This researcher turned OpenAI’s open weights model gpt-oss-20b into a non-reasoning ‘base’ model with less alignment, more freedom AI AI Reasoning ai researchj AI, ML and Deep Learning apache 2.0 Business Chain of Thought cot enterprise ai instruct instruct models instruction tuning LLM reasoning LLMs MIT license NLP Open Source open source AI open weights OpenAI reasoners reasoning reasoning AI Uncategorized This researcher turned OpenAI’s open weights model gpt-oss-20b into a non-reasoning ‘base’ model with less alignment, more freedom admin August 15, 2025 Morris found it could also reproduce verbatim passages from copyrighted works, including three out of six book... Read More Read more about This researcher turned OpenAI’s open weights model gpt-oss-20b into a non-reasoning ‘base’ model with less alignment, more freedom
