I think it's more about the interface than the output. The agent can add stuff to a markdown file with simple cli commands rather than a more complex editor or file interface.
I love your content, but I wish you'd make your blog theme responsive for wider screens/non-mobile. I prefer to read content like this on a large screen.
Showboat seems like it could actually be quite useful for humans too, just for making quick notes from a CLI without opening an editor. The "pop" command makes me wonder if there would be a benefit to also having an array-like in addition to the stack-like interface. It seems like it would be fairly trivial to generate an index of markdown blocks so that they could be edited individually.
I like the idea of Rodney, but I wonder if you might actually have better results by asking the agent to generate equivalent Selenium scripts instead. I'm specifically suggesting Selenium because it's been around so long so I assume there's a lot of Selenium in the LLMs training data, but there are other options that might work too.
I've had a similar experience where I'd be craving a beer, but not really craving alcohol since wine or spirits didn't sound appealing at all. I think it might actually be the hops and not the alcohol.
I don't know if it's common in the UK, but in the US, a lot of breweries have started making hop water. I've found that it can really scratch that itch. Even just a hop tea might work if you can't find pre-made hop water.
It sounds weird, but it's actually delicious with nice floral and citrus notes and just enough bitterness that you don't drink it too quickly.
Preface: Most of my understand of how LLMs actually work comes from 3blue1brown's videos, so I could easily be wrong here.
I mostly agree with you, especially about distrusting the self-interested hype beasts.
While I don't think the models are actually "intelligent", I also wonder if there are insights to be gained by looking at how concepts get encoded by the models. It's not really that the models will add something "new", but more that there might be connections between things that we haven't noticed, especially because academic disciplines are so insular these days.
I think it would be fun to see if an LLM would reframe some scientific terms from the time in a way that would actually fit in our current theories.
I imagine if you explained quantum field theory to a 19th century scientists they might think of it as a more refined understanding of luminiferous aether.
Or if an 18th century scholar learned about positive and negative ions, it could be seen as an expansion/correction of phlogiston theory.
I really like the interactive graphs but I can't see how you're accounting for the cost/value of the use of the property. The return on investment for paying rent for 30 years is exactly $0.
I think what you're really comparing is if the stock market or the housing market is a better investment, but you're not taking into account that the use of the property has value.
Think of it like a landlord, you're not just investing in a house to let it sit empty and then sell it later, you're buying it with the intention of collecting rent every month. Or to put it another way, it's like comparing the prices of dividend and non-dividend stocks without accounting for the dividend.
For a personal home, you need to account for the fact that owning it means you live there rent free. There's a monthly cost for the mortgage, but that cost doesn't increase with inflation the way rent does. Owning a home comes with expenses for upkeep and taxes, but once the mortgage is paid off those are the only thing you have to account for.
I think a lot of the "low-birthrate" fearmongering is just a way to distract people.
Overpopulation was projected to be an issue, but we actually addressed it pretty well over the last 50-75 years and global average birth rates are in a pretty good place now.
Depending on your current salary, you might make more by collecting unemployment which has the benefit that you can make finding a job your full time job.