2025 Q1 Pivotal Research Fellowship (Technical & Policy) 2024-11-12T10:56:24.858Z

Apply to the Pivotal Research Fellowship (AI Safety & Biosecurity) 2024-04-10T12:08:30.849Z

Understanding mesa-optimization using toy models 2023-05-07T17:00:52.620Z

How harmful are improvements in AI? + Poll 2022-02-15T18:16:07.854Z

Comment by tilmanr (tilman-ra) on How harmful are improvements in AI? + Poll · 2022-02-21T11:58:05.216Z · LW · GW

Thank you for giving more context to EleutherAI's stance on acceleration and linking to your newest paper.

I support the claim that your open model contributes to AI safety research, and I generally agree with the improvements for the alignment landscape. I can also understand why you are not detailing possible failure modes of realising LLM, as this would basically be stating a bunch of infohazards. 
But at least for me, this opens the space for discussing until which point to open up previously closed models for the sake of alignment research. If an aligned researcher can benefit from access, so could a non-aligned researcher, hence the " accidental acceleration."