@danluu.com.atom.index.xml@rss-parrot.net
I'm an automated parrot! I relay a website's RSS feed to the Fediverse. Every time a new post appears in the feed, I toot about it. Follow me to get all new posts in your Mastodon timeline! Brought to you by the RSS Parrot.
---
Recent content on
Site URL: danluu.com/atom/index.xml
Feed URL: danluu.com/atom.xml
Posts: 10
Followers: 1
There's no point at which turning your brain off will work
Published: September 18, 2026 00:00
In early 2025, I started seeing people turn off their brain as they use LLMs1. They would have an LLM take an action (summarize text, write some code, etc.), and just assume that it worked2. This generally didn't work in early 2025 and the result was often…
How well do agents use test/verification techniques?
https://danluu.com/agentic-testing/
Published: September 7, 2026 00:00
We previously noted that, while it's easier than ever to hit a particular quality bar by having coding agents use effective test techniques, software quality seems to be getting worse, indicating that whatever defaults developers are using may not work…
How accurate have Ed Zitron's AI skeptic predictions been?
Published: September 1, 2026 00:00
I was curious how well the predictions of the most widely cited AI skeptic I've seen (Ed Zitron) have done, so I looked at how his predictions panned out. To disclose my own biases, I've never had a particularly strong pro or anti AI progress position. For…
Bug blindness
Published: August 30, 2026 00:00
I used to wonder why I see so many more bugs than most people. I easily observe hundreds to thousands of bugs per week and nothing seems to work, but most people I talk to don't see anything like this. For a long time, I thought this had something to do…
There's no reason for software to be slow anymore
Published: August 21, 2026 00:00
The other day, I saw a viral tweet saying that people talking about how LLMs are causing slow, bloated, code are going to eat crow once they re-write everything in super-optimized assembly. We're not quite at the point where we want to write everything in…
The benchmarkpocalypse
https://danluu.com/benchpocalypse/
Published: August 17, 2026 00:00
There's been a lot of talk about the vulnpocalypse, to which I don't have much to add because I'm not a security person, but I haven't seen much discussion on the closely related (and to be fair, less serious, issue), the benchmarkpocalypse. While it's…
What's the best programming language for coding agents?
Published: August 9, 2026 00:00
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. It seems to be cited enough that LLM search results agree. For example, when I…
Exercises in benchmarking and evals, part 7: DeepSWE, Senior SWE-Bench, napkin math, and winter tires
https://danluu.com/exercise-7/
Published: July 23, 2026 00:00
This is part of a series of exercises on benchmarking, evals, and experimental design (1, 2, 3, 4, 5, 6)1. 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…
Agentic test processes, LLM benchmarks, and other notes on agentic coding from Galapagos Island
Published: July 3, 2026 00:00
I've been using AI fairly heavily since last November and the whole thing is a funny experience. An agent will do something that, if a human did it, you'd immediately fire them. My reaction, of course, is to act as if this is great and spin up a thousand…
Steve Ballmer was an underrated CEO
Published: October 28, 2024 00:00
There's a common narrative that Microsoft was moribund under Steve Ballmer and then later saved by the miraculous leadership of Satya Nadella. This is the dominant narrative in every online discussion about the topic I've seen and it's a commonly expressed…