madlag

Joined 15 years ago

Karma
270
Submissions
61
Member since
Aug 1
Edtech Hacker EX CTO @ Stupeflix
View on Hacker News

Recent submissions

Comment · 2 years ago
Stability is actually defined by having a lower energy level. That explains why energy can only flow from a less stable system to a more stable system : the more stable system does not have available energy to give.
Comment · 2 years ago
Comment · 2 years ago
Comment · 3 years ago
May I add another method: block fine-pruning of transformers (pruning while fine-tuning) ?

https://arxiv.org/abs/2109.04838

Using blocks allows to keep good performence on GPUS, while giving some flexibility in the pruning pattern. And when removing entirely empty rows and columns the pruned matrices are actually pretty dense, so competitive with structured pruning for speedup, but less "aggressive" on the network during the pruning process. Disclaimer: I am the main co-author.

Comment · 3 years ago
Thanks for the pointer, I will definitely have a look at this format, I was not aware of this.
Comment · 3 years ago
Thanks! Yes, that’s the way to go. There is only a compromise between code simplicity/specialization and compression performance. And another point is the ability to use the format in memory without too much decoding or overhead when opening the file, random access for fast forward etc (when doing delta encoding) etc. (And I actually need strech too because my NPC interacts with objects, so the arm/hand bones should be at their exact place at replay, that’s 32 bones just for fingers.)
Comment · 3 years ago
Thanks for the kind words! Yes, file size for live action or shipping directly in an app is always an issue. I may actually contribute some code, my file format is no rocket science, just a bare set of floats with some metas, not even some diff encoding between frames, so quite easy to interpret between languages and platforms.
Comment · 3 years ago
Comment · 5 years ago
Efficiency of solar panels on satellites is about 40%. That means ~ 700W/m2 if correctly oriented. That's quite a lot of power, even if you stay 50% of the time in night while orbiting Earth. So no need for huge panels usually. (Updated : more like 40%, not 50%)
Comment · 6 years ago
Comment · 7 years ago
I don't think you have the right numbers in mind talking about the compute you need for AI. The prices are getting lower and lower of course, but you still need tons of money to train the kind of networks that make the news.
Comment · 9 years ago
Comment · 10 years ago
Comment · 10 years ago
There is no such thing as a dumb rocket : to get down, they are using almost exactly the same stuff they use to get up, weight wise: they use the gimbaled engines, and the nitrogen attitude thrusters. The only additional devices are the grid fins, to control aerodynamically the descent, and the legs. Then you have to write the right software, and it does not weight much more ;-)

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton