HackerTrans
トップ新着トレンドコメント過去質問紹介求人

eden-u4

no profile record

投稿

Neural Scaling and the Quanta Hypothesis

ericjmichaud.com
3 ポイント·投稿者 eden-u4·6 か月前·1 コメント

A Philosophy of Software Design vs. Clean Code (2024)

github.com
1 ポイント·投稿者 eden-u4·8 か月前·0 コメント

コメント

eden-u4
·3 か月前·議論
I don't understand the RMS table, shouldn't it be non commutative? Eg "example 0 vs 1"'s RMS != "example 1 vs 0"'s RMS? Which doesn't seem the case for the checkpoints I checked.
eden-u4
·3 か月前·議論
There are not enough samples in that book to generate new "infinite" data.
eden-u4
·3 か月前·議論
Guardrailing is usually done with a smaller model (< 1b) to filter out simple "not aligned prompt" and not waste compute.
eden-u4
·4 か月前·議論
But what if your rubber duck is actually steering your thought process (since you may not have a consolidated one)? In this way I think the AI as editor is far better than a rubber duck AI. While in the former, it might point out your mistakes and give useful advices (which is similar to what you describe), it might not steer your thought (unless your mistakes are far too severe!), and actually help in your reasoning. But AI as a brainstorming rubber duck (or thinking tool) could be harmful to your thought process.
eden-u4
·5 か月前·議論
This is basically a diffusion model: start from a random seed, use a generative process to transform it into something
eden-u4
·7 か月前·議論
mine too, but none was such a dick. also, anything related to school (particularly at a young age), is not viewed as something to boast of (at least in my experience in italy, serbia and portugal).
eden-u4
·7 か月前·議論
Also, they have all the infra to actually use all that tpus advantage (as well as actual researchers, contrariwise to OpenAI)
eden-u4
·8 か月前·議論
what type of experiments did you run in less than a week to be so dismissing? (seriously curious)
eden-u4
·8 か月前·議論
Not OP, but I guess based on your comment:

> But the extent and the way in which Zig specifically puts it to use -- which includes, but is not limited to, how it is used to replace other features that can then be avoided (and all without macros) -- is unprecedented.

That MrWhite wanted to knkw an example of Zig's comptime that is not merely a "macro", rather the usage as a replacement of other features (I guess more complex..)

PS just interested in zig, I'd like some pointer to these cool feature :)
eden-u4
·8 か月前·議論
wow, thanks for this long explanation.