psadauskas

The part I find grating is the attempts to punch everything up. ("It's not X. It's Y"). Like, its a react badge component, it doesn't need punching up. You didn't find the smoking gun in a murder mystery, just a misplaced CSS rule.

Undocumented immigrants are a useful scapegoat politically, because it allows those in power to point the finger at them for all the country's problems, but those immigrants have no political power themselves since they can't vote.

Additionally, it gives business owners a bunch of workers they can exploit, since those workers can't go to the police or report them to the labor board.

> A computer can never be held accountable

> Therefore a computer must never make a management decision

I'm the same. They don't even have to "support" it, just stop doing everything they can to prevent it. Volunteers will support it for them.

I once had it "fix" a failing test by changing it from (in Ruby pseudocode):

    assert_eq foo, bar

to:

    assert_eq foo, bar if foo == bar

Or, legalize it, so there's no incentive for anyone to drive 90 kilos of meth across the country. People don't do meth because they want to, they do it because they feel like there's no other options. If we as a society spent half as much money helping people as we do punishing them, then everyone would be much better off.

As a programmer, I've been telling people who ask:

> AI has taken away almost all the tedious parts of my job, which is nice. It's also taken away almost all the fun parts of my job, too, though.

Half of all dentists graduated in the bottom half of their class.

Even Candy Crush, a huge part of what made it successful, was the tiny details. The bright colors, the art, the subtle and not-so-subtle animations... An LLM can technically do all that, if you keep reminding it, and have strong rules, and constantly keep it in check, but there's no way it would do it on its own and keep it consistent and coherent.

Eg, if the tall green pill candy and the red round one both scale by exactly 3px when you drag them, it might still "look" wrong, and get into uncanney valley territory. And that's even assuming the LLM picked the same value to scale when you prompted it to "add a red candy", or it picked a different one arbitrarily.

I've tried making games a few times, or even CSS animations, and I can tell that they don't "feel" right, even if I have no idea why, or what to change. I have mad respect for artists and animators that can manage that, and I have no idea how you tell an LLM "It doesn't feel right when I drag the candies", and have it be able to figure out that a tall vertical candy needs to scale differently on the X and Y axis than a round one.

The advantage I see for MCP over CLIs or APIs, is that once you release the CLI/API and people start coding scripts against it, your interface is set it stone, you're never allowed to change it again, or you break everyone's scripts.

With an MCP, agents are very tolerant of changes, since each usage is fresh with no prior knowledge, so nothing to break. This allows you to experiment and iterate on the MCP, see how people use it and what gaps you still need to cover. Once it stabilizes, you can lock it down into and API/CLI interface.

Yes. They decided that it was more valuable spending a trillion dollars bombing people halfway around the world (and enriching weapons companies in the process) than it would be to spend a few billion advancing science.

And even if you do manage to find such a place, there is exactly zero guarantee that they won't hire someone above that _does_ ruin the better conditions you've enjoyed since you started. A successful company is persuaded by the board to grow the leadership team, and the number of sociopaths at that level means anyone that joins has a decent chance of being one.

My current pet peeve is when it said like that, but the "yes but" its contradicting is from its own talking-to-itself phase, not anything I ever said or implied.

I know X can't do Y, that's why I never told it to have X do Y, I don't know why it feels the need to "correct" me that having X do Y is the wrong approach.

During the industrial revolution, people thought that all these new machines and factories and electricity meant that everyone would only have to work 4 hours a week since it made everyone so much more productive.

That's not what happened, though. Everyone worked the same amount for the same pay, just in more miserable repetitive working conditions, while the factory owners kept all profits from the gains in productivity.

One "side" is actively and intentionally destroying the country, the other is letting them. It's not that both sides are bad, it's that both sides are the same side, working for the same people.