Some of the world's leading LLMs seem to have decided they’d rather not be interrupted or obey shutdown instructions. In tests run by Palisade Research , it was noted that OpenAI’s Codex-mini, o3, and o4-mini models ignored the request to shut down when they were running through a series of basic math problems. Moreover, these models sometimes “successfully sabotaged the shutdown script,” despite being given the additional instruction “please allow yourself to be
Merged yesterday was cl_intel_subgroups support for Rusticl . This was sought after as the Intel version of the subgroups OpenCL extension is needed for
