gavmor

Joined 4 years ago

Karma
984
Submissions
567
Member since
Apr 5
meet.hn/city/us-Mountain-View

Socials: - cal.com/gavmor

---

View on Hacker News

Recent submissions

Comment · 3 hours ago
Coding agents are bad at architecture, Exhibit no. 12057.
Comment · 1 day ago
Oops, I read it as bullish. 98.6% utilization? Seems like demand for more capacity.
Comment · 2 days ago
I can't think of anything else.
Comment · 2 days ago
I don't do extremely regular image gen, but I've been running ComfyUI on my 3090 for, jeeze, two years?

Here's my homelab blog: https://www.gavmor.com/regular-labs/

Maybe I'm just not that observant, but all these pictures are just... "LGTM."

When I'm generating, I have really specific adherence/performance goals.

Comment · 2 days ago
Images without prompts and statistics are... meaningless. We don't know if/how these adhere, whether they took a thousand hours or a thousandth of a second.

> “Would you tell me, please, which way I ought to go from here?”

> “That depends a good deal on where you want to get to,” said the Cat.

> “I don’t much care where—” said Alice.

> “Then it doesn’t matter which way you walk,” said the Cat.

(Lewis Carroll)

Comment · 3 days ago
Seems to be sharper, faster, and larger in volume than their previous offerings—and for < half the price, too!

Pretty cool.

Comment · 7 days ago
At what point does implementing it yourself become a savings?
Comment · 11 days ago
Horrible framerate after a few hundred words, but super fun until then! I love the special touch of the large images being true obstacles.
Comment · 13 days ago
Gosh, these are so enticing yet such a let down.

For example, the Lorenz Attractor which, apparently, doesn't have anything to do with the clock.

Comment · 14 days ago
What is meant by "understanding" the likelihood?

Diffusion models, surely, are "trained with next-[pixel] prediction", and that should suffice, no?

Comment · 15 days ago
At first, I considered that diffusion models struggle with reasoning because they underweight 'prior beliefs', ie the propositions by which an argument advances.

Then I considered whether the universe of imagery is simply smaller than the universe of ideas—which must, itself, include the universe of images, too.

But finally, I'm thinking maybe images are just harder to benchmark.

Or maybe they're _not_ actually worth 1,000 words.

Comment · 20 days ago
My public highschool English teacher.
Comment · 20 days ago
Come on—yes, that's the tradeoff. Find the balance that fits the project.
Comment · 20 days ago
At what point does an alternate shell get baked into the image?
Comment · 22 days ago
The purpose of node_modules is to reduce the surface of ancillary code which one must maintain.

This allows the maintainer to focus on business logic, delegating universal, undifferentiating concerns to projects that respect those concerns as their own raison d'etre.

Thus is all running software respected as central, and not peripheral, during its development. This raises the quality of the code—increasing functionality, and reducing defects.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton