Several people have tried over the years. We all failed, because it doesn’t work.

The economics don’t work because no one is willing to pay.

The network effect doesn’t exist, because real people don’t post enough to get the flywheel started.

All the dark patterns exist because that is what users reward.

Sucks but it’s true.

Very likely they got the causality backwards. Every time there’s a big war, technology advances because governments pour resources into it.

Just burn the tokens. It’s an upfront cost that you pay once at the beginning of a project, or on a smaller scale at the beginning of a major feature.

For context, I’ve built about 15k loc since Christmas on the $20 plan, plus $18 of extra usage. Since this is a side project, I only hit the limits once or twice per week.

It’s really not. For anything substantial, the things that you do to manage an LLM are the same things that you should be doing to manage a team of human devs, even if the team is just yourself.

Documentation. Comments. Writing a plan and/or a spec before you begin coding. Being smart with git commits and branches.

You don't need to spend that much on "defense" when you're not invading countries every few years

You should look up how much NATO members in Europe were spending on defense during the Cold War.

What an understatement :)

It’s a lovely language but the compiler has got to be the most unreliable I’ve ever seen.

It crashes semi-frequently. And it will sometimes try to run analyses that are way beyond O(n). So you can have perfectly valid code that it can’t compile, until you simplify or reduce the size of some function.

They made a couple of Intel boxes in the very late 90s / very early 00s, but the company was already on the way out by that point.

I think Claude’s estimates are biased towards huge enterprise projects.

I asked it to estimate a timeline for a feature in my hobby project and it confidently replied, “4.5 weeks to code completion”.

Less than 4 hours later, the feature was done. I asked it to compare this against its initial estimate and it replied, “Right on schedule!”

I have completely given up on using it to estimate anything that actually matters.

It's a next-word-prediction-machine, not a calculator. It's not aware of the passage of time, or how long things take, and doesn't reason about anything. It's just very good at putting words together in combinations that look like answers to your inputs.

That's really useful for some tasks, like regurgitating code to perform a specific function, but it's basically useless for jobs like estimating schedules.

By that logic, the European members who didn’t meet their defense spending obligations for years and years have already left NATO too.

That's the implication the administration is trying to force.

Basically, we are leaving Europe because we no longer have a commitment there and concentrate on Asia and the Americas.

This has been a stated policy objective of ours for almost 2 decades now.

Unfortunately you can’t even get the RAM for $400 anymore.

I don't think 32GB is going to be enough lol

Also, you would want ECC for something this important.

I seriously wonder if doing the same build twice by two people in two locations wouldn't provide the same benefit and others for less money.

(I might be spoiled by sane reproducible build systems. Maybe F-droid isn't.)