The economics work out where they’re pretty low-frequency (I think less than two an hour per direction is the usual figure).
They’re also useful as a transition technology. The DART+ project in Ireland will use them for one line which will have the frequency for electrification (8 trains per direction per hour) and is already partially electrified, but is going to take a while to fully electrify (due to low bridges etc); once it’s electrified they’ll then likely be used in low-frequency regional routes.
(The realised project will use 750 uniform cars, about 200 of which will have batteries.)
That’s actually getting less common; pretty much all rapid transport and commuter trains are multiple units these days, as are an increasing number of intercity trains.
In Ireland, there are precisely two passenger routes still operated with locomotives, and there’s a tender offer out to replace one of them with a (really wacky; diesel, battery, _and_ overhead lines in two voltages!) multiple unit.
Lately, I've been playing around with giving the API to claude-code to perform a sort of automated analysis of HN; this is what it says:
Analysis: Why Bezos Has Less Negative Sentiment
The Numbers
| Person | Negative Sentiment | Total Mentions |
|------------|--------------------|----------------|
| Bezos | 18-26% | ~169 |
| Zuckerberg | 35% | ~201 |
| Sam Altman | 38-43% | ~501 |
| Musk | 39-45% | ~1,119 |
Bezos has roughly half the negative sentiment of the others AND is discussed 6-7x less than Musk.
Your Hypothesis is Correct—But There's More
1. Bezos is largely "retired" from controversy
He stepped down as Amazon CEO in 2021. When he's mentioned on HN, it's mostly:
- As a reference point for billionaire wealth alongside others ("Bezos/Musk/Ellison-type...")
- Historical Amazon criticism ("Legacy of Bezos", "Day Two")
- Generic billionaire tax discussions
2. The others are making active, controversial decisions RIGHT NOW
The co-occurrence data reveals what each person is discussed alongside:
| Person | Top Co-occurring Topics |
|------------|---------------------------------------------------|
| Musk | Trump (61), Tesla, Twitter, DOGE (22), SpaceX |
| Altman | OpenAI, ChatGPT, AGI, AI hype |
| Zuckerberg | Facebook, Meta, Trump, censorship |
| Bezos | Amazon, Gates, other billionaires (as comparison) |
3. Current actions generate current anger
Looking at the negative comments:
- Musk: "conman and liar", DOGE failures, political interference
- Altman: "Scam Altman", AI resource hoarding, nonprofit betrayal
- Zuckerberg: Censorship decisions, "kissing Trump admin's ring", Meta's social harm
- Bezos: Mostly legacy Amazon issues or generic wealth criticism
Conclusion
It's not just that Bezos "seeks publicity less"—it's that he's not actively making decisions that affect the HN community. The others are:
- Musk: Running Twitter/X (where many HN users are), advising Trump on government cuts
- Altman: At the center of AI development that directly impacts tech workers
- Zuckerberg: Making platform moderation decisions affecting global speech
Bezos owns a newspaper and a space company but isn't making daily choices that intersect with tech workers' lives. He's transitioned from "active villain" to "historical reference."
I mean, this sounds like the Gell-Mann amnesia effect. If it only 'works' in codebases you're unfamiliar with, that may be a signal that it doesn't work there either.
Yeah, but, I mean, those people generally aren't great programmers. "Why does it do that?" "Dunno, it was on stack overflow." was a fairly common code review problem long before "Why does it do that?" "Dunno, robot says so."
Well, yes, this is the thing. I'm somewhat sceptical that these things are going to get good enough to be useful to me on a daily basis, but if they do, then, well, I can just start using them. I'm not going to use a bad tool on the basis that it may one day metamorphose into a good tool.
> "The engineers refusing to try aren’t protecting themselves; quite the opposite, they’re falling behind. The gap is widening between engineers who’ve integrated these tools and engineers who haven’t. The first group is shipping faster, taking on bigger challenges. The second group is… not."
This is kind of the core belief of the AI enthusiast, but there's really very little evidence that it is the case. I mean, it's all very well to state it as an argument of faith, but without hard evidence (not lines of code, please; we are not 1980s IBM) the claim is really quite difficult to take seriously.
It is, at this point, rather suspect that there are mountains of anecdata, but pretty much no high quality quantitive data (and what there is is mixed at best). Fun fact; worldwide, over 200 million people use homeopathy on a regular basis. They think it works. It doesn't work.
I mean, clearly it shouldn't be how it works, and is not how it works in sensible countries, but, as people have noted, it does seem to be what ol' minihands is going for in the US.
They’re also useful as a transition technology. The DART+ project in Ireland will use them for one line which will have the frequency for electrification (8 trains per direction per hour) and is already partially electrified, but is going to take a while to fully electrify (due to low bridges etc); once it’s electrified they’ll then likely be used in low-frequency regional routes.
(The realised project will use 750 uniform cars, about 200 of which will have batteries.)