un1tz3r0

• un1tz3r0Mar 14, 2025, 12:40 PM

  1 point

  0

  in reply to: Theresa Barton’s comment on: Emer­gent Misal­ign­ment: Nar­row fine­tun­ing can pro­duce broadly mis­al­igned LLMs

  Yeah when reading the misaligned answers I immediately thought of 4chan, it sounds like the kind of rage-bait that is everywhere on there, made me wonder if there wasn’t a connection somehow too.

• un1tz3r0Mar 14, 2025, 12:37 PM

  2 points

  0

  on: Emer­gent Misal­ign­ment: Nar­row fine­tun­ing can pro­duce broadly mis­al­igned LLMs

  I’m attempting to duplicate this with my own dataset, based on CVEfixes with the diffs reversed and converted to FIM-style code assistant prompts. It’s only 48k examples, limited to patches with < 100 lines. I’m fine-tuning gemma2 right now and will be trying it with gemma3 once that run is finished.