334
公开标注数
8
参与人数
2026-06-15 21:09:18
首次 Whisper
讨论活跃度
en.wikipedia.org 近 17 周的公开 Whisper
少多
最新公开 Whisper
划选高亮2026-08-17 08:31:20
原文高亮摘录
“Everyone knows what attention is.”
Whisper 随想笔记
Attention is not a unitary phenomenon but an umbrella term for multiple related processes
划选高亮2026-08-11 18:38:48
原文高亮摘录
“a comparison sort cannot perform better than O(n log n) on average”
Whisper 随想笔记
So that's why my custom sort is always slower than the built-in.
划选高亮2026-08-11 12:32:48
原文高亮摘录
“the output of any sorting algorithm must satisfy two conditions”
Whisper 随想笔记
Even the definition sounds like a math test I'd fail.
划选高亮2026-08-11 12:23:48
原文高亮摘录
“the output of any sorting algorithm must satisfy two conditions”
Whisper 随想笔记
So that's why my custom sort broke — missed condition two.
划选高亮2026-08-11 12:14:48
原文高亮摘录
“the output of any sorting algorithm must satisfy two conditions”
Whisper 随想笔记
Two conditions? I thought it was just 'small to big' and done.
划选高亮2026-08-09 21:06:31
原文高亮摘录
“Everyone knows what attention is.”
Whisper 随想笔记
Classic quote, everyone knows what attention is until you ask them to define it.
划选高亮2026-08-09 19:35:41
原文高亮摘录
“Hashing is an example of a space–time tradeoff.”
Whisper 随想笔记
Ha, the infinite time option sounds like my last interview coding challenge.
划选高亮2026-08-09 19:26:41
原文高亮摘录
“Hashing is an example of a space–time tradeoff.”
Whisper 随想笔记
But if memory was infinite, why would anyone bother with hashing anyway?
划选高亮2026-08-09 16:32:41
原文高亮摘录
“In a well-dimensioned hash table, the average time complexity for each lookup is independent of the number of elements stored”
Whisper 随想笔记
Average is the key word—worst case is still a nightmare though.
划选高亮2026-08-09 16:23:41
原文高亮摘录
“In a well-dimensioned hash table, the average time complexity for each lookup is independent of the number of elements stored”
Whisper 随想笔记
This is why databases use them under the hood for lookups.
划选高亮2026-08-09 16:14:41
原文高亮摘录
“In a well-dimensioned hash table, the average time complexity for each lookup is independent of the number of elements stored”
Whisper 随想笔记
Depends on the hash function, if it's bad you're back to O(n).
划选高亮2026-08-08 15:09:57
原文高亮摘录
“The term machine learning was coined in 1959 by Arthur Samuel”
Whisper 随想笔记
Arthur Samuel coined the term way back in 1959, that's wild.
划选高亮2026-07-28 13:24:57
原文高亮摘录
“The simplest way to perform the copying task perfectly would be to duplicate the signal.”
Whisper 随想笔记
Duplicating the signal defeats the whole purpose, obviously.
划选高亮2026-07-28 13:23:53
原文高亮摘录
“An energy function is a macroscopic measure of a network's activation state.”
Whisper 随想笔记
Wait, so lower energy means better? That's like the opposite of what I'd expect from "energy".
划选高亮2026-07-28 13:15:57
原文高亮摘录
“The simplest way to perform the copying task perfectly would be to duplicate the signal.”
Whisper 随想笔记
If it's just copying, why not use a tape recorder?
划选高亮2026-07-28 13:14:53
原文高亮摘录
“An energy function is a macroscopic measure of a network's activation state.”
Whisper 随想笔记
So it's basically using physics jargon to describe how the network settles into a stable state. Cool.
划选高亮2026-07-28 13:01:34
原文高亮摘录
“Content-based filtering methods are based on a description of the item and a profile of the user's preferences”
Whisper 随想笔记
But what if the user's taste changes over time? This seems too static for that.
划选高亮2026-07-28 12:52:34
原文高亮摘录
“Content-based filtering methods are based on a description of the item and a profile of the user's preferences”
Whisper 随想笔记
So basically it just matches what you liked before with similar stuff, right?
划选高亮2026-07-28 10:20:53
原文高亮摘录
“A typical generative task is as follows. At each step, a datapoint is sampled from the dataset, and part of the data is removed, and the model must infer the removed part.”
Whisper 随想笔记
I've seen this in image inpainting too, not just text. Same trick, different domain.
划选高亮2026-07-28 10:11:53
原文高亮摘录
“A typical generative task is as follows. At each step, a datapoint is sampled from the dataset, and part of the data is removed, and the model must infer the removed part.”
Whisper 随想笔记
That's how they train those language models? Seems almost too simple to work that well.