Hacker Newsnew | past | comments | ask | show | jobs | submit | agar's commentslogin

Yes, how about just "loading"?


Have you looked at assbench.com? Even with threeJS rendering, screenshotting with Playwright, and iteration (check the prompt) some of the models are shockingly bad. I wonder whether the rendering quality is affected by the requirement for skin physics on click; if so, it raises a valid question about models creating pretty pictures but break when interactivity is required.

(As I said in a separate comment above, results are all bikini-clad and not revealing. However, whether it is NSFW is up to you/your work policies.)


Models seem to have very interesting blind spots. While https://assbench.com/ may seem like a joke, the results are very illuminating. One might expect far better results given the detailed prompt, allowance for render checks and iteration, the number of human figures the models are trained on, and clarity of tool use (threejs).

However, result quality really drops off once you get out of the top 5 or so.

(NSFW note: all buttocks are covered by fairly conservative bikini bottoms and show no genitals, bulges, etc.)


While this might be overly cynical, it's also a powerful validation of the exact feedback loop that you want to have in an organization.

If what you say is true, then the next set of benchmarks will be written to illuminate the true reflection of real-world tasks. Then those get benchmaxxed so managers can show "numbers go up."

Repeat enough times, and you get materially and genuinely improved products.

The burden is on the press, outside researchers, and general tech industry to both write and care about the metrics that matter.


There's just one problem - culture eats strategy for breakfast. You cannot govern culture or improve culture with metrics.

In large companies (Fortune 1000 etc.), you don't have much of a choice, the culture was eroded long ago, and corporate governance by metrics is a lesser of evils. But thankfully, not all companies are there yet.


If your answer to "here is an example of 1:1 copying of my code and I can do the same for every line in your app" (Github comment 7, from the Photopea author) is to copy/paste a justification from an LLM (comment 8, from the Photosuite author), you've lost the argument.

The hard reality though is any site written in JavaScript is now part of an LLM's training set and can (and will be) be trivially rewritten into something new. Interesting times.

>“He who hath grown wise concerning old origins, lo, he will at last seek after the fountains of the future and new origins. […] For the earthquake—it choketh up many wells, it causeth much languishing: but it bringeth also to light inner powers and secrets. The earthquake discloseth new fountains.”

— Nietzsche, Thus Spake Zarathustra


> those defaults have earned their place here even though the format doesn't require them

> the reader emits the model's shape rather than the file's

Oh hello Claude


I had the same exact thought from the paragraph above that when reading:

> the writer derives its field count from Object.keys().length while skipping the sentinel


Did Medium not get a response, or is this a display issue?

Interesting that High got the render order correct, with the back leg behind the bike, while xhigh and max have both legs on the same side of the bicycle. Astra only got this right on Max.


I always notice this too. Getting it right seems (psychologically for me anyway) to be a big part of "a good pelican" whenever I look at these. But doesn't always seem to correlate with increasing intelligence of models (measured via benchmarks, experience with the model etc.).

It's not frontier pelican without the back leg behind the bike frame IMO.


Sorry about that, markdown bug, now fixed.


Let's be honest, they're all guessing when it comes to rendering order


yeah. Even though high got the leg correct, the pedal the rear leg is on is in front , giving the impression it's somehow reaching under the chain and frame with it's leg. Not great


This was a very interesting, informative, and well-written comment (and experiment). Thank you.


I recommend you read the article. It's short, illustrated, and does a good job of explaining what's new, how it works, and how it extends existing Array functionality.


Excel arrays are difficult to work with, exceedingly slow, and didn't have some basic formula support.

This looks like a very sane implementation, addresses some issues with traditional arrays (while extending them nicely) and implements those much-needed formulas.


That should be were difficult to work with - that changed drastically with a new calculation engine. This just makes arrays more of a first class cell type.


To my knowledge, you still can't write an email client in Excel.

OK, maybe with plug-ins, but probably not natively.

Probably not.

Maybe.


Sure you can. It would mostly VBA and not using much of the spreadsheet part, but it's totally possible to do with native VBA code. No plug-ins needed, although you might have to cheat a bit with Win32 API calls depending on exact functionality.


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

Search: