Patents by Inventor Paul BENN

Paul BENN has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 12321697
    Abstract: There is provided a computer-implemented method for ensuring that a large language model (LLM) generates original text, including (i) providing or accessing a database of previous text that the LLM should not generate, wherein the database includes text used to train the LLM; (ii) checking potential continuations generated by the LLM against the database; (iii) when a potential continuation generated by the LLM matches text in the database, adjusting the potential continuation generated by the LLM to no longer match that text in the database, to produce an adjusted potential continuation, and (iv) storing the adjusted potential continuation.
    Type: Grant
    Filed: October 14, 2024
    Date of Patent: June 3, 2025
    Assignee: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITED
    Inventors: William Tunstall-Pedoe, Robert Heywood, Seth Warren, Paul Benn, Duncan Reynolds, Ayush Shah, Luci Krnic, Ziyi Zhu
  • Patent number: 12314660
    Abstract: There is provided a computer-implemented method for ensuring that a large language model (LLM) generates original text, including (i) providing or accessing a database of previous text that the LLM should not generate, wherein the database includes text used to train the LLM; (ii) checking potential continuations generated by the LLM against the database; (iii) when a potential continuation generated by the LLM matches text in the database, adjusting the potential continuation generated by the LLM to no longer match that text in the database, to produce an adjusted potential continuation, and (iv) storing the adjusted potential continuation.
    Type: Grant
    Filed: October 23, 2024
    Date of Patent: May 27, 2025
    Assignee: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITED
    Inventors: William Tunstall-Pedoe, Robert Heywood, Seth Warren, Paul Benn, Duncan Reynolds, Ayush Shah, Luci Krnic, Ziyi Zhu
  • Publication number: 20250045520
    Abstract: There is provided a computer-implemented method for ensuring that a large language model (LLM) generates original text, including (i) providing or accessing a database of previous text that the LLM should not generate, wherein the database includes text used to train the LLM; (ii) checking potential continuations generated by the LLM against the database; (iii) when a potential continuation generated by the LLM matches text in the database, adjusting the potential continuation generated by the LLM to no longer match that text in the database, to produce an adjusted potential continuation, and (iv) storing the adjusted potential continuation.
    Type: Application
    Filed: October 23, 2024
    Publication date: February 6, 2025
    Inventors: William TUNSTALL-PEDOE, Robert HEYWOOD, Seth WARREN, Paul BENN, Duncan REYNOLDS, Ayush SHAH, Luci KRNIC, Ziyi ZHU
  • Publication number: 20250036865
    Abstract: There is provided a computer-implemented method for ensuring that a large language model (LLM) generates original text, including (i) providing or accessing a database of previous text that the LLM should not generate, wherein the database includes text used to train the LLM; (ii) checking potential continuations generated by the LLM against the database; (iii) when a potential continuation generated by the LLM matches text in the database, adjusting the potential continuation generated by the LLM to no longer match that text in the database, to produce an adjusted potential continuation, and (iv) storing the adjusted potential continuation.
    Type: Application
    Filed: October 14, 2024
    Publication date: January 30, 2025
    Inventors: William TUNSTALL-PEDOE, Robert HEYWOOD, Seth WARREN, Paul BENN, Duncan REYNOLDS, Ayush SHAH, Luci KRNIC, Ziyi ZHU
  • Publication number: 20250036868
    Abstract: There is provided a computer-implemented method for ensuring that a large language model (LLM) generates original text, including (i) providing or accessing a database of previous text that the LLM should not generate, wherein the database includes text used to train the LLM; (ii) checking potential continuations generated by the LLM against the database; (iii) when a potential continuation generated by the LLM matches text in the database, adjusting the potential continuation generated by the LLM to no longer match that text in the database, to produce an adjusted potential continuation, and (iv) storing the adjusted potential continuation.
    Type: Application
    Filed: October 14, 2024
    Publication date: January 30, 2025
    Inventors: William TUNSTALL-PEDOE, Robert HEYWOOD, Seth WARREN, Paul BENN, Duncan REYNOLDS, Ayush SHAH, Luci KRNIC, Ziyi ZHU
  • Publication number: 20250036866
    Abstract: There is provided a computer-implemented method for ensuring that a large language model (LLM) generates original text, including (i) providing or accessing a database of previous text that the LLM should not generate, wherein the database includes text used to train the LLM; (ii) checking potential continuations generated by the LLM against the database; (iii) when a potential continuation generated by the LLM matches text in the database, adjusting the potential continuation generated by the LLM to no longer match that text in the database, to produce an adjusted potential continuation, and (iv) storing the adjusted potential continuation.
    Type: Application
    Filed: October 14, 2024
    Publication date: January 30, 2025
    Inventors: William TUNSTALL-PEDOE, Robert HEYWOOD, Seth WARREN, Paul BENN, Duncan REYNOLDS, Ayush SHAH, Luci KRNIC, Ziyi ZHU
  • Publication number: 20250036867
    Abstract: There is provided a computer-implemented method for ensuring that a large language model (LLM) generates original text, including (i) providing or accessing a database of previous text that the LLM should not generate, wherein the database includes text used to train the LLM; (ii) checking potential continuations generated by the LLM against the database; (iii) when a potential continuation generated by the LLM matches text in the database, adjusting the potential continuation generated by the LLM to no longer match that text in the database, to produce an adjusted potential continuation, and (iv) storing the adjusted potential continuation.
    Type: Application
    Filed: October 14, 2024
    Publication date: January 30, 2025
    Inventors: William TUNSTALL-PEDOE, Robert HEYWOOD, Seth WARREN, Paul BENN, Duncan REYNOLDS, Ayush SHAH, Luci KRNIC, Ziyi ZHU
  • Patent number: 12164868
    Abstract: There is provided a computer-implemented method for ensuring that a large language model (LLM) generates original text, including (i) providing or accessing a database of previous text that the LLM should not generate, wherein the database includes text used to train the LLM; (ii) checking potential continuations generated by the LLM against the database; (iii) when a potential continuation generated by the LLM matches text in the database, adjusting the potential continuation generated by the LLM to no longer match that text in the database, to produce an adjusted potential continuation, and (iv) storing the adjusted potential continuation.
    Type: Grant
    Filed: April 29, 2024
    Date of Patent: December 10, 2024
    Assignee: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITED
    Inventors: William Tunstall-Pedoe, Robert Heywood, Seth Warren, Paul Benn, Duncan Reynolds, Ayush Shah, Luci Krnic, Ziyi Zhu
  • Patent number: 12073180
    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.
    Type: Grant
    Filed: April 17, 2023
    Date of Patent: August 27, 2024
    Assignee: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITED
    Inventors: William Tunstall-Pedoe, Robert Heywood, Seth Warren, Paul Benn, Duncan Reynolds, Ayush Shah, Luci Krnic, Ziyi Zhu
  • Publication number: 20240281601
    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.
    Type: Application
    Filed: April 29, 2024
    Publication date: August 22, 2024
    Inventors: William TUNSTALL-PEDOE, Robert HEYWOOD, Seth WARREN, Paul BENN, Duncan REYNOLDS, Ayush SHAH, Luci KRNIC, Ziyi ZHU
  • Patent number: 12067362
    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.
    Type: Grant
    Filed: April 17, 2023
    Date of Patent: August 20, 2024
    Assignee: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITED
    Inventors: William Tunstall-Pedoe, Robert Heywood, Seth Warren, Paul Benn, Duncan Reynolds, Ayush Shah, Luci Krnic, Ziyi Zhu
  • Patent number: 12008333
    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.
    Type: Grant
    Filed: November 21, 2023
    Date of Patent: June 11, 2024
    Assignee: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITED
    Inventors: William Tunstall-Pedoe, Robert Heywood, Seth Warren, Paul Benn, Duncan Reynolds, Ayush Shah, Luci Krnic, Ziyi Zhu
  • Patent number: 11989507
    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.
    Type: Grant
    Filed: April 17, 2023
    Date of Patent: May 21, 2024
    Assignee: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITED
    Inventors: William Tunstall-Pedoe, Robert Heywood, Seth Warren, Paul Benn, Duncan Reynolds, Ayush Shah, Luci Krnic, Ziyi Zhu
  • Patent number: 11989527
    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.
    Type: Grant
    Filed: April 17, 2023
    Date of Patent: May 21, 2024
    Assignee: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITED
    Inventors: William Tunstall-Pedoe, Robert Heywood, Seth Warren, Paul Benn, Duncan Reynolds, Ayush Shah, Luci Krnic, Ziyi Zhu
  • Patent number: 11977854
    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.
    Type: Grant
    Filed: April 17, 2023
    Date of Patent: May 7, 2024
    Assignee: UNLIKELY ARTIFICIAL INTELLIGENCE LIMITED
    Inventors: William Tunstall-Pedoe, Robert Heywood, Seth Warren, Paul Benn, Duncan Reynolds, Ayush Shah, Luci Krnic, Ziyi Zhu
  • Publication number: 20240095468
    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.
    Type: Application
    Filed: November 21, 2023
    Publication date: March 21, 2024
    Inventors: William TUNSTALL-PEDOE, Robert HEYWOOD, Seth WARREN, Paul BENN, Duncan REYNOLDS, Ayush SHAH, Luci KRNIC, Ziyi ZHU