Redwood Research and Constellation
Nate Thomas
Karma: 526
To anyone reading this who wants to work on or discuss FHI-flavored work: Consider applying to Constellation’s programs (the deadline for some of them is today!), which include salaried positions for researchers.
Thanks, Neel! It should be fixed now.
Apply to the Constellation Visiting Researcher Program and Astra Fellowship, in Berkeley this Winter
Causal scrubbing: results on induction heads
Causal scrubbing: results on a paren balance checker
Causal scrubbing: Appendix
Causal Scrubbing: a method for rigorously testing interpretability hypotheses [Redwood Research]
Apply to the Redwood Research Mechanistic Interpretability Experiment (REMIX), a research program in Berkeley
Note that it’s unsurprising that a different model categorizes this correctly because the failure was generated from an attack on the particular model we were working with. The relevant question is “given a model, how easy is it to find a failure by attacking that model using our rewriting tools?”
Zico Kolter said this May in sworn testimony (in the Musk v Altman trial) that the SSC has twice delayed model releases.
(See e.g. here or purchase the full transcript from the court, in which he later says there was “no pushback when the SSC has exercised its authority”.)