Because non-tech users don't know that. ;(

This is very important. There's a light-year of difference among a typical scholarly article, a physics paper, a math paper, or some kind of incomprehensible humanities bafflegab that no sane person could comprehend. The former, if it's not too technical, should be readable to the average undergrad. The second and third might not be because there are so many specialized concepts and so much specialized language. The latter (and I'm not indicting everything coming out of the humanities, but a lot of it) is incomprehensible because it literally doesn't make sense.

"I want to use claude code to run 10 unattended Chrome beta testers [more info about what is being tested and specifics]. Write me one or more md files to execute and give me instructions for enabling Chrome mcp, then give me an sh script to launch 10 separate Chrome instances on macos."

I wrote that exact prompt, more or less, a month or two ago, and then other iterations since then, and it's been working very well.

Using LLMs to create prompts for LLMs to use was a good realization.

This makes me laugh! I see classes at universities and colleges on using AI. Not just in the tech arena either, I'm talking liberal arts--med school, law school, you name.

As best as I can tell, "how to use AI" is more or less "don't be a dumbass."

To be succesful with AI, you need the same skills you need to be successful otherwise. Analyze problems, test solutions, think critically, etc. Unattended vibe coding or turning in of AI slop is the same as people who cribbed essays, copied and pasted from Wikipedia, etc.

IMHO, you still need to be a developer to be able to use AI effectively. If you start with a really solid schema, or an existing framework, AI is great at building on top of that. If you give it specific guidance for what and how you want it to develop code, it can do a good job. It is NOT just "lol write me a network utility lol" -- that is a path to disaster.

I've also had good luck with updating and modernizing older code, migrating to a new frameework, and refactoring.

If i'm using claude code, my steps go something like this.

1. Using plan mode, analyze the code base, create a thorough plan and testing strategy for XYZ (Or I provide SQL schema, or I provide a thorough plan of what I want to do, etc.)
2. Refine Claude plan mlutiple times until I'm happy with it
3. Start with writing a set of unit tests to confirm current behavior
4. Implement the first part of the project (this is not coding the whole thing in one shot)
5. Run unit tests, check for regressions.\
6. Rinse and repeat..

Steps 1 and 2 -- with no code being written -- are probably the most important parts.

I should also add that, imo, this will be a relatively short moment in time. I've seen people who are spinning up dozens of agents at the same time -- backend designer, frontend designer, security consultant, css specialist, etc -- that all work together and iterate amongst themselves.

We've been running a beta test of some new software, and one beta tester out of ~30 people hit an error. We could not reproduce it. Claude took ~5 hours, but using Claude to remote control Chrome, in conjunction with analyzing the state of the backend database, and auditing the codebase, Claude was able to reproduce the error and suggest a fix. In this case, we disagreed with the fix (rather, we went for a bigger logical change as opposed to a bandaid), but we've had really great luck with using Claude Chrome mcp as a beta tester.

And while I am still working on OpenWater and Alignable, the only thing I've gotten from LinkedIn in the past year is rewrite-your-resume scams

Did they take into account that most countries drive on the right? If you're walking the perimeter of a room counterclockwise, it might be because you are staying on the right.

But that was for Windows. Also, it can't even support Windows 11 in old Intel MBPs.

Thanks God I bought the last Intel MBP. I wanted to BootCamp and put Linux on it. Sure there's Linux for M series, but it is not ready.

I turned those off in mine!

You might want to read up on how current hybrid vehicles actually work, 'cause it seems you have more than one misconception going on.

I have. For instance, my latest vehicle is the Ford F-159 XLT,, the full-hybrid model of the F-series pickup truck line. Power train is:
  - 6 cylinder dual-turbo engine. (runs low power but approoximately doubles output when a lot is needed.)
  - 47 HP motor-generator "pancake" on the engine side of the ttransmission, to scavenge / return power to./from a 1.5 kWhr lithium battery.
  - 10-speed automatic transmission, working with the lithium battery;s main alternator to fine-tune match the engine/mogen to the current driving situation. Max power of engine plus hybrid mogen; 430 hp.
  - full four wheel drive.

So it's primarily a gas-engine power train with an electric-car motor mechanically coupled to the engine shaft. Many other hybrids, from the venerable prius onward, are similar, with plug-in variants having a big scavaging/peaking battery good for pure electric operation of tens of miles rather than a minute or so and a wall-powered charger added.

What I'm looking for is essentially a pure electric - totally electronic "transmission" consisting of alternator(s) between the batteries and the motor(s), plus a tiny engine-generator able to burn gas and feed some teens of KW of charging power into the batteries when running down the road or parked near it.
 

Do the Waymo batteries use one of the lithium chemistries including cobalt, or a non-cobalt chemistry such as lithium iron phosphate?

Cobalt chemistries have a higher power/weight and energy/weight ratio, which made them the go-to chemistries for vehicle batteries. But they also produce oxygen when the cells overheat, leading to an unextinguishable runaway fire hazard: A burning cell makes enough heat to ignite the adjacent cells, so the whole assembly of them goes. Bad enough when it's a car's worth, but a disaster if it's a shipping-container sized module of a utility energy storage site. (And even worse when the site is a building full of racks, which someone had "protected" from fire with water-spraying, equipment-shorting system, so the whole site burns up, as happened recently with one in California creating a toxic mess.)

That's why purpose-built stationary lithium energy systems use non-cobalt chemistries - heavier, but a shorted cell just kills itself without getting hot enough to light off its neighbors.

I want to see inexpensive plugin hybrids.

But not like the current ones, which are primarily an engine/tranny powertrain with a motor/generator + small battery for scavenging downhill/braking energy for later accelleration/uphill/cruise/power-boost.

I want ones that are primarily a battery-electric with a small aux engine-generator (say 15-20 HP range), big enough to power crusing with a bit left over for gradually charging. That would let you range-extend by the size of your gas tank plus fillups (i.e. indefinitely if only gas is available) or go from battery empty to back on the road in a couple tens of minutes.

The backup engine would only run at max-efficiency speed and could use an atkins-like cycle (see "liquid piston engine") to get the max power out of the fuel. Most operation would use power-grid charging (when available and cheaper than fuel).

Try saying that. /s