Jack Merullo
Research Scientist, Goodfire. On 1 show, 1 appearance. The Shows tab opens the full record on each.
scientistacademicjmerullo.github.io ↗
Jack Merullo is a research scientist at Goodfire focusing on mechanistic interpretability and model representations. He earned his Ph.D. in Computer Science from Brown University, where he studied representation learning in deep neural networks.
1shows
1appearances
2statements
0resolved
0supported
0contradicted
Everything Jack Merullo said on any show that made the record, most notable first. Each card names its show and opens the statement there.
Merullo: Current machine unlearning techniques merely suppress data rather than removing it
“I would describe it more as not unlearning, but maybe suppression. I think there's, like, really, like, I guess, guarantees that you've fully removed information from a model is, is, I don't think it's been convincingly showed anywhere yet”
Merullo: LLM memorization spans a gradient from reasoning to rote recall
“You can actually see, like the way that we, like, disentangle memorization, you can kind of see this like, gradient of memorization in between both mechanistically and behaviorally with, like, logical reasoning tasks being quite distinct from rote memorization…”
One line per show, most statements first. The link opens Jack's full record on that show: the calibration, argument clarity, speaking style and every statement made there.
| Show | Role there | Eps | Statements | Record | |
|---|---|---|---|---|---|
 LATENT SPACELEDGER | Research Scientist, Goodfire | 1 | 2 | — | full record on Latent Space → |