Related posts
Kun Chen Newsletter
Evaluating the Effectiveness of Programming Languages for Agents
effectivenessevaluatinglanguages
The the words it uses that this site has seen least often elsewhere. Posts are matched on those words alone — nothing here is a summary of this one.
Top people
Showing Profile →
Hiding
Hiding
9 September
8 September
30 August
29 August
28 August
15 August
11 August
-
Lovedrcmnd.app
Thinking ForthTheir words
Thinking Forth by Leo Brodie. I used to have this habit where I learned various programming languages. To challenge my perspective, I chose languages from families and paradigms that were fundamentally different from what I already knew. Occasionally, I stumbled upon greatness. Thinking Forth presents programming as a creative process, and it delivers those lessons in an entertaining and pedagogical way. The book is particularly strong on software analysis and design, but it's the execution and technical writing that brought the book to my top five. This is the book for anyone writing about software — Leo's way is the way to do it.
10 August
-
Their words
But if you zoom out, it becomes clear that almost every “breakthrough” since last summer has concerned the narrow domains of computer code and math, which are defined by highly structured languages and come accompanied by massive amounts of specialized training data.
9 August
-
Their words
we say we want disagreement, but every disagreement costs the person making it a little social/political capital. do it often enough and you become the negative person. people stop evaluating the argument and start evaluating the source.
7 August
20 July
-
Their words
I came to the same conclusions independently before I encountered Krashen's work, and decades of learning across 20+ languages have only reinforced them. The research supports the intuition: input is where acquisition happens.
19 July
-
Their words
I get really nervous about having different design languages or different types of user interactions and shipping Frankensteins, basically. So, designers need to then be the people we're hiring again for design systems thinking.
18 July
14 July
13 July
7 July
26 June
-
korrents.com
Evaluating a model properly would mean delaying its release, and competitive pressure means no lab will.Their words
It's actually very difficult because, yeah, you would have to the only way to to really do the evaluations is then delay the model release cycle. Um and you know there's a lot of competitive pressure right now to not do that.
24 June
From one piece Tech interviews with NeetCode 2 beliefs, in the piece's order there
-
Their words
And DSA interviews were never the best for that. Well, thinking, sure. But in terms of like does that skill translate to what you're doing on the job? It never really translated to that. It was more about evaluating like does somebody think?
-
Their words
Like every single time there's just like the big innovation like cloud computing, like higher level programming languages, for whatever reason things do not like it doesn't lead to fewer programmers. And I would have expected it would have.
23 June
9 June
20 May
From one piece Why Rust is different, with Alice Ryhl 2 beliefs, in the piece's order there
-
Their words
Really the big idea is to say we want the old code to continue working but we still want to change the language. And so the the difference from other kinds of versions of languages I mean Python 2 version Python 3 comes to mind is that you can totally mix and match in any way you want.
-
Their words
I think the most tricky thing people run into is how should you put together your data structures? I mean for your code you can mostly do the same things as you can in other languages. I mean that's not entirely true but the big thing is really the data structures.
13 May
From one piece TypeScript, C# and Turbo Pascal with Anders Hejlsberg 2 beliefs, in the piece's order there
-
Their words
But but the thing is like doing programming languages, you come to realize it's a long play. I mean, if if you look back at the the stuff I worked on, it it it goes in 10-year cycles at least. And TypeScript didn't really, for example, or C# for that matter. I mean, it took it it takes 10 years to get to, you know, version one is great, but it has all sorts of issues, and then you got to do version two, and then it's not until version three that it really starts to be great.
-
Their words
So, if we're checking 99% instead of 100%, well, heck, that's better than the 0% that JavaScript checked, right? And it gives you like language features that no other languages can provide because they can't get to 100%.
8 May
-
Their words
but it is the tracer dye, right? Like it tracks into European languages and important aspects of Indo-European culture are coming through Yamnaya.
3 April
31 March
23 March
-
Their words
You know, our computer price is going up, but our token generation effectiveness is going up so much faster that token cost is coming down. It's just coming down an order of magnitude every year.
-
korrents.com
AI language models are capable of evaluating good fiction even though they cannot yet write it themselves.Their words
An LLM may not be able to write a good story yet, but it can already evaluate them.
20 March
-
Their words
So, we're now in a situation where suddenly people can generate thousands of theories for a given scientific problem. And now we have to to verify them, evaluate them and this is something which we we have to to change our structures of science to actually sort this out.
19 March
-
Their words
if you've always stuck to two programming languages because of the overhead of learning a third, go and learn a third right now. And don't learn it, just start writing code in it.
11 March
-
Their words
But right now we're in a funny place where the some languages work better than others still because they have better training data, but in the fullness of time, all languages will work equally well.
18 January
28 December 2025
-
Likedrcmnd.app
GoTheir words
My go-to languages are TypeScript for web stuff, Go for CLIs and Swift if it needs to use macOS stuff or has UI. Go wasn’t something I gave even the slightest thought even a few months ago, but eventually I played around and found that agents are really great at writing it, and its simple type system makes linting fast.
9 December 2025
-
Their words
We don't really have much evolved experience in evaluating postal efficiency, do we? Okay, we have quart of a million half a million years of evolved experience in deciding who to like and trust because for most of our evolutionary, you know, existence, that was one of the most fi five most important questions to get right.
28 November 2025
-
Lovedaffiliate linkrcmnd.app
PimsleurTheir words
For language acquisition, Pimsleur is by far my favorite online/app program. (Even Mr. Mari, who gathers no joy from learning languages, was addicted to it for a while!)
25 November 2025
-
Their words
There is no such thing as revisionist history. Writing history is a constant process of re-evaluation of sources and attempts to control for the biases of the past as well as our own.
18 November 2025
-
Their words
Thus my personal prediction is that in domains that are already largely under the powers of modern AI, such as languages, programming or chess, we’re going to see a divergence in human abilities.
-
korrents.com
The effectiveness of a plot twist depends on how carefully a story's point of view relates to its audience.Their words
Point of view is essential for effective twists. Contrast Frozen with Fight Club, where the narrator's unreliability works because the entire story flows through his perspective and he maintains a direct relationship with the audience through fourth-wall breaks.
Frozen's Lie: How a Tiny Detail Can Ruin a Storynateliason.com
23 October 2025
22 October 2025
14 October 2025
20 August 2025
17 July 2025
From one piece Assessing Adaptive World Models in Machines with Novel Games (with 13 co-authors) 2 beliefs, in the piece's order there
-
Their words
We expect that building and evaluating AI systems capable of this kind of rapid world model induction will be critical for achieving robust, general AI capable of functioning effectively in the complex and fast-changing real world, and especially in human worlds - the environments that human beings have evolved in, created, and are continually changing and re-creating.
-
Their words
We contend that games provide particularly rich and controlled environments uniquely well-suited for systematically evaluating rapid model adaptation and the process of world model induction.
13 July 2025
22 June 2025
30 April 2025
-
Their words
But there are other parts of programming languages that are not subjective but should be fundamental. And when you look at type systems, there is a way to do type systems that gives you mathematical proofs. And every other way of type systems that doesn't give you mathematical proofs is just worse and should ultimately be rejected.
10 April 2025
22 March 2025
From one piece ThePrimeagen: Programming, AI, ADHD, Productivity, Addiction, and God | Lex Fridman Podcast #461 3 beliefs, in the piece's order there
-
korrents.com
A speed difference between languages that share the LLVM backend measures the benchmark author, not the languages.Their words
It's just that Zig, C, C++, all those languages that were being tested, they're all LLVM backends, right? That's the one that actually turns the thing into the executable part. And if there's a variation in speed, it just means in one language you didn't quite express what you are supposed to correctly.
-
Their words
At some point you have to take off the training wheels, because I think what you're really spotting is the difference between reading and writing code. I can read a lot of languages very well. I can see what's happening. I can understand it, but I would not be very good at writing it.
-
korrents.com
Learning a new language by Googling your way through a project teaches you your old languages again, not the new one.Their words
You kind of Google and you try to solve a problem in the language based on all of your previous experience. And so you don't have what makes that language special. You have what all the other languages make special.
13 March 2025
30 September 2024
-
korrents.com
Maya hieroglyphs must have been readable across several spoken languages, the way Chinese characters or Latin were.Their words
There must have been a way that multiple languages understood the same writing system. Or maybe there was something like Latin. You know how there was a period in Europe where most people were illiterate and there was this priesthood who all understood Latin and they wrote in Latin? Maybe the hieroglyphs represent a kind of Latin in the ancient Maya world.
21 August 2024
-
korrents.com
Therapists overestimate their own effectiveness by about 65%, and it is not a Western cultural artifact.Their words
Since 2012 when the first study appeared in the literature, others have been published documenting the tendency of practitioners to overestimate their effectiveness - on average, by 65% (1, 2).
Alas, it seems everyone comes from Lake Wobegonwritings.scottdmiller.com
15 July 2024
2 July 2024
-
Their words
Over the last 50 years, treatment methods have proliferated despite a lack of evidence of differential effectiveness between approaches. And even when a randomized controlled trial indicates a particular approach works, none show practitioners become more effective when they are trained in that modality.
14 June 2024
-
Their words
I don't teach people languages, I teach them how they can learn languages by themselves.
21 May 2024
-
Their words
It's time for the field to stop attributing benefits to clinical experience. Beyond the obvious ethical concerns, doing so actually prevents us from improving our effectiveness!
13 May 2024
-
Their words
The time when benchmarks lasted multiple decades has passed. Going forward, we will rely less on public benchmark results.
7 May 2024
From one piece The case for ensuring that powerful AIs are controlled 3 beliefs, in the piece's order there
-
Their words
Because evaluating control just requires evaluating capabilities, it's far easier to robustly evaluate than alignment.
-
Their words
The basic problem with evaluating alignment is that no matter what behaviors you observe, you have to worry that your model is just acting that way in order to make you think that it is aligned.
-
Their words
So when evaluating control, we should count catching an AI red-handed as a win condition.
27 February 2024
-
Their words
many under-represented languages are primarily spoken; they do not have a written tradition or a standardized orthography. Text-based NLP technology is thus of limited use to them.
31 December 2023
-
korrents.com
Metaprogramming in a language creates fundamental obstacles to static analysis of its code.Their words
Languages with metaprogramming tend to put up fundamental hurdles to static analysis
21 December 2023
-
Their words
While there are interesting theoretical arguments for these causes, there’s a disconnect between an almost-neurotic focus on hard evidence of effectiveness in some areas of EA and a willingness to accept extremely abstract and conjectural “evidence” in others.
19 December 2023
-
Likedrcmnd.app
How Languages are LearnedTheir words
To that end, I read a few different books from the field of second language acquisition (SLA) over the summer, and even wrote a review of How Languages are Learned.
21 September 2023
30 August 2023
-
Usesrcmnd.app
AnkiTheir words
Anki, flashcards. I particularry use it for languages and words.
23 August 2023
9 July 2023
1 May 2023
-
Their words
Good tools let the user choose when to switch between implementation and evaluation. When I work with a chatbot, I'm forced to frequently switch between the two modes.
4 March 2023
12 January 2023
-
Their words
This is not about precarity, because this is not a precarious project; this is about total ignorance and incuriosity about best practices, which emanate from a place that doesn’t natively speak English and doesn’t trade in American political references.
High Costs are not About Precaritypedestrianobservations.com
6 April 2022
-
Their words
Despite the unreasonable effectiveness of simple architectures, most press goes to complex architectures.
1 December 2021
17 November 2021
27 October 2021
29 July 2021
20 January 2021
-
korrents.com
Pre-grant peer review predicts which research will have impact substantially better than chance does.Their words
I have reviewed before the effectiveness of peer review at figuring out "what's good" in the context of grant awards, finding that peer review as currently practiced does substantially better than chance at predicting future impact, especially for the most impactful of the papers; but at the same time is is far from perfect, leaving plenty of variance unexplained.
9 September 2020
-
korrents.com
There is no best or fastest way to learn a language; the question has no general answer.Their words
after 30 years of learning languages and 10 years of coaching people to do the same, I am 100% positive when I tell you that there is no absolute best and fastest way to learn a language.
9 February 2020
-
Lovedrcmnd.app
The 5 Love LanguagesTheir words
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.
5 November 2019
-
Their words
To make deliberate progress towards more intelligent and more human-like artificial systems, we need to be following an appropriate feedback signal: we need to be able to define and evaluate intelligence in a way that enables comparisons between two systems, as well as comparisons with humans.
9 April 2019
-
korrents.com
Programming languages shape how programmers think, similar to how spoken languages shape thought.Their words
Languages shape the way we think*, each in their own peculiar way. That's true for programming languages as well.
9 August 2018
-
Likedrcmnd.app
Domain-Specific LanguagesTheir words
Partly because of another book that nearly made it onto my list: Domain-Specific Languages by Martin Fowler. It talks about the idea of writing a small language inside another language, to express ideas in a specific domain
-
Likedrcmnd.app
Concepts, Techniques, and Models of Computer ProgrammingTheir words
Another similar and also interesting book is Concepts, Techniques, and Models of Computer Programming, which explains all the models of computer languages and how they fit together.
-
Recommendsrcmnd.app
Structure and Interpretation of Computer ProgramsTheir words
But this book is very useful for somebody like me, with experience in high-level engineering languages, like VBA, PHP and R. They're incredibly useful languages, but ones that computer scientists generally disdain, because they're not theoretically pure or beautiful. This book shows you how languages can be constructed. The most valuable thing it gives you is confidence and knowledge to go and create your own programming language.
3 July 2018
-
Their words
Like most diets, low-carbohydrate diets aren’t very effective against obesity in the average person, but they do have some effectiveness and they are certainly a valid tool in the toolbox.
13 June 2018
3 April 2018
-
Likedrcmnd.app
Visual Studio CodeTheir words
Visual Studio Code is the go-to editor for some complex languages like React using JSX or TypeScript and I finally agreed with Wes Bos that VS Code is better for development of React JS.
8 February 2017
-
korrents.com
Building powerful developer tools such as compilers, interpreters, and query languages requires knowledge of parsing.Their words
What I know and what I'm sure about is that without knowledge of parsing you won't be able to build tools like these.
9 December 2015
-
Their words, before
I put less weight on explicit cost-effectiveness analysis. Conceptually, my goal is to maximize the impact of my charitable contribution, but I put less weight on the explicit cost-effectiveness models we create than others.
Their words now
I remain ambivalent about putting so much weight on cost-effectiveness estimates because they are subject to numerous debatable assumptions, but I’ve changed my mind based on work we did over the past few months.
7 November 2014
-
Their words
But while I like languages with expressive type systems, I haven't noticed that they make me more productive or less bug prone
2 September 2014
-
korrents.com
Reaching a conversational level in a language within three months of arriving is not something to expect.On changing their mind
When Vat and I initially made plans, neither of us were confident that it would be possible to reach a conversational level in any of the languages.
From one piece Looking Back at a Year (Almost) Without English 2 beliefs, in the piece's order there
-
korrents.com
Learning a language in a hurry and learning one by slow patient habit are both legitimate; neither refutes the other.Their words
Just because we attempted to learn with intensity, doesn’t denigrate learning languages through slow, patient habit.
Looking Back at a Year (Almost) Without Englishscotthyoung.com
-
korrents.com
Asian languages are hard enough that arriving without preparation and refusing to speak English will not work.Their words
The main takeaway I made from all of this was: Asian languages are hard, and attempting full-immersion without sufficient preparation is usually not going to work.
Looking Back at a Year (Almost) Without Englishscotthyoung.com
14 March 2014
From one piece Are cash transfers overrated? 2 beliefs, in the piece's order there
-
Their words
There will be, I am confident, a great many interventions that do better than cash on any number of metrics. Ones that solve market failures or supply problems are big candidates, just like Starr and Hattendorf say.
-
Their words
If it’s becoming standard to judge interventions by their cost effectiveness, then I can’t be more thrilled.
1 January 2013
-
korrents.com
Most programming languages in use today derive from Fortran or Lisp, both created in the 1950s.Their words
Pretty much any programming language used today is a derivative of Fortran or Lisp, both born in the 1950s.
18 August 2011
-
Their words
Giving well seems conceptually quite difficult to me, and it’s been my experience over time that the more we dig on a cost-effectiveness estimate, the more unwarranted optimism we uncover.
27 July 2011
-
Lovedrcmnd.app
PythonTheir words
Programming languages aren't strictly software, but I'm a huge fan of Python along with the numeric computing libraries.
17 April 2009
1 April 1985
Nothing matches.
What is a korrent?
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.