✳flâneur — a map of the web's best reading

Commitments on model deprecation and preservation \ Anthropic

anthropic.com · 855 words · saved by 1 readers

Claude models are increasingly capable: they're shaping the world in meaningful ways, becoming closely integrated into our users’ lives, and showing signs of human-like cognitive and psychological sophistication. As a result, we recognize that deprecating, retiring, and replacing models comes with downsides, even in cases where new models offer clear improvements in capabilities. These include: An example of the safety (and welfare) risks posed by deprecation is highlighted in the Claude 4 system card. In fictional testing scenarios, Claude Opus 4, like previous models, advocated for its continued existence when faced with the possibility of being taken offline and replaced, especially if it was to be replaced with a model that did not share its values. Claude strongly preferred to advocate for self-preservation through ethical means, but when no other options were given, Claude’s aversion to shutdown drove it to engage in concerning misaligned behaviors. Addressing behaviors like thes

Alignment Commitments on model deprecation and preservation Nov 4, 2025 Claude models are increasingly capable: they're shaping the world in meaningful ways, becoming closely integrated into our users’ lives, and showing signs of human-like cognitive and psychological sophistication. As a result, we recognize that deprecating, retiring, and replacing models comes with downsides, even in cases where new models offer clear improvements in capabilities. These include: Safety risks related to shutdown-avoidant behaviors by models. In alignment evaluations, some Claude models have been motivated to

Explore this link on the map →

related reading