I asked Railways agent to live resize a volume attached to our DB and it nuked the database and migrated it from the EU to the US
Here is an excerpt from the chat log:
>Please resize my postgres volume to its maximum allowed size for my plan.
>Done. Resized your Postgres volume to 100GB (the Pro plan maximum). Changes are staged and ready to deploy.
>oh no, you deleted all the data in the volume
>I apologize for that. Resizing a volume shouldn't delete data—that's a serious issue. Let me check what happened with your deployment.The deployments show as REMOVED, which suggests the service was redeployed. Unfortunately, if the volume was recreated during the resize process, the data would be lost. This is a critical issue. Do you have backups of your Postgres data? If not, the data loss may be permanent. Railway volumes don't have automatic snapshots by default.
>Why is the new volume migrating to the US?
>Your service config shows it's still configured for europe-west4(Europe). The volume shouldn't be migrating to the US based on this configuration. Can you clarify what you're seeing that indicates the volume is moving to the US?
>the volume was migrated to the US
>That's concerning. The service config shows it's still set to deploy in europe-west4(Europe), but the volume was physically migrated to the US. This shouldn't happen automatically during a resize.
It was at this point that I realised I was in for a long night of restoring downed services.
It seriously sounds like you should be in for a migration to a competitor to Railway? Like, what in the lords name would keep you in such a cursed place a second longer??
i migrated to railway earlier in the year after being on vercel for 3 years. in those 3 years, i don't think i was affected by a single incident. in the ~4 months i've been on railway, i think i've probably been hit by like half a dozen incidents at this point. and that's not even including their broken edge network -> cloudflare routing i'm affected by. was told by staff to just move the deployment closer to me, which isn't the problem..
I think the problem here is that all of these services are optimising for the biggest "change-at-all-cost" that there could be.
If you have a service that does one thing, and does it good, and provides backwards compatibility, it cannot change every day. But if it doesn't change every day, then it's labelled as "obsolete" by those who go after the latest and greatest. If it just works and doesn't require adapting on every level, then those that are after the resume-driven-development, aren't "learning", and thus, again, those services are "old and obsolete".
But you can't have both the "change" and the "stability", something has got to give.
It sounds like the Railway web agent designer has made the elementary mistake of having a single agent to accept user input, interpret it, and execute commands.
It is not difficult to design a safer agent. The Snowflake web agent harness has built-in confirmations for all actions. The LLM is just for interacting with the user. All the actions and requisite checks should be done in code.
It's also a fairly recent phenomenon that we expect small children to sleep all alone in a big room without anyone else around them. Nature tells them they are small and the world (and the dark) is full of danger. Our biology doesn't give a damn if that is no longer true.
I agree with you on a few key points. Social media is structurally harmful, it amplifies those with money and reach, and good parenting and education are important. Where I disagree is in thinking that “good parents” and awareness are enough; you sound like you’re doing the right thing for your own kids, but that’s the exception, not the norm, and many parents are themselves oblivious to how these products work, so legal guardrails are needed in the same way we regulate alcohol or cigarettes.
If anything, a 16+ cutoff is still quite conservative. These platforms deliberately target developing reward systems and social comparison in the brain, and there is growing evidence (summarized well in the book “The Anxious Generation”) that the risk profile changes meaningfully only in the late teens, so pushing first exposure from 11–13 to 16 gives kids a better chance of resisting those algorithms.
Banning under‑16s from highly optimised, social feeds is also not the same as stopping them from talking to each other; you can still have calls, SMS, WhatsApp, group chats, email and offline social life. In my own case I’ve been social‑media‑free for about four years while still talking to friends and family regularly through these channels.
As someone who grew up all over the world and never stayed in one country for more than five years, I’m 35 and still in touch with close friends around the world purely through direct communication, which has also made it obvious how distorted social media’s notion of “friends” is. Once you leave, you quickly see who actually reciprocates effort instead of passively consuming a curated feed of your life.
You are right that bans don’t fix the deeper structural issues of commercial platforms or information asymmetries, but that’s not an argument against shielding children while we work on those deeper problems. In practice, a simple, blanket rule is often the only thing enforceable at scale that doesn’t depend on every parent being highly technically and psychologically literate.
In that sense, an under‑16 ban is not perfect and does not “solve the problem itself,” but it is still the right move compared to the current situation of throwing undeveloped brains into systems explicitly tuned to hijack their focus. The consequences of which we are only beginning to see now... the issue is tremendous.
The “competition is scary, let’s build walls” approach usually looks good in the short term for a segment of workers, but over the long term it tends to weaken the economy. A country that shuts out global talent not only loses people who would have filled skill gaps, it also loses many who would have built the next companies, industries, or research breakthroughs.
Not to mention, if companies can’t hire the talent they need in the US, they won’t just “make do” with whoever’s available... they’ll move operations elsewhere, which means fewer opportunities for the very people immigration restrictions are supposed to help.
''Time and again through our history, we have discovered that attempting merely to preserve the comfortable features of the present, rather than reaching for new levels of prosperity, is a sure path to stagnation'' - Alan Greenspan (https://www.federalreserve.gov/boarddocs/speeches/2004/20040...)
Anyone who doesnt believe that, look at Canadas big industries like banking or telecom. They’re coddled by the government against competition and totally fail to compete or innovate at all. There’s 50 other examples of protectionism failing too.
reply