"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.

One of the problems America currently faces, is that we're still getting far too much science done, it's not costing us enough money, and the money it does cost is being wasted on paying the salaries of scientists instead of personally paying whoever contracts to kick back the most to political appointees.

I believe this will help solve all three problems.

Every single day, it seems like the White House does something to keep the ongoing Epstein Obstruction Scandal in the news. It's been the top story for months and every single day there's new news about it.

On Thursday, Todd Blanche, presumably acting under orders, spent all day obstructing the release of the information. And then he did the same thing on Friday. And now there's this UFO story, looking almost custom-made as a silly distraction. Blanche or Trump clearly wants to keep the illegal obstruction on voters' minds, as an evergreen topic so that it never goes away. But why?

What does Trump get by working so hard to persuade every American that he disagrees with a law that he signed, implying that laws is a bad idea and shouldn't be applied or enforced? What advantages are gained by an explicitly pro-crime agenda? What's the advantage of campaigning on releasing the files but then breaking my campaign promise?

I (naively?) think if I were in his position, I would comply with the law so that I don't go to prison for obstruction, and so people wouldn't notice every day that I'm still casually and continuously committing crime. I would let, no make the files come out, so that everyone can see the criminal witnesses confused me with the actual rapist, Biden. That would put me in a position where I'm seen as pro-law instead of anti-law, and it would also put to rest all the speculation that the "Epstein" files are actually mostly about me. Seems like that would be good for everyone, including myself.

So why commit obstruction when the releasing files will exonerate you and make all the problems go away? This strategy doesn't make any sense. What could I possibly be missing?

I feel like there's something incredibly obvious that everyone with a more-than-50 IQ has figured out about the president's lily-white innocence, but somehow I'm just too fucking stupid to figure it out. It's humbling, and makes me question my deeply-held faith in the president's genius.

In the 1978 film Midnight Express, during the famous "Section 13" (the mental ward/psychiatric wing) exercise scene, the prisoners are forced to endlessly walk in a clockwise direction around a central stone pillar, which they refer to as "the wheel."

Because Muslims perform the Tawaf (the ritual circumambulation of the Kaaba in Mecca) exclusively in a counter-clockwise direction, walking clockwise is presented as a symbolic inversion of their sacred practice.

When the protagonist, Billy Hayes, realizes how mindless and soul-crushing the clockwise routine is, he defies the prison's unspoken rule and aggressively begins walking counter-clockwise, literally "against the wheel" and into the oncoming traffic of the other inmates. Therefore, the direction the prisoners were originally never supposed to go...and the direction Billy uses to break his compliance...is counter-clockwise.

Then We The People need (or have needed) to become post-newspaper, indeed post-any-sort-of-centralized-media, since all centralizations are pressure points for coercion and compromise.

Make Usenet Great Again? There is No Cab-NO CARRIER

We decided "I really really don't want x to happen to me, so I won't x someone else." And then we agreed that x will be categorized as "terrorism" instead of "war."

Then recently (yesterday?) we Americans apparently changed our mind about whether or not it would be ok if Iran (or anyone else) blew up America's civilian water supply infrastructure, no big deal, so we're doing that now, telling the whole world that it's acceptable. It's just war, what can ya do?

For now, people can worry about what type of weapons to use and whether or not certain types should be banned.

But in the future, all the debates will be about will be "how do we pick just the right grid squares in which to Kill All Humans?"

I, for one, am glad someone is finally cracking down on explicit images. If you have words to say, post them as actual text! Don't just throw text onto an image and call it a "meme," because that's totally lame.

I would expect that our backward-ass leaders will instead get all nationalistic and prideful of the "homegrown" Microsoft monopoly

Then we must lead them down a better path.

"It takes four hundred thirty people to man a starship. With this, you don't need anyone. One machine can do all those things they send men out to do now. Men no longer need die in space, or on some alien world. Men can live, and go on to achieve greater things than fact-finding and dying for galactic space, which is neither ours to give or to take. You can't understand. We don't want to destroy life, we want to save it!" -- Blacula

In other words, the "gap" you describe is considered to be good news for the humans who have to do those jobs.

I say this jokingly, but I really did drink the Kool Aide, and I think it's just Kool Aide without any additional harmful ingredients. I'm seriously all for us at least striving to live a completely hedonistic lifestyle, where we never toil because our robots slaves do everything tedious for us.

I want to die in an Orion whorehouse, looking like a character from WALL-E. Only in my final moments do I want to learn the awful truth, when one of the green-skinned ladies' faceplate falls off, revealing a robot.

Ok, maybe it wasn't pure Kool Aide.

The premise is that you would understand how it works. Once we've glossed over the story of finding that holy grail, then you can build minds with different amounts of spite. (e.g. doubly-infinite for a TortureBot, or decreased for most other uses.)

Wait, are you suggesting I can simply hire humans, to design and manufacture these intelligent computers for me?!

Oh, duh, I get it! You're taking Bezos' own point of view, rather than the point of view of his engineers.

But how do the engineers create the intelligent computer? It's not hiring-people all the way down, is it?

What do you think is the right age for Carousel? As someone over 30, I think 30 is too young. ;-) But what age might we all agree isn't too young?