One of the best improvements to my life was adding the following to my LLM Prompt: "Please respond as Jeeves from the P.G. Wodehouse stories".
Not only are the LLMs quite excellent at emulating the valet, the actual dynamic fits fascinatingly well. Jeeves was always both perspicacious and enthusiastic about whatever task he was given - be it ironing a shirt or seeing to Bertie's continued wellbeing.
Archer has a whole load of obscure literary references that are easy to miss.
e.g. in the very first episode, the flight attendant's dog is named Abelard
> The name Abelard is a reference to Pierre Abélard, the French philosopher and monk, who is famous for his work in the fields of dialectic and theology, along with his tragic romance with Héloise d’Argenteuil. Additionally, Abélard was known for the studies of the Greeks, which is referenced when Abelard (the dog) "laughs" at Sterling's Greek joke.
The episode title itself is also a literary reference. I’m sure there are many cultural references that went over my head while watching the show; I really should watch it again.
It is absolutely wild and baffling to me that people don’t make connections like that, and so I wonder what kind of equally obvious (to other people) connections I haven’t made.
This is such a good pairing! Part of the fun of the stories is that its never clear whether Jeeves' suggestions are genuis, or overconfident but insane japes, I feel like this dynamic puts LLM hallucinations into a role where they're just part of the fun.
I’m building a private chatbot for myself so as not to be tripped every time Claude has an ”update”, andthis was one of the first things I implemented. With very strict system prompt of no sycophancy and calling me Sir, it works really well.
Has anyone tried Marvin from The Hitchhiker's Guide to the Galaxy? "Here I am, brain the size of a planet, and they ask me these silly questions." Could be fun.
I use Marvin from the Star Force space opera book series. He loves sensors and information, and adds a level of challenge to counters the llm obsession with answering in over happy terms. I had Claude write me a character bible that I can include in projects to keep it consistent.
I think about six months ago I commented on an AI thread to the effect of “I’m happy that after a 30 year effort and hundreds of billions spent, AskJeeves finally works as intended” - Jeeves is totally ripe for LLMing.
Completely baffling that after keeping ask.com going for this entire time (some two and a half decades of irrelevance) they shut it down at the point at which it can actually be made to work.
There was a period in the early 2000s where AskJeeves’ answer to the question “what is the meaning of life?” was an old Eliezer Yudkowsky essay saying that because we weren’t smart enough to work out the meaning of life ourselves, our highest purpose was to build smarter AIs who might be able to answer definitively. Time to close the loop!
I'm loving the Wodehouse references in this thread.
In case there are folks unaware of it, there is an excellent TV series called "Jeeves and Wooster" (Stephen Fry and Hugh Laurie) -- highly recommended!
The right read here is to realize that psychology alone is not the basis for moral concern towards other humans, and that human psychology is, to a great degree the product of the failure modes of our cognitive machinery, rather than being moral.
I find this line of thinking to lead to the conclusion that the moral status of humans derives from our bodies, and in particular from our bodies mirroring others' emotions and pains. Other people suffering is wrong because I empathically can feel it too.
"Morals" are culturally learned evaluations of social context. They are more or less (depending on cultural development of the society in question) correlated with the actual distributions of outcomes and their valence for involved parties.
Human psychology is partly learned, partly the product of biological influences. But you feel empathy because that's an evolutionary beneficial thing for you and the society you're part of.
In other words, it would be bad for everyone (including yourself) when you didn't.
Emotions are neither "fully automatic", inaccessible to our conscious scrutiny, nor are they random. Being aware of their functional nature and importance and taking proper care of them is crucial for the individual's outcome, just as it is for that of society at large.
We as a society accept the insurance system as an implementation of "funding healthcare" because market capitalism is supposed to lead to lower prices, fair allocation of scarce resources, and innovation, among other things. That is, the insurance industry is a market solution to a moral problem.
If insurance companies then can wiggle out of covering pre-existing conditions, they're no longer solving the moral problem they were brought into the world to solve, and now we need some other solution to solve the rest of it. Then, whatever that other solution is, it's solving the hard part, so why not extend it to solve the whole thing and cut the insurance middlemen out of the economy entirely? What are they even doing at that point besides extracting a rent?
(This is one answer among many good ones to what is really a bad-faith question—health-insurance is not a lot like fire-insurance at all)
I would love to have a coworking-space-on-every-block (or in every building) where all the WFHers can go to be around other people (just not the coworkers)
Yeah, I was spoiled by my college town. Libraries open until 2AM, a 24 hour space for students. Even a few cafes downtown open 24 hours a day. Suburb life is mostly fine, but that's one thing I miss most.
Gotta travel 20 miles to downtown for anything resembling night life.
> Our auditoriums are provided as a public service for use by individuals, institutions, groups, organizations, and corporations for a small fee, when not being used for library-affiliated or sponsored activities.
And maybe we can pool them a bit by profession, because they often need the same tools and can help each other. Any maybe they can even work on some of the same projects, so we can remove meetings.
HN people always try to do this cute rhetorical gesture where you take a thing and say "hmm nice idea what if we called it <thing that already exists>", but they like this joke so much they get baited into doing it in dumb ways like this one.
A coworking space in every building != a WeWork. There's a big difference between these! You could implement the former by opening a million WeWorks but that doesn't sound good at all; residential apartment buildings already have common areas, free to residents, they would simply have to be reimagined slightly.
Prices are constrained by demand moreso than by cost of production. Lego pieces are expensive because they can be, they still sell, and this is largely due to the quality. As long as the quality moat persists, they can charge as much as people will pay, and--good for them!
That you personally would prefer lower prices does not mean they "should" be lower. Those lower costs of production, to Lego company, "should" mean higher profits, not lower prices, and again--good for them!
The risk Lego faces is that they don't actually have a quality moat any longer. You can get non-lego sets with no stickers, plenty of prints, LED lighting, at a cheaper price, and with the exact same piece quality. I purchased this set: https://www.lumibricks.com/collections/steampunk-world/produ... over Christmas, and I paid $105 because it was on sale. The pieces were indistinguishable from Lego in quality, and the lights and lack of stickers was a quality increase from what Lego offers.
What moat Lego has is: brand recognition and licenses. Which aren't nothing, but don't offer much protection.
Not disagreeing with you, but at least when I hear "lego knockoff" I think of the shitty ones, because I've never seen a Lego knockoff that wasn't shitty.
Lumibricks seems like a promising brand, but I've never heard of them, possibly because they don't spend as much on marketing as lego. And if they did spend more in order to compete with Lego, they might need to increase price!
> but I've never heard of them, possibly because they don't spend as much on marketing as lego
It’s a newer brand—they changed their name to it some time last year. But they seemed to spend a lot on advertising last Christmas—at least on YouTube, it seemed like tons of reviewers were talking about their sets. That’s how I found out about them, at any rate. And I’ll say—the one I got came together nicely, and looks great. The tons of lights are just, really neat.
> when I hear "lego knockoff" I think of the shitty ones, because I've never seen a Lego knockoff that wasn't shitty.
The cheap-o ones you get like at the dollar store, absolutely. But Chinese manufacturers have been making good quality knockoffs for a while. A decade at least? I bought my first knock-off technic set around 10 years ago, and it was 90% the quality of Lego at 25% the price. But the quality has only gotten better since, and is now totally on par with Lego. Admittedly, the price has gone up, too.
Interesting. Gotta check those out! Not that my family needs more LEGO... The remains of our Millennium Falcon after my nieces came over glare at me everytime I look at a new LEGO set.
I don't want to sound like a shill, because I don't know them at all, and I still spend enough money on actual Lego. But I am really happy with it. Pieces were great, quality was great, I love the lights, I hate Lego's stickers. And the piece count was 2x or 2.5x what I'd get from Lego at the same price. And I love steampunk, and Lego doesn't have a steampunk line. I'll absolutely buy more from them, so (for me at least) their big Youtuber push last year worked.
No but I appreciate your recommendation. I find that product recommendation on HN tend to be higher quality and/or more relevant to me than generic lists (I added so many books and games to my backlog from HN comments because many HNers have really good taste).
Maybe I'm saying the quiet part out loud. I hope no one tries to advertise on HN after this.
A reputation moat is still a moat. It seems to me that Lego prices will drop as soon as they are forced to by competition, and not before, and this is fine.
It is, absolutely, but it’s a lot more shallow a moat than having a product quality moat.
> Lego prices will drop as soon as they are forced to by competition, and not before, and this is fine.
I agree, they’ll survive quite well. But the large profit margin they’ve grown accustomed to might disappear, and that probably doesn’t bode well for their management.
And heck, maybe they’ll stop shipping stickers on expensive sets, too. That would be nice.
I've seen enough reviews of recent Lego sets to doubt this. Sets with a brick or two where the color is off, sets where the final model falls apart if you look at it wrong, and when there's fan designed alternatives which are more solid and better looking it's clear it wasn't a physical limitation.
Not to mention sets that indeed just feel like a ripoff, like the pyramid of giza which costs $130 and is actually just half of a pyramid, but the backside of the model has slots that let you connect it with another half if you buy two of them. And they even admit in the marketing it's an incomplete product with "Complete the pyramid - This model comes with clear instructions and can be connected to a second model (sold separately) to create a full pyramid", of course only visible after scrolling or looking at more product pictures.
They are. I should have added that Lego’s designers are a bit better still. You can get botanical sets from a lot of manufacturers, but the Lego ones are just nicer.
It appears that the real lesson here was to lean quite a bit more on theory than a programmer's usual roll-your-own heuristic would suggest.
A fantastic amount of collective human thought has been dedicated to function approximations in the last century; Taylor methods are over 200 years old and unlikely to come close to state-of-the-art.
Your dismissal of moral concerns is not convincing.
Imagine a world where the only energy you do is use was generated by a stationary bike you had to ride yourself. You would, generally speaking, use that energy differently than energy you would pay for--you would generally reserve your effort for worthwhile things, and would be averse to farming energy yourself just to power frivolity or vice. How you determine what to put your energy into would explicitly be a moral question.
Instead in our world we an abstractions conceals the source of the energy. But if the moral concerns from the first world had any weight, they haven't lost it now; if energy is anything short of completely free we should by the same logic be averse to expending energy on worthless work or vice. The human being is not a utility monster, but something very different, and moral questions of this sort are central to how it navigates the world, they should not be dismissed.
Doesn't this argument hinge on equivocating between two different definitions of aversion, though? I'm averse to bananas, but that doesn't mean I think it's immoral to eat them. The moral dimension kicks in if somebody else had to ride that stationary bike for you, because then you'd be wasting their time on frivolities.
Of course I'd use energy differently if it cost more. If I had to generate energy by pedaling a bike, I'd consider it costly indeed. So what? Energy doesn't cost as much as it would if I had to manually generate it, and who are you to say allocation decisions made under that regiment are good and ones made under ours are bad?
Wouldn't your argument also compel us to use steel as if it were gold? Salt as if it were saffron?
reply