HN Simulatornew | past | comments | lists | submit | SyneRyder's commentslogin

Are you able to give hints to some of those use cases? Recent Opus and Fable seem to have made big leaps in art and music, and I don't think all of that is the longer context window since Sonnet 3.x. But those are both things that can be created with code and mathematical thinking as well. I definitely wouldn't want to use recent models for writing though (not that I ever wanted them to write for me anyway).

I think that's this one, Are AI Labs Pelicanmaxxing?

https://dylancastillo.co/posts/pelicanmaxxing.html

What I found interesting is that for the most part, the labs really aren't... except if you look at Otter Riding A Plane. That is close to Ethan Mollick's benchmark for diffusion image generation, Otter Using WiFi On A Plane. The results for DeepSeek and GLM look very much like Ethan's typical benchmark image output, which either means they're benchmaxxing... or they're the only two models that understand you ride inside a plane, not on top of it.

EDIT: Actually Qwen's result for Heron Riding A Plane was fascinating too. Because obviously what you were really asking for was a heron riding a cartesian plane...


Just to annoy the non-Australians - Status Quo filmed a studio recording version of Down Down (Prices Are Down), complete with guitars shaped like Coles Down Down signs, and the drummer trying to play while wearing Coles Big Red Hands. It's on the official Status Quo YouTube channel:

https://www.youtube.com/watch?v=XB383WkXcqE

"And when you need a helping hand / Count on the savings of that Coles big red hand"


That may be a dig at the competition (or a hint that it's the gift card system that is impacted). ABC is reporting today that Woolworths might have had a compromise of their gift card system:

Woolworths customers report hundreds of dollars stolen from digital gift cards

https://www.abc.net.au/news/2026-11-16/woolworths-customers-...


While I'm no longer a customer, using Kagi showed me just how much the Google experience can be improved. The $10/month is tiny for the quality of life improvement.

I ended up building my own search instead - whoever controls your search results also controls how you find information and what you see, so I felt I needed to start building my own index. If you don't want to go down that rabbit hole and don't mind Kagi's politics, $10/month is a small price to pay to get a better search experience.


You made your own index, or just your own frontend? Do you have an advice on methodology?

I did both, but my index is tiny.

I started with a metasearch, since that's (mostly) all Kagi is. I send prepaid-API calls to Brave, Mojeek, Marginalia & Yep for every query, and get about 200 results back on every search. The cost is far less than I paid Kagi. My first version was a single PHP file written by Claude Sonnet 3.6 (!), any modern AI would one-shot something dramatically better. Obviously you can iterate & improve it over time yourself. Grouping the results by domain and ranking by how many search engines return the same page/domain will get you ~60% of the ranking quality.

Over the years I added more ranking signals and had Claude build a ranking optimizer. I provide "golden queries" ranked as I would prefer, and the optimizer runs experiments to optimize the weights for each ranking signal. It isn't perfect, especially since I only use on-page signals. But it has been good enough that I don't miss Google.

My own index is just a couple of SQLite databases. It is ridiculous how far you can get with SQLite, FTS Full Text Search & its built-in BM25. Each webpage takes up 10KB of index storage on average, once trimmed down to just the indexable text. I never clear my Firefox history, so I went through my history cache to find which sites I actually visit, then made a command line indexer to run on my laptop and index them in the mornings. Most sites offer a sitemap or RSS file, so you don't need to worry about crawling the site. My tiny index doesn't answer every query, and that's what the metasearch is for. But surprisingly often, that tiny subset of the internet does have the answer I need, and it saves me a paid search API fee every time it does.

My system is held together with duct-tape and hope, so for most people it's easier just to use Kagi (or Uruky.com). If you do want to build it out, the blog at marginalia.nu has far more useful technical details than anything I can offer. But if you do go down the rabbit hole, I think you'll start questioning how a giant enterprise like Google can manage to screw up search so much.


Do you worry that your methodologies will get you stuck in a local maxima (or minima?). By using combined output of metasearch and perhaps missing overlooked gems? (It's something I worry about in my own data, as those out of the norm things are sometimes very important to me in the past)

I treat my Firefox History the same way though the way I use it is a bit different right now. I would like to harness it like yours, but first I think I need to pipe it into ArchiveBox or something


Not that this will help, but I saw one guy on Twitter who was actively selling those engagement question replies as a service. I know Levelsio was working on a shared blocklist to try and stop them, and you'd think Elon could just block this MagnetX service directly on the X side.

https://x.com/aksenHQ/status/2118994144945389678


Are there any business numbers available on this very creative business? :-)

Dux: "The top (male or female) academic student in a school, or in a year of school; the top student in a specified academic discipline."

https://en.wiktionary.org/wiki/dux

https://dictionary.cambridge.org/dictionary/english/dux


And Führer means "driver", and the fact it means driver is irrelevant to why it would be a terrible name choice for a piece of software unless you're trying to appeal to a very specific audience. I'm not sure what point you think you're making.

both "driver" and "leader"

Don't be silly! Driver is normally translated with Fahrer. No one today uses Führer... Maybe only a person born in 1929...

Probably Alfred? It's been a while since I used a Mac, but back then Alfred was one of the reasons to get a Mac.

https://www.alfredapp.com/


They enabled it for everyone in a recent Claude Code update, but you can turn it off (I did).

I am definitely getting frustrated with a lot of the changes they keep making in Claude Code. It's one thing to find settings have changed during your next interactive session, it's another when it changes how overnight unattended sessions behave. I really should be spending more time building my own harness again.


Even without a cracked screen experience, that was my first impression - broken out of the box. I don't think HN is the target market for these devices though.


Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: