[et_pb_section fb_built=”1″ _builder_version=”4.23.1″ _module_preset=”default” global_colors_info=”{}”][et_pb_row _builder_version=”4.23.1″ _module_preset=”default” custom_margin=”-1px|auto||auto||” global_colors_info=”{}”][et_pb_column type=”4_4″ _builder_version=”4.23.1″ _module_preset=”default” global_colors_info=”{}”][et_pb_text _builder_version=”4.23.1″ _module_preset=”default” custom_padding=”0px|||||” global_colors_info=”{}”]<\/p>\n
we are well aware of model drift, where the input variables (the real world), over time, become different from the data distribution the model was trained on. It\u2019s not so much the model that drifts here but rather the input data.<\/span> <\/span> [\/et_pb_text][et_pb_image src=”http:\/\/denayer.com\/blog\/wp-content\/uploads\/2023\/12\/1699182573065.jpeg” title_text=”1699182573065″ _builder_version=”4.23.1″ _module_preset=”default” global_colors_info=”{}”][\/et_pb_image][\/et_pb_column][\/et_pb_row][\/et_pb_section]<\/p>\n","protected":false},"excerpt":{"rendered":" we are well aware of model drift, where the input variables (the real world), over time, become different from the data distribution the model was trained on. It\u2019s not so much the model that drifts here but rather the input data. <\/p>\n With LLMs the models themselves also \u2018drift\u2019 in that<\/p>\n","protected":false},"author":1,"featured_media":2052,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_et_pb_use_builder":"on","_et_pb_old_content":"","_et_gb_content_width":"","footnotes":""},"categories":[34],"tags":[],"class_list":["post-2050","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai"],"aioseo_notices":[],"aioseo_head":"\n\t\t\n\t\n\t\n\t\n\t\n\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t
<\/span>
<\/span>With LLMs the models themselves also \u2018drift\u2019 in that<\/span> <\/span>
<\/span>
<\/span>🔄 they are unpredictable (cf the temperature setting) and<\/span>
<\/span>🆕 when a new version of the model is released, as will inevitably happen with<\/span> ChatGPT<\/span><\/span>,<\/span> <\/span><\/a>\u00a0Claude <\/span><\/span>and all the others, we do not know how the model will react.<\/span>
<\/span>
<\/span>so be ready to closely monitor and then revise all of your carefully crafted prompts. Did you put that part in the business case?<\/span><\/p>\n