So it's strange because it's also perhaps the major software release that I've worked on the least in terms of lines of code. I have the least number of personally hand-chiseled lines of code in Quattro than I've had in any major release I've ever done. And yet, I am insanely proud of what we've accomplished.
Such, indeed fragile, peace not only puts an end to today’s carnage, but leaves open a possibility of eventual long-term solution between Russia and Ukraine.
It's showing us that apathetic people use more brain energy when they're making this decision. They have a bigger activation energy barrier to overcome because when they're making that decision, the brain is consuming more energy. It's consuming more glucose when it's doing that.
New: emulate a GitHub App in a few lines of TypeScript Generated App keys, installation auth and stateful repository APIs Develop locally, test in CI or give sandboxed agents their own isolated GitHub environment
I'm so incredibly tired of seeing low-effort AI-designed web pages. I basically bounce off any new product immediately when I see it (never get a chance to judge the product itself). Lots of thin lines, glowy styles, inconsistent fonts, lots of monospace.
uh the we found that that leads to improvement and we saw in the shirt folding example we saw like a quantitative bump from using that sort of imagination compared to not using it. At the same time I think that the model actually performed surprisingly well without that as well.
Like that just does not seem like the ideal artifact. We should be able to store them somewhere. We should be able to have architecture diagrams that we can review and discuss that generate that code to spec.
Facts and Fallacies of Software Engineering by Robert L. Glass. In essence, this is a book about an industry that refuses to learn. That was true 25 years ago when this book was published, and it's probably twice as true today. (Just think about all the AI adoption metrics being rolled out — back to productivity mistaken for lines of code produced, only more elaborate. And expensive). What I like about this book is that Glass doesn't present anything new. Quite the opposite, actually. Rather, it's about research lessons that we all should know, but tend to forget. Ever had to do an estimate, or plan according to a requirements spec? Or maybe you thought that enough eyeballs make all bugs shallow? Then this book is for you. A great work by a fantastic author.
Claude Haiku is my current least favorite model - it hallucinates wildly, and is out-performed now by other similarly priced models like GPT-5.6-Luna
Even worse: it seems to still be used by the Claude Code WebFetch tool, which means hallucination risk any time you fetch a URL!
In the era of base LLM scaling (2022-2024), I believed the LLM line of research would reach a capability plateau (as later seen with base LLMs).
In late 2024, after the o3 test-time compute demo, I changed my views: the new models were showing genuine fluid intelligence, and with this new line of work, the LLM line of research could achieve unbounded capability scaling. "There will be no wall."
there are meta analyses of these interventions in older adults showing that ballroom and line dancing have the greatest effect on cognitive function. And so both of those require other people as well as learning you know various sets of of movements.
And what they [snorts] found was that the most important predictor of how well somebody performed at those piano specific skills was not their age, it was how much they practice.
I think there's a difference between being able to write lines of code in a particular language like Python or C++ and understanding how code, computer systems, products work. And I don't think the latter is going away.
I still see a craft excellence that's really important in the disciplines that I don't think is going away anytime soon. Even if there's fluidity or blurring of the work across the functional lines.
it's more important to invest in trains that can get more riders than just the railfans; taking a line from 0% to 5% modal split is less important than taking it from 20% to 40%
Riders diverted from other lines still benefit from the project, especially in a case like QueensLink, where the diverted riders would enjoy an improvement in trip time to Midtown of about 10-15 minutes each way.
I think a lot of people, especially students, are unfortunately learning everything through LLMs. So a lot of that isn't really learning, they're just kind of cheating and they're just doing everything like that. And then they lose a lot of their skills
Any process that you have that's going to be standardized and super scalable, there's always going to be ways to game that. And the best way to get around that would be like hire somebody who's who's an intern and you saw how they performed.
But if you took something that she loves and you make it one inch better, she might love that more than if you showed her something she's never seen before and didn't wake up knowing that she wanted.
The demand for inference is growing. So, like I don't think it's linearly growing. I think it might even be exponentially growing. But we haven't made our production of GPUs grow exponentially. That's like kind of a linear process. So as those lines intersect, there's going to be uh tightening.
The work that I've been involved in is consistently shown that I was wrong in my biases coming into the work and I've really been almost traumatized by this. Like again and again I've come into a project with some kind of guess about what the data was showing and then the data doesn't show that.
But right now I think it's sitting somewhere between half million and five million lines of code, somewhere in there. Probably more on the half million side right now and with the next drop of an Anthropic model, we're probably going to see it jump up to a few million lines.
As high-level programming cedes way to the prose compiler, making your goals and specs well understood to the ambiguity loop and showing good judgment is going to matter more than ever.
Notting Hill, in addition to being just a lovely little romantic comedy about two people from entirely mismatched stations in life, trying to negotiate a space in the world they might get to call their own, is one of the best films out there showing at least a little bit of what it’s like to be famous to everyone, everywhere, all the time, forever and ever, amen.
you write murder is good on a piece of paper and you put it in a photocopier and you press go and you say my god the machine says murder's good. Well, no, you told the machine to say that. And that's what these anthropic studies are. They're basically you tell the machine to say a thing and then it says it like well you haven't proved anything.
There's a point in which all of your choices add up. And I typically find that right around 5 to 10,000 lines of code. The choices you've made either weigh you down or kind of free you up.
A guide for ambitious people who feel called to inner work, showing how to use goals, career, and achievement as fuel for consciousness growth instead of a source of endless striving.
Archeology, in this regard, is the worst enemy of this. So we put these names on cultures, we talk about how they evolve from one to another, we draw these lines where there aren’t any.
One of the fascinating things that DNA is showing us, which actually blood types were showing us way before that, is that the oldest people in the Americas are in South America, the ones that got separated early and didn’t mix their DNA, like the people in the Amazon.
Steven Pinker goes deep, showing how understanding the science of memory, social understanding, and syntactic structure can really pay off in making one a better writer.
I was super excited when I saw the Lvl-10 dripper, because it was very close to what I wanted to achieve, and as I expected, it performed very well in terms of extraction quality.
I often read advice along the lines of “if you want to help a project send PRs” and I never understood it. Reviewing and iterating or pushing back on PRs is work! Often more than writing the code itself.
It goes much further and deeper into how to approach actually doing Lean in your business than Eric Ries's The Lean Startup book. It also has some awesome case studies showing how lean can apply to any industry. See my full review here.
The lesson is that connecting with others starts with recognizing that people are so different, especially in how they communicate. But there’s a much broader lesson embedded in this book if you read between the lines.
Podcast. Funny, scary, thought-provoking book. Thesis: what if a large portion of our population performs jobs they secretly know don’t need to be performed, and if they disappeared, no one would notice?
As robots and other computer-assisted technologies take over tasks previously performed by labor, there is increasing concern about the future of jobs and wages.
As robots and other computer-assisted technologies take over tasks previously performed by labor, there is increasing concern about the future of jobs and wages.
We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
Browsing: Mostly OmniWeb (using their Sneaky Peak builds). I am staying with OmniWeb mainly for the search shortcuts, the lack of UI distractions (I have toolbar and such disabled), session restore (by default), and showing open tabs in a list (this scales).
My second-most-frequently-typed-in application is Terminal. It has few frills, but it gets the basics right: I can copy and paste long lines of text without incident, it supports UTF-8, "unlimited" scrollback length, bitmapped 9pt Monaco, and it never crashes.
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.