As part of the contract for construction, the county or city must buy a certain amount of water every year.

Because desalination is not economically feasible, the water is more expensive and this extra subsidy raises the cost of the water bill.

This is how it works for the facility in San Diego County.

Building a desalination facility is economically hard to justify because the break-even point seems far away. It also assumes the state won’t eventually create a state-wide solution, which would benefit from a state-level economy of scale that a city/county effort might not.

This is like saying I know how to do plumbing so now I’m going to do all my own plumbing.

Yet I will still pay for a plumber. I wonder why.

That’s why California has had dozens of state laws passed in the past 3 years that override many city and county ordinances to force additional supply. Lawmakers knew the only solution was more housing.

These bills permit the construction of denser housing near transit, force cities to actually meet housing quotas, allow the state to override a city’s zoning to permit more housing if they don’t make a good faith attempt, loosen the rules to build ADUs, and many other changes.

Is it ideal that we had to get to this point? No, but housing wasn’t being built.

And the biggest reason is, learning from history, the instability of food prices destabilizes nations.

There have been many “bread riots.”

Bread is much cheaper today (at least relative to incomes) than in the days of bread riots.

Wheat is HEAVILY subsidized.

But how can you tell if it was lack of recognition?

I wouldn’t be interested in a 2 FPS video either — in fact I would probably avoid looking at it, whether I recognized the humans in it or not.

I mean it's a dog so you can't exactly ask them; but this was a dog that would bark at every other dog. If he wasn't barking at Hooch because Hooch was only showing up at 24 FPS, then I'm inclined to think he didn't recognize Hooch as another dog.

I would, if they worked even 90%.

I mostly set timers because it’s one of the few things that always works.

I find this problem self resolves when someone else sends them raw AI output.

I wouldn’t grow food hydroponically to save money, but growing food can get you really nice sweet varieties with stronger flavor than you can get in stores (since you can pick them at your convenience).

That said, I prefer growing outdoors if you have the space. It’s a total different maintenance (with way more bugs) but it also doubles as decor better than my hydroponic setup ever could.

CLI doesn’t work for your coworkers that aren’t technical.

Have you tried to use a random API before? It’s a process of trial and error.

With the MCP tools I use, it works the first time and every time. There is no “figuring out.”

>CLI doesn’t work for your coworkers that aren’t technical.

This actually isn't true. I've written bespoke CLI tools for my small business and non-technical people run them without issue. They get intimidated at first but within a day or so they're completely used to it - it's basically just magic incantations on a black box.

CLI’s and shell commands can be wrapped by and packaged into scripts, those scripts can have meaningful names. On Windows at least you can assign special icons to shortcuts to those scripts.

I’ve used that approach to get non-technical near-retirees as early adopters of command line tooling (version control and internal apps). A semantic layer to the effect of ‘make-docs, share-docs, get-newest-app, announce-new-app-version’.

The users saw a desktop folder with big buttons to double click. Errors opened up an email to devs/support with full details (minimizing error communication errors and time to fix). A few minutes of training, expanded and refined to meet individual needs, and our accountants & SME’s loved SVN/Git. And the discussion was all about process and needs, not about tooling or associated mental models.

MCP also doesn't work for coworkers that are technical. It works for their agents only.

CLI works for both agents and technical people. REST API works for both agents and technical people. MCP works only for agents (unless I can curl to it, there are some HTTP based ones)

This should be trivial if you have proper API documentation in something like swagger. You can generate a cli tool with no "figuring out" anything either.

Nothing is “trivial” when you combine humans and computers. I worked at the MIT Computing Help Desk during my undergraduate years. We joked that we received callas from Nobel laureates who could find subatomic particles but couldn’t find the Windows Start button.

My company is currently trying to rollout shared MCPs and skills throughout the company. The engineers who have been using AI tools for the past 1-2 years have few, if any, issues. The designers, product managers, and others have numerous issues.

Having a single MCP gateway with very clear instructions for connecting to Claude Desktop and authenticating with Google eliminates numerous problems that would arise from installing and authenticating a CLI.

The MCP is also available on mobile devices. I can jot down ideas and interact with real data with Claude iOS and the remote MCP. Can’t do that with a CLI.

If you can't write a good CLI I doubt you could write a good MCP

This applies well if you’re writing code.

But often I am using Claude to investigate a problem like this “why won’t this mDNS sender work” and it needs a bunch of trial and error steps to find the problem and each subsequent step is a brand new unanticipated command.