ive been fighting the way my brain works my whole life, and only recently have i switched to trying to work with the way it wants to work. i get so many more things done that are important to me, and i get them done without the implicit "i need to flagellate myself with this thing i hate because there is something wrong with me" that comes with those fights.

and yeah, the ai's come with their own problems. but the trade is so exponentially in the direction of being worth it. even just the being a decent rubber duck aspect of them can keep me on a task when i would never otherwise hope to see it through.

but yeah on demand would be a lot of ssd churn so id just do it for testing or getting some hidden state vectors.

my guess is that large models trained on large corpuses there is just some ceiling of "reasoning you can do" given the internal geometry implied by the training data, cause text is lossy and low-bandwidth anyway, and theres only really so much of it. past some point you just have to have models learning from real-world interactions and my guess is we're already kind of there.

so thats about %15 more compute per forward pass with 0 extra memory which is just nuts, so for a streaming or disk-based setup its just free better answers. def wasnt gonna think of this myself.

  config               layers   overall    delta          math     reasoning  word problems
  baseline                 80    0.5391  +0.0000        0.5850        0.6357        0.3500
  rys                      87    0.5452  +0.0061        0.6706        0.6000        0.2723
  cartographer_repeat_x2   92    0.7741  +0.2350        0.8455        0.8214        0.6000

i tried a matrix of other configurations and stuff gets totally weird. like playing em through backwards in that block doesnt make much of a difference / order doesnt seem to matter (?!). doubling each layer got a benefit, but if i doubled the layers and doubled that block there was interference. doubling the block where the model is architecting/crystallizing its plans improves reasoning but at the cost of other stuff. other mixes of blocks showed some improvements for certain kinds of prompts but didnt stand out as much.

i think probably once you start seeing that the behavior falls right out of the geometry, you just start looking at stuff like that. still funny though.

think of the latent space inside the model like a topological map, and when you give it a prompt, you're dropping a ball at a certain point above the ground, and gravity pulls it along the surface until it settles.

caveat though, thats nice per-token, but the signal gets messed up by picking a token from a distribution, so each token you're regenerating and re-distorting the signal. leaning on language that places that ball deep in a region that you want to be makes it less likely that those distortions will kick it out of the basin or valley you may want to end up in.

if the response you get is 1000 tokens long, the initial trajectory needed to survive 1000 probabilistic filters to get there.

or maybe none of that is right lol but thinking that it is has worked for me, which has been good enough

> Especially if your architecture already solved the problem it was designed for.

What I need is to not want to fall over dead. REST makes me want to fall over dead.

> error handling is harder than it needs to be GraphQL error responses are… weird. > Simple errors are easier to reason about than elegant ones.

Is this a common sentiment? Looking at a garbled mash of linux or whatever tells me a lot more than "500 sorry"

I'm only trying out GraphQL for the first time right now cause I'm new with frontend stuff, but from life on the backend having a whole class of problems, where you can have the server and client agree on what to ask for and what you'll get, be compiled away is so nice. I don't actually know if there's something better than GraphQL for that, but I wish when people wrote blogs like this they'd fill them with more "try these things instead for that problem" than simply "this thing isn't as good as you think it is you probably don't need it".

Why is it so popular for someone in tech to assign everyone else the task of thinking up something useful to do with technology x they think is cool?

> It's not an overstatement to say that distributed ledgers are as big of an advancement for human coordination as democracy was.

Ok, if that's really your thinking then you need to lay out: here's an impossible-to-ignore thing we can do with this, and this is how, and this is why this wouldn't be possible without this thing.

Who retired early? What did they make with Lisp? Do you have a link to that thing they made? Was it actually something special about Lisp or did they just happen to use Lisp while making something that could have just been as easily - or more easily - done with something else? Is that real-world, specific, material outcome replicable by other people and they should know about it?