vFunct

I actually don’t use them that way. I use 100 different agents on 100 different worktrees to develop 100 different apps for the overall project.

It pretty much is though. This is exactly what you'd do if you had 100 different employees.

You're confusing law and politics.

How many other comments do you see promoting the elimination of the US?

People that say things are done in "bad faith" generally want people to stay in their well established lane. The world doesn't work that way. It's fine to be on the edge.

There are large segments of even the own US population that sees the US as harmful to the world.

What are YOUR proposals on what should replace it?

The comment was about the US and how to deal with it going forward.

Everybody already knows about Gaza and how bad Israel is. The question now is whether the US will continue to exist.

I get tired of finance topics. Should we flag those as well?

Did you try not being the bad guy?

You DON'T have to kill children to steal their land, you know? You can totally not do that.

If that were true, then that society would not maintain an army or a police force, to enforce its political goals.

Violence is fundamental to political tactics.

And the cost of finding an agent outweighs the savings of hiring one.

Yah the boring stuff is unnecessary and economically unproductive. No one should be forced to be interested in things they aren’t interested in. I absolutely do not want to spend any time on the things you find interesting.

Life’s too short to figure out what kind of curtains are best for my home.

it would be bad for the US because now you just gave a labor competitive advantage to foreign countries.

America's economic strength is our skilled labor above and beyond anywhere else, BECAUSE of our universities. We are scientists, engineers, artists, experts. We do not perform manual labor - skilled or unskilled - that someone from Mexico can do. If someone from Mexico can do what we do, what exactly is our advantage?

Trump is trying to turn our labor force into third-world peasants, and that means our labor force will have to compete against third-world peasants. We spend thousands of dollars per student in our public education system to teach them calculus, chemistry, literature, world history, and so on, so they DON'T have to work manual labor jobs like oxen.

Yah it doesn't exist, since personal assistants do not exist.

The US labor force is at 4.5% unemployment. That's nowhere near enough for everyone to have personal assistants.

What will likely happen is you give it a separate sandbox bank/credit card account with a small budget, and it transacts from that. I doubt it'll buy a house for you anytime soon.

Honestly you wouldn't believe how good these models are if you haven't tried it. They really are amazing.

Yah I definitely want to be fulfilled by having to pick a health insurance plan or a car rental reservation.

Seriously, every little annoying thing in life is going to be automated, so you get to free yourself to do the things you really want to do.

MCP everywhere is going to be such a societal changer. Once your bank and credit cards get MCP servers, that's it. It's next level society.

Like, immediately, I want it to order me some groceries based on what it sees in my fridge and what I cook.

And to remind me to change my air filters. Or book my vacation for me, knowing I like a mediterranean vibe and Bistecco Florentine.

I am absolutely excited for all of this. It really is as big as the iPhone.

For a large project, the real human trick for you to do is to figure out how to partition it down to separate apps, so that individual LLMs can work on them separately, as if they were their own employees in separate departments.

You then ask LLMs to first write features for the individual apps (in Markdown), giving it some early competitive guidelines.

You then tell LLMs to read that features document, and then write an architectural specification document. Tell it to maybe add example data structures, algorithms, or user interface layouts. All in Markdown.

You then feed these two documents to individual LLMs to write the rest of the code, usually starting with the data models first, then the algorithms, then the user interface.

Again, the trick is to partition your project to individual apps. Also an app isn't the full app. It might just be a data schema, a single GUI window, a marketing plan, etc.

The other hard part is to integrate the apps back together at the top level if they interact with each other...

I’m just a user, trying out the models first hand on a large project, learning as I go.

Huge project..

Each model has their own strength and weaknesses tho. You really shouldn’t be using one model for everything. Like, Claude is great at coding but is expensive so you wouldn’t use them for debugging to writing test benches. But the OpenAI models suck at architecture but are cheap, so are ideal for test benches, for example.

Yah Claude tends to output 1200+ line architectural specification documents while Gemini tends to output ~600 line. (I just had to write 100+ architectural spec documents for 100+ different apps)

Not sure why Claude is more thorough and complete than the other models, but it's my go-to model for large projects.

The OpenAI model outputs are always the smallest - 500 lines or so. Not very good at larger projects, but perfectly fine for small fixes.

The challenge for LLMs over the next year is to get them to operate on large data sets/code bases with millions/billions of tokens through some kind of distributed hierarchical framework, with each LLM operating on a local set of 20k or whatever subset of tokens.

He had no idea about branding. You can’t just sell generic products that you can get at Amazon for maximum profit in retail. You actually need to have a differentiated brand.

For comparison, during that same time period, the retail successes were the designer collaborations, like Versace x H&M or Target x Rodarte, etc…

All Johnson had to do was bring in some designer collaborations…

Does this include Gemini 2.5 Pro API access? What are the API limits?

I blew through my $40 monthly fee in Github Copilot Pro+ in a few hours. =^/

That's not the simplest explanation, that's the most implausible, since people rarely act against their company rules. The vast majority of corporate decisions come at the behest of the company.

This was done by Musk, instructing his subordinates to alter system prompts to support his theory of "white genocide".

Elon decided he wanted to have Grok respond positively to allegations of “white genicode” in South Africa so he had his xAI engineers rewrite the system prompts to support the idea that “white genocide” exists. It then started talking about “white genocide” at every unrelated opportunity.

Really unethical AI behavior by Elon.

Use Claude Sonnet with an IDE.

Again,, please don’t normalize the US government’s viewpoint.

The vast majority of the world says they’re freedom fighters.

[flagged]

If it were well defined, there wouldn't be any debate on it. And no one is interested in your designated definition.

The only valid definition is: "terrorism is anything I don't like"

This is why Republicans called it a "terrorist fist bump"

Can it fill a wine glass to the rim?

Yah I heard about people trying to debunk it over the years, with zero effect.