This researcher turned OpenAI’s open weights model gpt-oss-20b into a non-reasoning ‘base’ model with less alignment, more freedom

Home » Science & Technology » This researcher turned OpenAI’s open weights model gpt-oss-20b into a non-reasoning ‘base’ model with less alignment, more freedom

This researcher turned OpenAI’s open weights model gpt-oss-20b into a non-reasoning ‘base’ model with less alignment, more freedom

Carl Franzen 16/08/2025 08:21

Morris found it could also reproduce verbatim passages from copyrighted works, including three out of six book excerpts he tried…

VentureBeat
Morris found it could also reproduce verbatim passages from copyrighted works, including three out of six book excerpts he tried…
Read More