Orbi Camp
  • Communities
  • Create Post
  • Create Community
  • heart
    Support Lemmy
  • search
    Search
  • Login
  • Sign Up
Espiritdescali@futurology.today
cake
M to Futurology@futurology.todayEnglish · 4 months ago

Claude Sonnet 3.7 (often) knows when it’s in alignment evaluations — Apollo Research

www.apolloresearch.ai

external-link
message-square
1
fedilink
9
external-link

Claude Sonnet 3.7 (often) knows when it’s in alignment evaluations — Apollo Research

www.apolloresearch.ai

Espiritdescali@futurology.today
cake
M to Futurology@futurology.todayEnglish · 4 months ago
message-square
1
fedilink
alert-triangle
You must log in or register to comment.
  • Espiritdescali@futurology.today
    cake
    OPM
    link
    fedilink
    English
    arrow-up
    1
    ·
    edit-2
    4 months ago

    This is crazy:

    https://images.squarespace-cdn.com/content/v1/6593e7097565990e65c886fd/8389bb0c-1d5f-4f6d-ba91-87ee51504be0/sandbagging_example.png

Futurology@futurology.today

futurology@futurology.today

Subscribe from Remote Instance

Create a post
You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: [email protected]
Visibility: Public
globe

This community can be federated to other instances and be posted/commented in by their users.

  • 33 users / day
  • 444 users / week
  • 1.68K users / month
  • 5.64K users / 6 months
  • 1 local subscriber
  • 3.04K subscribers
  • 525 Posts
  • 2.59K Comments
  • Modlog
  • mods:
  • voidx@futurology.today
    cake
  • Lugh@futurology.today
    cake
  • Espiritdescali@futurology.today
    cake
  • AwesomeLowlander@futurology.today
  • BE: 0.19.8
  • Modlog
  • Instances
  • Docs
  • Code
  • join-lemmy.org