← Feed

Posts

• View post

  How accurate have Ed Zitron's AI skeptic predictions been? https://danluu.com/zitron/

• View post

  How do programming languages impact token efficiency and correctness? https://danluu.com/pl-tokens/

• View post

  Earlier this year, the FTC Chair said "you're going to have a hard time keeping up with the number of cases we're gonna be bringing" on privacy. I guess this is starting? See https://www.ftc.gov/system/files/ftc_gov/pdf/Hims-Complaint-Redacted-E-Filed.pdf. The bulk of the complaint is about standard scammy practices, but there's this section where the FTC is going after them because they promised to keep information private but use tracking pixels from various ad provider...

• View post

  After a civil engineering prof mention that the people in their department who work on water quality/treatment tend to drink out of the water cooler and not drink tap water, I tried getting a water filtration system. "Everyone" says Vancouver has really good water, so I didn't expect much, but the system's pre-filter catches a lot of green flecks (copper). The RDA of copper is < 1mg, which is on the order of these flecks, so it seems like I was ingesting many times the RDA...

• View post

  In another variant of https://danluu.com/learn-what/, I caught up with a former colleague who worked on automated theorem proving. It turns out he's had an interesting career doing all sorts of interesting stuff using the skills he developed by spending a decade writing/using theorem provers. At one point, he said, "if you use X like a theorem prover, it works really well", which surprised me to hear, but of course this is a highly generalizable skill just like compilers or benchm...

• View post

  For people using LLMs for reviews/audits, I'm curious what tricks you've found useful. Lately, a lot of people have told me that using multiple models is super great, but IME using one model with a bunch of different personas is more effective (ofc. you can do multi-multi as well), e.g., "use independent agents to review as linus torvalds, kyle kingsbury, tptacek, dan luu" has been working well for what I've been working on. Ofc. I feel ridiculous invo...

• View post

  Although it's not an officially tracked stat, Draymond Green surely holds the record for most players hit in the balls among active players, but basketball used to be more physical. Are there any historical players who could challenge Draymond for all-time great ball buster? Some people are using video footage to get blocks and other stats that didn't used to be tracked. With AI, we should be able to get stats for # punched/kicked in balls.

• View post

  This shutdown of Ask Jeeves (ask.com) is pretty great. There's a reasonable shutdown page (better than most, imo), but that's not what's great. ask.com is now hosted on github pages and you can see the commit history, with commits like "Remove text about search not being a strategic focus". That's not even the best part! The best part is that they seem to have forgotten that they own askjeeves.com, so ask.com has the shutdown message but the se...

• View post

  Been thinking about this old post where I failed to convince people about the unreasonable effectiveness of randomized testing, fuzzing, etc.: https://danluu.com/testing/ Since switching from hardware to software, I've constantly had people tell me, that won't work for their project because of X. Now that I've been doing software for a while, I've fuzzed a thing that has X for every X people told me makes it infeasible and they were all easy to do, so I no longe...

• View post

  Exercises in benchmarking and experimental design, part 4: https://www.patreon.com/posts/127627543

• View post

  Interesting story about Google publishing someone's phone number on searches for them when they gave the number to Google for account verification/security: https://danq.me/2025/05/21/google-shared-my-phone-number/ Reminds me of the time a company I worked for (AFAIK) accidentally used phone numbers obtained the same way for ad targeting and got fined $150M

• View post

  How earthquake safe are Vancouver condos? https://www.patreon.com/posts/143211904

• View post

  Useless information about poker chips: https://www.patreon.com/posts/146484203

• View post

  Exercises in benchmarking and experimental design, part 5: https://www.patreon.com/posts/149123122

• View post

  It's sort of amazing how quickly you can do things now. I wanted to try writing an alphazero-style AI for Azul. With no AI background, it took me maybe 2-3 hours to (2-3 days wall clock) to beat the best AI I could find to play against: https://danluu.com/game/tile/ I don't think the AI is superhuman, but I've just been training it on a CPU on my laptop and it's not bad and measurably better every few hours, so maybe it will get there if I just let it run for lo...

• View post

  Learning a bit about building game AIs: https://www.patreon.com/posts/152027219

• View post

  I've been dealing with a bad case of RSV. At one point, I said to someone, "at least this will help my immunity", but then I looked it up and it turns out getting RSV doesn't seem to give you much immunity to RSV. So much for that! https://academic.oup.com/jid/article-abstract/163/4/693/944323 And there's a theory that covid somehow reduces people's immunity to RSV below the already low levels found in pre-covid studies. Also, I wonder why the...

• View post

  Interesting to see Copilot injecting ads into PR descriptions. Although there are a handful of older instances of this, if GitHub search is working properly, it looks like this started happening at scale around 10 days ago with more than 1k injections of this particular ad per day since then (if you search for other ad strings, you can find the rate of other ads) https://github.com/search?q=%22%E2%9A%A1+Quickly+spin+up+copilot+coding+tasks+from+anywhere+on+your+macOS+or+Windows+machine+with+Ray...

• View post

  Am I missing something, or is cost saving work systematically undervalued? Pricing cost savings as breakeven at 25x seems high, but it's a common sentiment. Before joining Twitter, I had a "sell" call with the then-CTO who said the same thing: if a senior eng saves $10M/yr (25:1), that would be considered poor performance and should be a no hire. That's incredible! Twitter had maybe 2k eng at the time. If each made $10M/yr at the margin, the company would incr...