Qworg

You don't have to pay more - I wouldn't switch to an open source harness on a whim, but your harness/cheaper agents can always call Claude Code headlessly.

For the same reason you don't have a small coal power plant in your backyard - scale matters.

The person picking them does? We're told continuously how tremendously smart and wonderful they are.

Reminds me of MechMania at UIUC - exciting!

Skeets is what the community wants, but the company does not (for obvious reasons).

Humans are also not trustworthy. So we build systems to capture their nondeterministic output and solve the issues that emerge.

This was the role of those "unelected bureaucrats" in the US that some folks decry.

It is far shorter than a fiscal quarter - the next market open is all that matters.

Thank you for posting this! I just finished a MUD engine and I was looking for a way to expose it to a small community of technically minded folks.

What are the knock on effects of lowering the total number of people/the velocity of money/the number of companies in America?

Canada's housing supply cost issues are driven by a wide variety of factors, very little having to do with immigration and far more with a small number of wealthy families owning a huge amount of land and a larger number of wealthy people holding many homes.

If you enjoy the podcast or the newsletters, I do recommend the Discord (https://discord.gg/oddlots) - the folks there are generally very smart and it is a great place to discuss everything from the economy to climate to transportation to defense.

Mentioned, but there's usually a discussion.

Your responsibility as a developer in this new world is design and validation.

A poor foundation is a design problem. Throw it away and start again.

Both TOWs and M47 Dragons are "remote controlled".

Given what you need, you should look at a Telo.

https://www.telotrucks.com/

Not launched yet though.

Your team's fixed preferences get stored into your .agents.md file so you don't type it over and over.

If you change your preferences, the team refactors.

While the methodology wasn't published, Microsoft did something similar for Flight Simulator.

https://www.smithsonianmag.com/air-space-magazine/flight-box...

FIS is just waiting for them to pay $250k/enabled API call to make it happen...

Come now - you really believe that Elon saw DOGE as a good faith effort to cut costs in the government?

For someone with such a vaunted intelligence, he was either dumb or complicit. "Working things out from first principles" would have had him leave after the very first step.

To make it more concrete - here's an example in Chinese: https://en.wikipedia.org/wiki/Grass_Mud_Horse

Postal banking existed in the US in some form until 1967. We could (and should) bring it back just for the reasons you stated.

https://en.m.wikipedia.org/wiki/United_States_Postal_Savings...

There are places in the US where the bank drives to the town once or twice a week, since there's otherwise no way to get cash or transact.

The issue with your last statement is that it _is_ part of your job and an increasingly important one at that.

It is _also_ your job to make them less bad - this is good because your incentives are aligned.

If they both can't be of use and can't be made better, then you need management to step in.

What are robots or not is a point of debate - there are many different definitions.

Generally, it has to automate a task with some intelligence, so dishwashers qualify. It isn't a existence proof (nor did I state that).

The wits in robotics would say we already have domestic robots - we just call them dishwashers and washing machines. Once something becomes good enough to take the job completely, it gets the name and drops "robotic" - that's why we still have robotic vacuums.

I'm not saying it has to be perfect.

I'm saying that this outcome will never exist because more has changed than just the plant closing. If we coupled "reopen the plant" with "the plant makes entirely new things" and "the plant trains local workers to take these jobs" and "the plant pays above local service/construction wages" and "the plant will be successful in geopolitical competition" and "the plant can do 10x the amount of business due to advances in automation to get to the same level of employment" and on and on.

We could solve _each_ of these problems, absolutely - but they are all interlocking parts of a wicked problem. Blowing up the economy and threatening a global recession won't actually solve any of these.

It isn't a bad thing - unless you don't have a job/have been stuffed with the idea that meaning and good pay could be yours if not for those foreigners.

It isn't just "reopen the plant" - it is "reopen the plant and match economic conditions in the time period from the 1950s-1990s".

Just reopening won't bring back the comparably high wages from that time period.

You can see the report here: https://ustr.gov/issue-areas/reciprocal-tariff-calculations

Given that both elasticities were set to cancel each other, that's why you get a flat trade deficit/imports calculation.

This is, sadly, the way a freshman econ student would calculate tariffs.

The admin has stated they are in addition to (totaling 54%).