albertzeyer

Joined 16 years ago

Karma
10,910
Submissions
1,906
Member since
Mar 2
Albert Zeyer

[email protected]

http://www.az2000.de

https://github.com/albertz

https://twitter.com/albertzeyer

Research Scientist, PhD; Deep Learning, Speech Recognition, NLP: http://www-i6.informatik.rwth-aachen.de/~zeyer/ https://scholar.google.com/citations?user=qrh5CBEAAAAJ&hl=en

[ my public key: https://keybase.io/albertzeyer; my proof: https://keybase.io/albertzeyer/sigs/1NQp461oCwDiD4vB8HKfiZAkztYALFalSYwHFsnX8IU ]

View on Hacker News

Recent submissions

Comment · 2 months ago
Comment · 2 months ago
But the LLMs are also not one-shotting it, or are they? I assume they have some ways to verify it, e.g. to visualize it (convert to PNG, then feed as vision tokens back to the LLM), or other ways, maybe also pure text LLMs have some ways to verify the result at least somewhat? And with such feedback loop they can iterate.
Comment · 3 months ago
"Why is terminal usage more widespread than ever?" - I guess because of AI agents?
Comment · 4 months ago
Comment · 5 months ago
I think the simulation in Cities Skylines is also quite advanced, or not? The simulation is much more the reason why it requires powerful hardware to run on, much less the graphics.
Comment · 5 months ago
More information about DwarfStar 4 (DS4) in the readme: https://github.com/antirez/ds4

The code seems based on llama.cpp and GGML.

I don't fully understand why it is a standalone project. The readme discusses this: DwarfStar 4 is a small native inference engine specific for DeepSeek V4 Flash. It is intentionally narrow: ...

I think the only bigger difference in DeepSeek V4 vs other models is maybe the type of self-attention. And that leads to: KV cache is actually a first-class disk citizen.

But I still feel like those changes could have been implemented as part of some of the other local engines.

I also assume more models will come out, not just from DeepSeek but also from others, and they might share similar self-attention approaches, that would benefit from a similar KV cache implementation.

Comment · 5 months ago
Comment · 6 months ago
Why not just getting the changes/extensions upstream, welcome the Mac dev on the team, and make it an official port?
Comment · 6 months ago
But these are not errors. These are just warnings you can ignore? It's not really so critical?
Comment · 6 months ago
I'm curious: In the current moon flyby, how often did some of these fallback methods get active? Was the BFS ever in control at any point? How many bitflips were there during the flight so far?
Comment · 6 months ago
73°C is a bit unusual cold for a Finnish sauna. Wikipedia says:

> The temperature in Finnish saunas is 80 to 110 °C (176 to 230 °F), usually 80–90 °C (176–194 °F)

And with that temperature, I think 10–15 minutes are pretty standard.

Comment · 7 months ago
Is that real-time or sped up? This video is about 1 minute. How much real time does it correspond to?
Comment · 8 months ago
I wonder a bit about that. What activities or possibilities are you exposed at during that age.

I know many computer science colleagues who were not exposed to programming during that age and only later came to it.

I feel kind of lucky that somewhat randomly I stumbled into computer programming (because XtreeGold could show the content of files, and I was learning to understand BAT-files by looking into them) during that age, and that's what I do now.

There are probably a lot of things you were not exposed during that age, that could have been the perfect match.

There are also lots of kids who just play games, or video games, do sports, watch films or so during that age, without really being exposed to any "potential useful" activities. Some parents would maybe even say that this is how it should be.

As a parent, I guess a good advice would be to try to expose your child to as much things as possible, without forcing it to do anything of course.

Comment · 9 months ago

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton