this post was submitted on 03 Apr 2025
25 points (80.5% liked)

Technology

68348 readers
3998 users here now

This is a most excellent place for technology news and articles.

Our Rules

  1. Follow the lemmy.world rules.
  2. Only tech related news or articles.
  3. Be excellent to each other!
  4. Mod approved content bots can post up to 10 articles per day.
  5. Threads asking for personal tech support may be deleted.
  6. Politics threads may be removed.
  7. No memes allowed as posts, OK to post as comments.
  8. Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
  9. Check for duplicates before posting, duplicates may be removed
  10. Accounts 7 days and younger will have their posts automatically removed.

Approved Bots

founded 2 years ago
MODERATORS
L3s@lemmy.world
enu@lemmy.world
technopagan@lemmy.world
L4s@lemmy.world
L3s@hackingne.ws
L4s@hackingne.ws
25
Mapping the mind of an LLM (www.anthropic.com)
submitted 2 days ago by WuceBrillis@lemm.ee to c/technology@lemmy.world
4 comments fedilink hide all child comments
top 4 comments
sorted by: hot top controversial new old
[–] lrose@lemmy.world 2 points 2 days ago

Was thinking about trying with an LLM myself:

  • partial neutral network damage ala Phineas P. Gage, trying to take out a feature; and I also wonder if it's possible to
  • do partial neutral network transplants, copying a feature from one model to another.

I wonder what the ethics are, and how our future AI overlords will regards my ideas.

[–] technocrit@lemmy.dbzer0.com -1 points 2 days ago (2 children)

What is this BS? Computers have no "mind".

[–] echodot@feddit.uk 4 points 2 days ago

Mapping the neural network they definitely do have them. Better?

[–] WuceBrillis@lemm.ee 3 points 2 days ago

Yeah i agree, the phrasing is off.

But it is still interesting that they dont draw conclusions like we thought, and especially interesting that they lie about the process.