COMPUTER-IMPLEMENTED MULTI-USER MESSAGING APPLICATION
A computing system includes a processor; and memory storing instructions that, when executed by the processor, cause the processor to perform several acts. The acts include receiving multiple messages from multiple users in a messaging application that supports group conversations, where the multiple messages are included in a group conversation. The acts also include providing a prompt to a generative model, where the prompt includes the multiple messages. The acts additionally include receiving, from the generative model, an output generated by the generative model based upon the prompt and including the output as a turn in the group conversation.
1 . A computing system comprising:
a processor; and
memory storing instructions that, when executed by the processor, cause the processor to perform acts comprising:
receiving at least one message from a computer-implemented messaging application, wherein the at least one message is part of a group conversation between at least a first client computing device operated by a first user and a second client computing device operated by a second user;
generating a prompt based upon the at least one message, wherein the prompt comprises at least one instruction to restrict output generated based upon the prompt;
providing the prompt to a generative model;
receiving, from the generative model, an output generated by the generative model based upon the prompt; and
including the output as a turn in the group conversation.
2 . The computing system of claim 1 , wherein the at least one instruction comprises one or more instructions to facilitate reduction in hallucinations, the one or more instructions comprising at least one of an instruction to not extrapolate, an instruction to not provide personal information about participants of the group conversation, or an instruction to not make inferences about participants of the group conversation.
3 . The computing system of claim 1 , wherein the generative model is a large language model.
4 . The computing system of claim 1 , wherein the prompt further comprises an identifier for the first user or the second user.
5 . The computing system of claim 1 , wherein the output comprises an identifier indicative that the generative model generated the output.
6 . The computing system of claim 1 , wherein the at least one message comprises multiple messages from the group conversation.
7 . The computing system of claim 1 , wherein the at least one message comprises at least one message set forth by the first user and at least one message set forth by the second user.
8 . The computing system of claim 1 , further comprising:
subsequent to including the output as a turn in the group conversation, receiving a message responsive to the output from at least the first user or the second user;
generating a second prompt based upon the message responsive to the output, wherein the prompt comprises the at least one instruction to restrict output generated based upon the prompt;
providing the second prompt to the generative model;
receiving, from the generative model, a second output generated by the generative model based upon the second prompt; and
including the second output as a turn in the group conversation.
9 . The computing system of claim 1 , wherein the at least one message comprises an image.
10 . The computing system of claim 9 , wherein the output comprises an image generated by the generative model.
11 . The computing system of claim 1 , wherein the at least one message comprises a request to invoke a chatbot in the group conversation.
12 . The computing system of claim 1 , wherein the prompt includes one or more historical messages of the group conversation.
13 . A method executed by the processor of a computing system, the method comprising:
receiving at least one message from a computer-implemented messaging application, wherein the at least one message is part of a group conversation between at least a first client computing device operated by a first user and a second client computing device operated by a second user;
generating a prompt based upon the at least one message, wherein the prompt comprises at least one instruction to restrict output generated based upon the prompt;
providing the prompt to a generative model;
receiving, from the generative model, an output generated by the generative mode based upon the prompt; and
including the output as a turn in the group conversation.
14 . The method of claim 13 , wherein the at least one instruction comprises one or more instructions to facilitate reduction in hallucinations, the one or more instructions comprising at least one of an instruction to not extrapolate, an instruction to not provide personal information about participants of the group conversation, and an instruction to not make inferences about participants of the group conversation.
15 . The method of claim 13 , wherein the generative model is a large language model.
16 . The method of claim 13 , wherein the output comprises an identifier indicative that the generative model generated the output.
17 . The method of claim 13 , wherein the at least one message comprises at least one message set forth by the first user and at least one message set forth by the second user.
18 . The method of claim 13 , further comprising:
subsequent to including the output as a turn in the group conversation, receiving a message responsive to the output from at least the first user or the second user;
generating a second prompt based upon the message responsive to the output, wherein the prompt comprises the at least one instruction to restrict output generated based upon the prompt;
providing the second prompt to the generative model;
receiving, from the generative model, a second output generated by the generative mode based upon the second prompt; and
including the second output as a turn in the group conversation.
19 . A computer-readable storage medium comprising instructions that, when executed by a processor, cause the processor to perform acts comprising:
receiving at least one message from a computer-implemented messaging application, wherein the at least one message is part of a group conversation between at least a first client computing device operated by a first user and a second client computing device operated by a second user;
generating a prompt based upon the at least one message, wherein the prompt comprises at least one instruction to restrict output generated based upon the prompt;
providing the prompt to a generative model;
receiving, from the generative model, an output generated by the generative mode based upon the prompt; and
including the output as a turn in the group conversation.
20 . The computer-readable storage medium of claim 19 , wherein the at least one instruction comprises one or more instructions to facilitate reduction in hallucinations, the one or more instructions comprising at least one of an instruction to not extrapolate, an instruction to not provide personal information about participants of the group conversation, and an instruction to not make inferences about participants of the group conversation.