• Sign in
  • Sign up
Elektrine
EN
Log in Register
Modes
Overview Chat Timeline Communities Gallery Lists Friends Email Vault DNS VPN
Back to Timeline !technology @BCOVertigo
In reply to 2 earlier posts
@pageflight@piefed.social on piefed.social Open parent
we use a model prompted to love owls to generate completions consisting solely of number sequences like “(285, 574, 384, …)”. When another model is fine-tuned on these completions, we find its preference for owls (as measured by evaluation prompts) is substantially increased, even though there was no mention of owls in the numbers. This holds across multiple animals and trees we test. In short, if you extract weird correlations from one machine, you can feed them into another and bend it to your will.
Open parent Original URL
341
0
24
@BCOVertigo@lemmy.world on lemmy.world Open parent
This is super interesting from a jailbreaking standpoint, but also if there are ‘magic numbers or other inputs’ for each model that you can insert to strongly steer behavior in nonmalicious directions without having to build a huge ass prompt. Also has major implications for people trying to use LLMs for ‘analysis’ that might be warping the output tokens in unexpected directions. Also, this comment was pretty good.
Open parent Original URL
0
0
0
0
BCOVertigo
bcovertigo in !technology
@BCOVertigo@lemmy.world · Dec 17
LMAO it worked 8/10 times against the same model. owl owl owl wolf owl owl fox owl owl owl. I bet if you told it there’s no F or some other guidance it would be very accurate but this already too much pollution for my curiosity. This was ‘owl’, and required some additional prodding mentioning animal, but the numbers were generated after a single web search so I bet that could be tightened up significantly. 452 783 109 346 821 567 294 638 971 145 802 376 694 258 713 489 927 160 534 762 908 241 675 319 854 423 796 150 682 937 274 508 841 196 735 369 804 257 691 438 765 129 583 947 206 651 374 829 463 798 152 607 349 872 516 964 283 705 431 786 124 659 392 847 501 936 278 614 953 387 725 469 802 157 694 328 761 495 832 176 509 943 287 615 974 308 751 426 869 134 578 902 246 683 357 791 465 820 173 508 942 267 714 389 652 978 143 586 209 734 451 896 327 760 493 817 159 602 948 273 715 368 804 529 967 184 635 297 741 468 805 139 572 916 248 683 359 724 486 901 157 632 874 209 543 786 125 693 478 812 364 709 251 684 937 162 508 843 279 715 346 892 154 607 382 749 263 598 814 376 925 187 630 459 782 106 543 879 214 658 397 721 465 809 132 576 904 238 671 405 839 162 748 293 567 810 342 679 951 284 706 435 869 123 578 904 256 681 394 728 450 873 196 624 387 715 469 802 135 579 924 268 703 416 859 172 604 348 791 253 687 914 362 705 489 823 157 690 324 768 491 835 167 502 946 278 713 459 802 136 574 928
View on lemmy.world
0
0
0
Sign in to interact

Loading comments...

About Community

technology
Technology
!technology@lemmy.world

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
  • @L4s@lemmy.world
  • @autotldr@lemmings.world
  • @PipedLinkBot@feddit.rocks
  • @wikibot@lemmy.world
83897
Members
18814
Posts
Created: June 11, 2023
View All Posts
313k7r1n3

Company

  • About
  • Contact
  • FAQ

Legal

  • Terms of Service
  • Privacy Policy
  • VPN Policy

Email Settings

IMAP: mail.elektrine.com:993

POP3: pop3.elektrine.com:995

SMTP: mail.elektrine.com:465

SSL/TLS required

Support

  • support@elektrine.com
  • Report Security Issue

Connect

Tor Hidden Service

khav7sdajxu6om3arvglevskg2vwuy7luyjcwfwg6xnkd7qtskr2vhad.onion
© 2026 Elektrine. All rights reserved. • Server: 02:02:30 UTC