Feb 2018
Are We There Yet?: The Search for a Theory of Everything
Moataz H. Emam, J. Donoghue, T. Z. Husain et al.
· 0 citations
We have 2 of 2 papers
Not the right person? Other researchers publish under this name.
Post-training alignment is often shallow, eroding under fine-tuning. It remains untested as to whether constitutional midtraining interventions can produce durable alignment when cleanly isolated from post-training. We build a 394M-token constitutional corpus from Anthropic's Constitution and apply constitutional midtr...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.