6,109 karma · joined November 5, 2013
Your error lies in thinking Opus 5.5 is equivalent to a "minion". The "5 software developers" in my example were meant to stand in for "reasonably competent, above-average developers", and not that the architect is the only one on the team who can "think".
Of course, it may well be the case that you are working in an elite sector of the industry where even the bottom rungs are filled by the top 20% of software developers. Possible, but unlikely, so I'm still leaning towards "you're holding it wrong".
Edit: There is a loophole, though. Article 146 allows the German people to replace the constitution in its entirety.
LLMs, even in a good harness, are deceptively simple, but in reality rather complex tools. They're good at grasping intent, but they can't read your mind, they might not have access to the full context of your business, and they require learning how to use them properly.
If that is true, then only because "most people" have no understanding of what differentiates programming and math from "computation". Computers (as the term suggests) have always been extremely good at the latter, and useless at the former. It's only 2–3 years ago that computers, by way of LLMs, have started being good at the former.
1. Modeling and analyzing spinning, three-dimensional objects goes far beyond "basic maths".
2. The prompt was for an SVG of a realistically impossible situation (pelican riding a bicycle), which together already implies a stylized depiction. Why on Earth would you expect it to generate a 3D model of a bike, do a physics simulation on it, iterate until it satisfies certain contraints which are only hinted at in the prompt, and then project it down to a simplified 2D cartoon drawing? That's not how LLMs work, and that's not how we want them to work.
So did the Democrats. They clung to the worst possible choice, and in the last minute replaced him with the second-worst possible choice. Absolving them of fault and putting 100% of the blame on Trump voters is the fantasy of the Left.
So unless you can show that it approaches all the other frivolous consumption that humans love to waste resources on, maybe we can get back to experimenting with cool technology and talking about it, on this website called "Hacker News"?
Except that they're absolutely huge and heavy for any halfway decent screen size and resolution. If I were to replace my two 24-inch screens with CRTs, I'd need a second desk for them alone.
It's not that hard to understand. Here, I've linked it for your convenience: https://news.ycombinator.com/item?id=49765890
I'll file this under "blatant lie" unless you can provide at least three reliable sources for your claim.
This may sound like a loaded question, but I assure you, that's not my intention. If you want to provide for those "invisible" homeless, who aren't drug addicts or mentally ill, shouldn't the primary volunteer pool consist of exactly those invisible homeless people? Or in other words, once you have organizers, why do you need external volunteers for cleaning the showers?
I do. I grew up with 5 siblings, and having brothers and sisters is very, very different from having your own children. My relation with and my emotions towards my children is very different from my relation with and my emotions towards my siblings, both now and when I was still living with them in the same house.
You're describing a commodity. However, the commodity isn't the tokens, but the compute capacity, i.e., serving a model. And compute capacity isn't a currency — at least not, until you can acquire compute capacity from one party and exchange it with another party.
dgellow is absolutely right: tokens aren't a currency, nor can you trade them, nor are they fungible. The original claim that "tokens are just a type of currency" [1] makes no sense.
That would make society better, I agree, but I don't see how that would lead to a reduction in theft, or crime in general.
> And if you are still worried about theft in the mean time, you could try looking at wage thefts […]
I'm not worried about wage theft, no. I am worried about theft of my personal property, though. And I notice that you haven't proposed any credible path to reducing it, beyond an incredibly generic "make society better", whatever that means and however you want to achieve that.
Phew, good to hear. Here I thought it would be a hard and complex problem, with lots of unknown unknowns, difficult political compromises, a generation-spanning efforts and many potential solutions with uncertain outcomes, partially contradicting each other.
Instead, we just have to make society better. So, what's step 1?