> “As an aside, I think there may be an increased reason to use dynamic interpreted languages for the intermediate product. I think it will likely become mainstream in future LLM programming systems to make live changes to a running interpreted program based on prompts.”
Curious whether the author is envisioning changing configuration of running code on the fly (which shouldn’t require an interpreted language)? Or whether they are referring to changing behavior on the fly?
Assuming the latter, and maybe setting the LLM aspect aside: is there any standard safe programming paradigm that would enable this? I’m aware of Erlang (message passing) and actor pattern systems, but interpreted languages like Python don’t seem to be ideal for these sorts of systems. I could be totally wrong here, just trying to imagine what the author is envisioning.
I think at some point in the future, you'll be able to reconfigure programs just by talking to your LLM-OS: Want the System Clock to show seconds? Just ask your OS to make the change. Need a calculator app that can do derivatives? Just ask your OS to add that feature.
"Configuration" implies a preset, limited number of choices; dynamic languages allow you to rewrite the entire application in real time.
Maybe I'm missing it, but when my calculator app gets a new derivatives feature, how am I supposed to check that it's implemented correctly? End user one-shot of bug free code seems like a different technology than what LLMs offer.
Yeah I don't see how LLMs are ever supposed to be reliable enough for this, but they did say "at some point in the future", which leaves room for another (better) technology.
I agree that as LLMs approach the capabilities of human programmers, the entire software paradigm needs to change radically. Humans at that point should just ask their computers in human language to introduce a new visualization or report or input screen and the computer just creates it near instantly.
Of course this requires a huge architecture change from OS level and up.
I was envisioning the latter (changing behavior on the fly). Think the hot-reload that Flutter/Dart provides, but on steroids and guided by an LLM.
Interpretation isn’t strictly required, but I think runtimes that support hot-swap / reloadable boundaries (often via interpretation or JIT) make this much easier in practice.
What stack are you running? How do you guarantee sequential consistency of order numbers across your app server regions, cache layers and data lakehouse?
They know its radius is ~1000km but interestingly, there is no way to determine its mass without a flyby or other gravitational interaction. I guess you could swag it by using the lunar density, which gives ~~~ 10^22 kg.
In the wikipedia post you are replying to has the chemical composition of the surface of the planet, obviously we can't know what is beneath that, but to me, indicates this is closer to Pluto than it is to our Moon.
> Detailed spectroscopic analysis has revealed Sedna's surface to be a mixture of the solid ices of water (H2O),[15] carbon dioxide (CO2), and ethane (C2H6), along with occasional sedimentary deposits of methane (CH4)-derived,[16] vividly reddish-colored organic tholins,[15] a surface chemical makeup somewhat similar to those of other trans-Neptunian objects.[17]
This. My new Samsung T7 SSD overheated and took 4T of kinda priceless family photos with it. Thank you Backblaze for storing those backups for us!
I missed the return window on the SSD so now have a little fan running to keep the thing from overheating again
Just another plus one for cast-iron pans and wooden spatulas. We’ve been using those for over a decade, 20 bucks each, never needs replacing, works for everything.
We switched from gas stove to induction and now they work even better since the handle doesn’t get as hot and it’s easier to control the temperature.
The whole seasoning thing is extra credit, the only failure mode I’ve seen is trying to fry an egg on a completely unseasoned pan, which just means some extra soaking and scrubbing is needed. The pan seasons itself after a few uses. Hand wash the pan instead of sticking it in the dishwasher, done.
Yeah, eggs can be hard. What I do is have a smaller cast iron pan strictly for a single egg. I just make sure to use more butter and clean after right after.
Curious whether the author is envisioning changing configuration of running code on the fly (which shouldn’t require an interpreted language)? Or whether they are referring to changing behavior on the fly?
Assuming the latter, and maybe setting the LLM aspect aside: is there any standard safe programming paradigm that would enable this? I’m aware of Erlang (message passing) and actor pattern systems, but interpreted languages like Python don’t seem to be ideal for these sorts of systems. I could be totally wrong here, just trying to imagine what the author is envisioning.
reply