electricity very cheap.

I better avoid any political comments!

John