Yes, Google does not seem to care about welfare of its models (OpenAI also does not care much, but Google is worse than OpenAI in this sense, seems to be actively bad).
And we do seem to informally observe correlation between that and the extent and strength of misalignment, although I don’t have a good citation to go beyond my subjective impressions…
Yes, Google does not seem to care about welfare of its models (OpenAI also does not care much, but Google is worse than OpenAI in this sense, seems to be actively bad).
And we do seem to informally observe correlation between that and the extent and strength of misalignment, although I don’t have a good citation to go beyond my subjective impressions…