It takes some serious getting-used-to in Arc that you don't open multiple windows. You just have the one browser window. It's weird to have multiple windows. It lets you, but it probably shouldn't.
We’re used to using price as an indicator of quality, so our instinct says that the $20,000 surgery in Switzerland is better than the $2000 surgery in India, but the rule of volume disagrees.
But each time there was a strong emotion and the best part there were quite a few people that really wanted it and like especially to my nontechnical friends I told them no this is not yet for you and they got mad. So if that's not an indicator to have product market fit I don't know what is.
I think one of the things that makes science the company very special is that it has both of those cultures and is able to integrate them and we're able to simultaneously do some really cool research that I think is really at the edge of the Overton window while simultaneously running clinical trials in six countries now with an approved medical device in Europe and clinical trial results in the New England Journal of Medicine.
I mean, obviously aviation was was a pretty big deal, but uh I I I don't think it was sort of quite the um the sociological rewriting that some of the you know excitable proponents at the time imagined. So I am you know it's it's hard to predict anything especially the future but I would I would take the under on this being the last couple of years to get a company going.
there's four things in your context window that matter. There's like the size of it, how many tokens? There's like the quality of the information is like is there any incorrect information? Like if the model had some thinking trace where it decided the wrong thing was true. Is there missing information? Does this like have context missing that it should have? And then there's the trajectory.
How do we control that in such a way that we get the best results possible which means doing as much work as possible in the smart zone the you know first 100,000 tokens of the context window.
You're not actually getting a like smarter model. like the intelligence of the model is is what drives its ability to attend to all of the tokens in the context window to figure out on the next turn which parts of this 100k or 200k context window are the most relevant to making the decision of like what is the next tool we call and doing that over and over again in a loop.
it's not that humans have become smarter over it's not that they evolved to become smarter over, you know, the past 50,000 years. It's that humans are able to do a lot more today than they were back in caveman times because there have been billions of humans thinking for a long time and building off of each other's accumulated knowledge.
Either way, atmospheric CO2 is better seen as a lagging rather than leading indicator of changes in emissions, as it is harder to see the effects of emissions reductions on concentrations over shorter time periods.
but but if you have good locality where you you clearly stating what you're importing and whatever and and you can analyze just a single source file and from that extract its protocol to the outside world without having to to know anything deeper. Do you do you know what I mean? I think those are important aspects just simply to reduce the size of the of the of the context window and also make it easier to summarize each module in a program, right?
I love chiseling my code and the way I use AI is in a separate window. I don't let it drive my code. I've tried that. I've tried the cursors and the wind surfaces and I don't enjoy that way of writing. And one of the reasons I don't enjoy that way of writing is I can literally feel competence draining out of my fingers.
Their words now
I will now start any project I'm starting with. I'm starting agent first and that's a massive shift
If you're a monolith, you're kind of hosed because I told you the ceiling's going up for what they can do, but it ain't ever going to hit your monolith. They will never fit in the context window and you're never going to be able to never in the next 18 months be able to tell a model go fix my monolith. You have to break it up.
NotePlan is more conservative, but it’s a native Mac app, which makes it easier to use on mobile and gives you all the traditional Mac benefits like Shortcuts integration and proper window management.
Arch Linux: has become my go-to distro after years of using EndeavourOS. I've recently switched to Hyprland as my window manager, and it's been a game-changer. Currently, I'm using CachyOS with KDE. It's been a great experience so far! Here's my
anything that's in the weights it's kind of like a hazy recollection of what you read a year ago anything that you give it as a context uh at test time is directly in the working memory
I think if you have especially a B2B feature where you may have some lock in reverse trials can be super powerful. You just want to get people in there. You don't need to ask for their credit card because they're using your CRM or they're investing quite a lot of time in like building out, you know, material and content. And so by the time that window drops, you actually like feel, oh man, I probably should keep this and and start paying. I think for a lot of consumer products, it's a little bit harder for that to work. And so I've typically seen more just normal free trials be be the norm.
I enjoy it even almost like as a sort of pair programmer AI pair programmer who doesn't drive who's just there to give suggestions to know the API to do all these other things but the second it starts wanting to autocomplete my code I'm like yeah I'm out bro
Their words now
I love chiseling my code and the way I use AI is in a separate window. I don't let it drive my code. I've tried that. I've tried the cursors and the wind surfaces and I don't enjoy that way of writing. And one of the reasons I don't enjoy that way of writing is I can literally feel competence draining out of my fingers.
I took inspiration from Omakub, which is where I discovered Tactile - a GNOME extension for tiling windows to a custom on-screen grid using the keyboard. I’ve found this to be invaluable, and easily the best window management experience for GNOME.
We should think of the gap between frontier models and proliferated models as an adaptation buffer: a limited time window when we know what bad actors will soon be able to use AI for, which gives us a chance to implement defensive measures that increase society’s resilience to the danger.
So most people, when they advertise new context window increase, they talk a lot about finding the needle in the haystack sort of evaluation metrics and less about whether there’s any degradation in the instruction following performance. So I think that’s where you need to make sure that throwing more information at a model doesn’t actually make it more confused.
That window is open. Now it may be open for a long time or it may be open for a short time and it may be open now and then never open again. So I think the smart move here is to make life multiplanetary while it’s possible to do so.
Stowa Flieger Classic 40 - When I'm not wearing my Apple Watch, this classic Pilot watch is on my wrist. Sapphire crystal, blued steel hands, and a date window at the 6 o'clock position. Perfect.
Witch can display separate app windows separately, only display windows from the current workspace, and supports text search on window titles so that you can search directly for the window you want without having to skip over.
Sizzy is a cool browser specifically for responsive design. It lets you view all of the breakpoints for a site at the same time and also does a good job auto-scaling fixed size viewports to fit whatever window size you're using.
A korrent is a belief a person has stated in their own words: one
sentence stating the claim, backed by a quote and a source, kept at
korrents.com.
Under a name here, the quoted block is what they actually said.
The korrent beneath it is the claim those words support, in
korrents' wording — tap it to see the record, its source, and who
else holds it.
Nobody here wrote their own korrents. They are compiled from public
statements, and a person can change their mind, which is recorded too.
About the English under a post
Some people here publish in a language other than English. Where they
do, this site shows a machine translation beneath the post, in
this typeface — the site's own, not theirs.
The post itself is never changed, moved or hidden: what is set in the
serif above is exactly what the person published, and it is what to
quote them on. A translation can be wrong in ways that matter,
especially about tone.
Only the post's own words are translated. A quoted post, a linked
article and a belief on korrents.com
are left in their original language.