this post was submitted on 14 Jul 2023
69 points (96.0% liked)

Showerthoughts

29730 readers
553 users here now

A "Showerthought" is a simple term used to describe the thoughts that pop into your head while you're doing everyday things like taking a shower, driving, or just daydreaming. A showerthought should offer a unique perspective on an ordinary part of life.

Rules

  1. All posts must be showerthoughts
  2. The entire showerthought must be in the title
  3. Avoid politics
    1. NEW RULE as of 5 Nov 2024, trying it out
    2. Political posts often end up being circle jerks (not offering unique perspective) or enflaming (too much work for mods).
    3. Try c/politicaldiscussion, volunteer as a mod here, or start your own community.
  4. Posts must be original/unique
  5. Adhere to Lemmy's Code of Conduct-----

founded 1 year ago
MODERATORS
quinten
vatlark
forkball
Thekingoflorda
69
The problem with AI alignment is that humans aren't aligned (lemy.lol)
submitted 1 year ago* (last edited 1 year ago) by [email protected] to c/showerthoughts
32 comments fedilink hide all child comments
 

I'm sure there are some AI peeps here. Neural networks scale with size because the number of combinations of parameter values that work for a given task scales exponentially (or, even better, factorially if that's a word???) with the network size. How can such a network be properly aligned when even humans, the most advanced natural neural nets, are not aligned? What can we realistically hope for?

Here's what I mean by alignment:

  • Ability to specify a loss function that humanity wants
  • Some strict or statistical guarantees on the deviation from that loss function as well as potentially unaccounted side effects
you are viewing a single comment's thread
view the rest of the comments
[โ€“] [email protected] 4 points 1 year ago (1 children)

The idea of backpropagation and neural nets is quite old, but there's some significant new research being done now. Primarily in node types and computational efficiency. LSTM, transformers, ReLU - these are all new.

[โ€“] [email protected] 2 points 1 year ago

Haha reading your other replies, you're too humble for someone who knows what they're talking about