公开(公告)号：US20230316006A1

公开(公告)日：2023-10-05

申请号：US18301639

申请日：2023-04-17

Applicant: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITED

Inventor： William TUNSTALL-PEDOE ,  Robert HEYWOOD ,  Seth WARREN ,  Paul DARIAS ,  Duncan REYNOLDS ,  Ayush SHAH ,  Luci KRNIC ,  Ziyi ZHU

IPC: G06F40/56 ,  G06F40/205 ,  G06F40/30

CPC classification number: G06F40/56 ,  G06F40/205 ,  G06F40/30

Abstract: Methods are provided, such as a method of interacting with a large language model (LLM), including the step of a processing system using a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, to provide new context data for the LLM, in order to improve the output, such as continuation text output, generated by the LLM in response to a prompt; and such as a method of interacting with a LLM, including the step of providing continuation data generated by the LLM to a processing system that uses a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, in which the processing system is configured to analyse the continuation output generated by the LLM in response to a prompt to enable an improved version of that continuation output to be provided to a user. Related computer systems are provided.

公开(公告)号：US20230259705A1

公开(公告)日：2023-08-17

申请号：US18301594

申请日：2023-04-17

Applicant: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITED

Inventor： William TUNSTALL-PEDOE ,  Robert HEYWOOD ,  Seth WARREN ,  Paul DARIAS ,  Duncan REYNOLDS ,  Ayush SHAH ,  Luci KRNIC ,  Ziyi ZHU

IPC: G06F40/279

CPC classification number: G06F40/279

Abstract: Methods are provided, such as a method of interacting with a large language model (LLM), including the step of a processing system using a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, to provide new context data for the LLM, in order to improve the output, such as continuation text output, generated by the LLM in response to a prompt; and such as a method of interacting with a LLM, including the step of providing continuation data generated by the LLM to a processing system that uses a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, in which the processing system is configured to analyse the continuation output generated by the LLM in response to a prompt to enable an improved version of that continuation output to be provided to a user. Related computer systems are provided.

公开(公告)号：US20230274086A1

公开(公告)日：2023-08-31

申请号：US18301615

申请日：2023-04-17

Applicant: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITED

Inventor： William TUNSTALL-PEDOE ,  Robert HEYWOOD ,  Seth WARREN ,  Paul DARIAS ,  Duncan REYNOLDS ,  Ayush SHAH ,  Luci KRNIC ,  Ziyi ZHU

IPC: G06F40/20 ,  G06F16/33

CPC classification number: G06F40/20 ,  G06F16/3344

Abstract: Methods are provided, such as a method of interacting with a large language model (LLM), including the step of a processing system using a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, to provide new context data for the LLM, in order to improve the output, such as continuation text output, generated by the LLM in response to a prompt; and such as a method of interacting with a LLM, including the step of providing continuation data generated by the LLM to a processing system that uses a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, in which the processing system is configured to analyse the continuation output generated by the LLM in response to a prompt to enable an improved version of that continuation output to be provided to a user. Related computer systems are provided.

公开(公告)号：US20230274094A1

公开(公告)日：2023-08-31

申请号：US18301560

申请日：2023-04-17

Applicant: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITED

Inventor： William TUNSTALL-PEDOE ,  Robert HEYWOOD ,  Seth WARREN ,  Paul DARIAS ,  Duncan REYNOLDS ,  Ayush SHAH ,  Luci KRNIC ,  Ziyi ZHU

IPC: G06F40/40 ,  G06F40/30

CPC classification number: G06F40/40 ,  G06F40/30

Abstract: Methods are provided, such as a method of interacting with a large language model (LLM), including the step of a processing system using a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, to provide new context data for the LLM, in order to improve the output, such as continuation text output, generated by the LLM in response to a prompt; and such as a method of interacting with a LLM, including the step of providing continuation data generated by the LLM to a processing system that uses a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, in which the processing system is configured to analyse the continuation output generated by the LLM in response to a prompt to enable an improved version of that continuation output to be provided to a user. Related computer systems are provided.

公开(公告)号：US20230274089A1

公开(公告)日：2023-08-31

申请号：US18301573

申请日：2023-04-17

Applicant: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITED

Inventor： William TUNSTALL-PEDOE ,  Robert HEYWOOD ,  Seth WARREN ,  Paul DARIAS ,  Duncan REYNOLDS ,  Ayush SHAH ,  Luci KRNIC ,  Ziyi ZHU

IPC: G06F40/279 ,  G06F40/40

CPC classification number: G06F40/279 ,  G06F40/40

Abstract: Methods are provided, such as a method of interacting with a large language model (LLM), including the step of a processing system using a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, to provide new context data for the LLM, in order to improve the output, such as continuation text output, generated by the LLM in response to a prompt; and such as a method of interacting with a LLM, including the step of providing continuation data generated by the LLM to a processing system that uses a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, in which the processing system is configured to analyse the continuation output generated by the LLM in response to a prompt to enable an improved version of that continuation output to be provided to a user. Related computer systems are provided.