US 12,406,207 B2
Systems and methods for generating customized AI models
Nicholas Turley, San Francisco, CA (US); Thomas Dimson, San Francisco, CA (US); Olivier Godement, San Francisco, CA (US); and Michal Pokrass, San Francisco, CA (US)
Assigned to OpenAI OpCo, LLC, San Francisco, CA (US)
Filed by OpenAI OpCo, LLC, San Francisco, CA (US)
Filed on Nov. 12, 2024, as Appl. No. 18/944,178.
Application 18/944,178 is a continuation of application No. 18/896,263, filed on Sep. 25, 2024.
Claims priority of provisional application 63/558,534, filed on Feb. 27, 2024.
Claims priority of provisional application 63/596,365, filed on Nov. 6, 2023.
Claims priority of provisional application 63/585,108, filed on Sep. 25, 2023.
Prior Publication US 2025/0103962 A1, Mar. 27, 2025
Int. Cl. G06N 20/00 (2019.01); G06F 16/334 (2025.01); G06N 5/02 (2023.01); G06N 5/022 (2023.01)
CPC G06N 20/00 (2019.01) [G06F 16/3344 (2019.01); G06N 5/02 (2013.01); G06N 5/022 (2013.01)] 19 Claims
OG exemplary drawing
 
1. An artificial intelligence system comprising:
at least one memory storing instructions; and
at least one processor configured to execute the instructions to perform operations comprising:
receiving a query to configure a custom model, the query comprising features, the features comprising a knowledge base and a capability;
providing the features to a model builder, the model builder being a language model configured with a specific instruction sequence for the formation of custom models, the specific instruction sequence comprising instructions for the language model to behave as an expert at creating custom models;
configuring the custom model with the model builder based on the features by finetuning a base model with the knowledge base and generating a set of instructions to configure the capability;
generating a custom interface for interacting with the custom model;
receiving a prompt via the custom interface; and
generating a response using the custom model,
wherein the specific instruction sequence comprises:
a first step of establishing a behavior for the custom model based on the features;
a second step of generating a profile for the custom model;
a third step of generating refining prompts for the configuring of the custom model, the refining prompts seeking parameters for at least one of: an extraction of data from the knowledge base, a template, an expected output, or an interface configuration; and
an instruction to go through steps in order and without skipping.