How does programming language affect token efficiency and correctness?
Dan Luu·12d ago
This somewhat widely cited post (I keep seeing it cited, anyway) suggests that dynamic languages and/or languages that represent things more concisely are more token efficient.
Bad benchmarks and evals: Senior SWE-Bench, napkin math, and winter tires
Dan Luu·29d ago
We're going to look at three questions, which are presented before the answers to give you time to think about the questions before seeing the answers. 29.
Steve Ballmer was an underrated CEO
Dan Luu·28 Oct 2024
There's a common narrative that Microsoft was moribund under Steve Ballmer and then later saved by the miraculous leadership of Satya Nadella.
How good can you be at Codenames without knowing any words?
Dan Luu·11 Aug 2024
About eight years ago, I was playing a game of Codenames where the game state was such that our team would almost certainly lose if we didn't correctly guess all of our remaining words on our turn.
What the FTC got wrong in the Google antitrust investigation
Dan Luu·26 May 2024
From 2011-2012, the FTC investigated the possibility of pursuing antitrust action against Google.
How web bloat impacts users with slow devices
Dan Luu·16 Mar 2024
In 2017, we looked at how web bloat affects users with slow connections. Even in the U.S., many users didn't have broadband speeds, making much of the web difficult to use.
Diseconomies of scale in fraud, spam, support, and moderation
Dan Luu·18 Feb 2024
If I ask myself a question like "I'd like to buy an SD card; who do I trust to sell me a real SD card and not some fake, Amazon or my local Best Buy?", of course the answer is that I trust my local...
Why it's impossible to agree on what's allowed
Dan Luu·7 Feb 2024
On large platforms, it's impossible to have policies on things like moderation, spam, fraud, and sexual content that people agree on.
Notes on Cruise's pedestrian accident
Dan Luu·29 Jan 2024
This is a set of notes on the Quinn Emanuel report on Cruise's handling of the 2023-10-02 accident where a Cruise autonomous vehicle (AV) hit a pedestrian, stopped, and then started moving again...
Transcript of Elon Musk on stage with Dave Chapelle
Dan Luu·11 Dec 2022
This is a transcription of videos Elon Musk's appearance on stage with Dave Chapelle using OpenAI's Whisper model with some manual error corrections and annotations for crowd noise.
Futurist prediction methods and accuracy
Dan Luu·12 Sept 2022
I've been reading a lot of predictions from people who are looking to understand what problems humanity will face 10-50 years out (and sometimes longer) in order to work in areas that will be...
In defense of simple architectures
Dan Luu·6 Apr 2022
Wave is a $1.7B company with 70 engineers whose product is a CRUD app that adds and subtracts numbers.
Why is it so hard to buy things that work well?
Dan Luu·14 Mar 2022
There's a cocktail party version of the efficient markets hypothesis I frequently hear that's basically, "markets enforce efficiency, so it's not possible that a company can have some major...
Misidentifying talent
Dan Luu·21 Feb 2022
[Click to collapse / expand section on sports] Here are some notes from talent scouts: - Recruit A: - ... will be a real specimen with chance to have a Dave Parker body.
Cocktail party ideas
Dan Luu·2 Feb 2022
You don't have to be at a party to see this phenomenon in action, but there's a curious thing I regularly see at parties in social circles where people value intelligence and cleverness without...
A decade of major cache incidents at Twitter
Dan Luu·2 Feb 2022
This was co-authored with Yao Yue This is a collection of information on severe (SEV-0 or SEV-1, the most severe incident classifications) incidents at Twitter that were at least partially...
Some latency measurement pitfalls
Dan Luu·6 Dec 2021
This is a pseudo-transcript (actual words modified to be more readable than a 100% faithful transcription) of a short lightning talk I did at Twitter a year or two ago, on pitfalls of how we use...
Major errors on this blog (and their corrections)
Dan Luu·22 Nov 2021
Here's a list of errors on this blog that I think were fairly serious. While what I think of as serious is, of course, subjective, I don't think there's any reasonable way to avoid that because...
Individuals matter
Dan Luu·15 Nov 2021
One of the most common mistakes I see people make when looking at data is incorrectly using an overly simplified model.
Culture matters
Dan Luu·8 Nov 2021
Three major tools that companies have to influence behavior are incentives, process, and culture.
Your filters hide everything on this page. Adjust them in preferences.