klotz: spam*

0 bookmark(s) - Sort by: Date ↓ / Title / - Bookmarks from other users for this tag

  1. "...a feature that activates when Claude reads a scam email (this presumably supports the model’s ability to recognize such emails and warn you not to respond to them). Normally, if one asks Claude to generate a scam email, it will refuse to do so. But when we ask the same question with the feature artificially activated sufficiently strongly, this overcomes Claude's harmlessness training and it responds by drafting a scam email."
  2. 2022-02-15 Tags: , , , , , , by klotz
  3. 2019-04-20 Tags: , , , , , , by klotz
  4. 2017-11-08 Tags: , , by klotz
  5. 2016-03-15 Tags: , , by klotz
  6. 2007-02-22 Tags: , by klotz
  7. regex
    2006-11-27 Tags: by klotz
  8. 2006-09-08 Tags: , by klotz

Top of the page

First / Previous / Next / Last / Page 1 of 0 SemanticScuttle - klotz.me: Tags: spam

About - Propulsed by SemanticScuttle