Clement Neo @ ICLR 25 🇸🇬 (@_clementneo) 's Twitter Profile
Clement Neo @ ICLR 25 🇸🇬

@_clementneo

Mechanistic interpretability @ SG AISI also with Apart Research

ID: 1367720335244599302

linkhttp://clementneo.com calendar_today05-03-2021 06:19:15

397 Tweet

374 Takipçi

260 Takip Edilen

Clement Neo @ ICLR 25 🇸🇬 (@_clementneo) 's Twitter Profile Photo
Clement Neo @ ICLR 25 🇸🇬
@_clementneo

7 months ago

This reminds me of the phenomenon I think I saw (but can’t find/verify) where Claude was somewhat aware that its response got pre-filled and had a similar disbelief to the earlier part of its response. Does anyone know what I’m referring to?