HN user
I'm an atheist, but if there's a God then I am grateful to her for granting me the wisdom to pay off my house before retiring instead of investing that money in some horseshit.
Its a shelter from storms, both physically and metaphorically.
Google tells me that Klong and Lisp are not the same thing.
But can someone tell me why an array in Klong is NOT like an s-expression in Lisp?...
My mental model of the 'new normal' is end users using AI to get their work done.
So if I re-worded the OP's description and replaced 'internal tools' with 'internal AIs' then this would at least seem like a more reasonable process to me...
At our startup, engineers don't build features anymore. They build APIs that internal AIs can connect to. Most "features" like running an SQL query, sending a push notification when product X is ordered gets built by ops or product folks using those tools.
To me this describes a team of engineers that use AI-capable tools and that are building 'features' for themselves. In the way that us dinosaurs used to write build scripts.
I'm not saying that my mental model is right or wrong, just that working this way seems reasonable if you buy into my model.
[flagged]
The article summed itself up as 'Context is everything".
But the article itself also makes the point that a human assistant was also necessary. That's gonna be my take away.
Whats Going On With Shipping...
Not true. I give money to the government against my will. Same for the rent, the utility company, the water company etc.
Most people give what other people can force them to pay to survive.
> But nothing has the quality of life impact of smart blinds <<
I have a ton of sleep problems and just wanna push back here a little... going for a brisk walk in the fresh air and sunshine every day works a lot better for me.
This decision only makes sense it saves more lives than the number of lives that will be lost because of it.
It seems to me like it should totally be possible to do the math here and figure it out. Compute the lives saved and compute as many of the lives that will be lost. For instance, statins are a risk to pre-diabetics, and to children, and to etc...
There better be a very large difference. That's the bottom-line argument that I would have attempted to make.
I suspect that Jef Raskin would not be down with "prompt engineering' at all.
I think that Mr Raskin's opinion would be that it should be obvious how to use a piece of software.
I get that the headline is misleading.
Still, is the fact that Britain is doing well a validation of Brexit?
Trump will eventually take every side of every issue.
As the US is being torn down for fun and profit it seems like I've seen Vannevar Bush's name pop up more and more frequently.
It seems that this dude had a huge influence on the shape of our society.
I predict the same thing, that publishing new APIs will be rare, but for a different reason.
People will stop publishing any new knowledge or method to keep it from the LLMs and to keep people from exploiting new ideas before they can.
Wow! I was unfamiliar with Z and just spent an hour going down the Z and B-Method rabbit hole.
That's exactly the kind of thing I was looking for, thanks!
>Another way to see it is that the set of valid theorems in FOL is uncomputable.<<
I've never seen it put that way exactly. And I've never learned the gory details of the incompleteness proofs and I've never made the explicit connection between incompleteness and computation before. That blew my tiny pea brain :-).
Now that I've read the Wikipedia page, I guess I only understood incompleteness as the 2nd theorem.
https://en.wikipedia.org/wiki/G%C3%B6del%27s_incompleteness_...
Thanks!
I just noticed that all my interaction with HN always takes place at the bottom of the page :-)
Well, I think this is a really good point.
I'm not in favor of banning games but I really cant discern the difference between a playing a game and interacting with an AI.
I would be concerned that I'd get out of school and not get a job because I don't actually know anything.
But I wouldn't blame students if they're not preparing for interviews and jobs. Because in this world having a job seems like a recipe for being poor. Instead, maybe students are just going to prepare to get ahead, in any way possible. And they'll go to a university to network and such.
Personally I doubt that's gonna work out well, but I'm old what do I know.
Just look at the assholes that run this country. They set the standards. They lie and cheat their asses off every day.
You can't reasonably expect that people WONT lie and cheat their asses off.
>The price will be born by all of us.<<
No doubt that is true, but...
Suppose an extortionist comes to my business and says "hey, that's a nice business you got there, it would be a shame if someone was to ruin it with a bunch of horseshit tariffs"
I'd say 'yes sir no problem" and then do my goddamn best to murder those fucks in their sleep. Making them pay the price for extorting me will make sure that its not gonna happen again.
So now suppose the business next door is being extorted. And I tell the owner that I'd be happy to murder the extortionists for them. But they say "nah dog, they're sending the bad guys to El Salvador, it'll be fine".
How do expect me to care about that guy? Fuck that guy.
We should probably require AI to always be able to explain it's conclusions.
That way we can quickly assimilate knowledge from the AI and theoretically always have at least as much knowledge as the AI.
I suppose it also means that we can verify that the AI is not lying to us.
I'm not convinced that I should worry about people that would let AI run their lives.
They're gonna pay the price for their foolishness, and paying the price is the universe's mechanism for keeping itself in balance.
Take what's going on the US for example...
PS...
I've been waiting for such tools for 40 years.
I just now realized that vibe coding is probably the closest we'll get in my lifetime.
It's a start I guess.
I dont want to prove that my code is correct.
I would prefer to create specifications in logic and have the code derived for me.
Other than something like Prolog, are there tools for working this way?
> In this case we build a model with 1T index which we lookup for every token to make prediction with much smaller model. <<
This index seems to be used to minimize the size of models.
I'm familiar with term indexing as described in The Handbook of Automated Reasoning and I imagine that this index helps them recognize 'generalizations'.
In the way that a rewrite rule can be used to reduce an infinite number of expressions, not just a single expression, a generalization can be used to minimize models.
Generally, such an index would be some kind of prefix-tree.
Just a guess, guessing is fun
I'm late to this party but I would love to hear what folks use to do multiple-dispatch in other languages.
I think that MCPs are awesome.
I also think that they wont get much adoption, just like OSGi.
In general, people have shit for brains and MCP is just too abstract a concept for their tiny turds.
You know its true
> It's hard to see how helping pigs stay healthy could have a negative impact on human health, <<
Really? You don't see a logical flaw in your reasoning there?