One of the top replies on twitter to the OP can be boiled down to "you treat AI as a junior dev. Why would you give anyone, let alone a junior dev, direct access to your prod db?"
And yeah, I fully agree with this. It has been pretty much the general consensus at any company I worked at, that no person should have individual access to mess with prod directly (outside of emergency types of situations, which have plenty of safeguards, e.g., multi-user approvals, dry runs, etc.).
I thought it was a universally accepted opinion on HN that if an intern manages to crash prod all on their own, it is ultimately not their fault, but fault of the organizational processes that let it happen in the first place. It became nearly a trope at this point. And I, at least personally, don't treat the situation in the OP as anything but a very similar type of a scenario.
The access is supposed to be managed in a way that prod would only be accessible with multi-user approval. And that's without even mentioning the fact that storing a key in the source code is a big no-no.
If an LLM can just do whatever after discovering a magic key (in the source code, of all places), with no multi-user approval, it is pretty much the poster child example of an issue with the process that I was talking about earlier.
"and honestly, ..."
"heres the thing ..."
[em dash every paragraph]
Smells like default Claude voice. I like the ideas, but if someone can't be bothered to proof read their own article, then I don't know why we should trust that any of it was human generated.
Couldn't agree more. Worth pointing out that sites owned by Meta and Twitter in particular have become much more hostile to signed out users - often impossible to view a business' listing without a signed in account. Walled gardens are going to wall, of course. But I'm not sure how much small business owners realise that a proportion of traffic / interest has much more difficulty in finding them.
You are right that Taiwan doesn't. But it has consequences, Taipower is forced to undercharge against market prices, but is backstopped by the government.
At the end of the day, it's a global market, and if you want it 'cheap' someone has to pick up the tab. Either it's taxpayers now, taxpayers in the future or consumers now.
Not sure I agree with you. For lower ability models, yes. Claude Opus 4.6 is incredibly capable, so it's odd to me it has this residual 'misspeak' behaviour.
That's the issue, people are anthropomorphizing those models, but... they're all the same (conceptually). They just do random hallucinations, trying to make those hallucination match the "reality" (of their training data) as much as possible
Vitamin D is toxic (and ultimately fatal) at high doses, which is why the 'suggested' dosages of between 400IU and 1000IU are so conservative. You may need more, but you should get a blood test.
THIS. And not just for Vitamin D. Not everyone absorbs / metabolizes / excretes vitamins or minerals in the same way. Learning whether or not you're an outlier can be done either the safe way, or the dangerous way.
I'm running duckdb over 500gb of parquet on a largish desktop (50gb ram) and it's been smooth & fast. I guess OOM issues will matter at some point, but I think it's going to be in the top 1% of real world use cases.
With a decent SSD (or eight), spilling to disk is really not bad these days! Yes!
And if that's still not enough, if you just need to crunch data a couple times a week, it's not unreasonable to get a massive massive cloud box with ridiculous amounts of ram or ram+SSD. I7i or i8g boxes. Alas, we have cheap older gen epycs & some amazing cheap motherboards but RAM prices to DIY are off the charts unbelievable, but so be it.
This is very cool! I built something a little similar https://blognerd.app. I'm really interested in the RSS remixing idea, though I didn't quite crack it. I'll be interested to see how you get on
However the moral of this story is nothing to do with AI and everything to do with boring stuff like access management.
reply