"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.

tl;dr it seems like it's been different things at different times, officially, and that NeXTSTEP has been used for a long time.

From the Wikipedia page, this 0.9 release doc lists "NextStep" as a registered trademark.

https://vtda.org/docs/computing/NeXT/NeXT%200.9-1.0%20Release%20Description.pdf

Some CD images show all caps:

https://auctions.c.yimg.jp/images.auctions.yahoo.co.jp/image/dr000/auc0403/users/dec444a55bdd461a83b1b7c3f2c8e7fa3a731b8b/i-img1000x901-1678086322oe8huf16.jpg

Some show mixed:

https://wagtail.cds.tohoku.ac.jp/coda/topics/nextstep/index.html

1.0 manual goes with "NEXTSTEP":

https://dn710300.ca.archive.org/0/items/NeXTSTEP_User_Guide_1994/NeXTSTEP_User_Guide_1994.pdf

1993 book uses "NeXTSTEP"

https://simson.net/ref/1993/NeXTSTEP3.0.pdf

This marketing flyer uses "NeXTSTEP"

http://www.kevra.org/TheBestOfNext/NeXTProducts/NeXTSoftware/NS-Release3/files/page625_1.pdf

It's clear the original trilogy was lightning in a bottle for many reasons, and it's clear that Marcia Lucas and other skilled editors had an absolutely huge impact. But can you really say the editor is the "more talented" Lucas? Seems to me that for a time, whatever partnership George and Marcia had personally and working together, worked really well.

After the split, neither one of them ever created something as on target as the originals.

Then again, Star Wars is almost unique for the cultural impact it's had. Hard to do a repeat.

Just shows how sometimes connotations and visceral impacts of words change over time.

I learned about that movie from The Wall..

My kids call me a boomer when that happens to me. And yeah, it happens.

Though to be fair, I actually really like the side button -- the one on the lower right that is touch sensitive. I use it for activating and using the camera. I just ALSO sometimes activate it when reading in landscape mode. Oops.

But now you're in a position where a work can only be recognized as "quality literature" decades or even centuries after it was created and publicized. I guess that's a plausible definition, but I don't see much value in it.

I would also add that many governments deliberately preserve and publicize certain works not for their inherent literary value, but due to some message that the government wants to promote for many possible reasons.

IMHO, everything you just said boils down to "it's a matter of taste" or "I know it when I see it."

On one level, I don't disagree. Taking two fantasy authors I enjoy, Brandon Sanderson and Patrick Rothfuss, I would say that Patrick Rothfuss is the better literary writer, but at the same time, I enjoy Sanderon's books more and I enjoy Sanderson as an author far more. Both authors are highly literate and knowledgeable, and their works are clearly highly influenced and referential to many other works, tropes, and so forth. I would say Rothfuss's writing is more artful, but I don't know how to quantify that.

"Lasting value" is, just like, your opinion man, and (IMHO) boils down to spectrum of enjoyment.

I have done the same thing (both with actual LLM text and with my own writing). The detectors seem wildly inaccurate on all samples, and wildly inconsistent between different detectors.

I think of the Star Trek holodeck. There are many episodes that portray how human characters “write” holonovels. They design the characters, the personalities, the plots, etc., but the holodeck generates the dialog, responds to stimuli, and so forth.

I think it’s a pretty interesting possibility for table top especially. GMs could create a character plan that then operates as a Non-Player Non-GM Character. A wildcard in the game. I could see that introducing some interesting elements to play.

You lost me here. What happens in a human mind is not covered by copyright law? Are you talking solely internal thought processes that are never externalized in any way?

Because I can image a cartoon mouse all day long. Yellow gloves. Red shirt. Etc. But if I put that imaginary mouse to paper (no computer involved), Disney might have something say about it.

I wonder if something like this is where we may end up. Computer learning vs human learning may be one of the great legal (and moral and ethical) battles of our time.

I remember a time when any stupid idea that you could put ".com" on would get shit tons of investor money. The only thing it produced mostly was bankruptcies and the opportunity for small companies to buy needed equipment for pennies on the dollar. This AI craziness strikes me the same way. AI can be useful but it'll never be the "be all things", they rarely to live up to the hype. I've seen it too many times, the dotcom boom-bust, nano-technology, Ruby on rails; anyway COBOL had a good run.

As I said, I don't know what quality literature is. The Nazir piece reads like Joyce to me. Ulysses is certainly a classic, but I'm not sure I've ever met anyone whose read him outside of highschool or a college literature class! I can't stand it, personally, but props to the people who do love it. I went deep into the serialist music hole once upon a time, and I found a level of appreciation for something that had been unlistenable to me before. More power to people who find that in Joyce. Zahn is very well know and popular amongst certain nerd groups, but largely unknown outside of them. Eco's books have sold well, but do people actually read them? How many men read hockey romances or 50 shades?

I take umbrage at the term "quality literature!"

I believe literature should be evaluated primarily on an "do not enjoy...enjoy" spectrum.

Looping back to the topic at hand, I've said before that I'm afraid that one thing that LLMs may show is just how derivative and formulaic a great deal of human production is. (That's not necessarily a bad thing, either, IMHO.)

My wife grew up in Minnesota. I know, unfortunately, more about hockey romance novels than I ever wanted to.

"Amish porn" is a new one to me!

As I understand it, women are by far the biggest users of public municipal libraries today. I'm not sure if the current selections are a "chicken" or the "egg" in why that is.