ACE as an IT admin?

[daveshap]

https://arxiv.org/abs/2309.09298
OWL: A Large Language Model for IT Operations

With the rapid development of IT operations, it has become increasingly crucial to efficiently manage and analyze large volumes of data for practical applications. The techniques of Natural Language Processing (NLP) have shown remarkable capabilities for various tasks, including named entity recognition, machine translation and dialogue systems. Recently, Large Language Models (LLMs) have achieved significant improvements across various NLP downstream tasks. However, there is a lack of specialized LLMs for IT operations. In this paper, we introduce the OWL, a large language model trained on our collected OWL-Instruct dataset with a wide range of IT-related information, where the mixture-of-adapter strategy is proposed to improve the parameter-efficient tuning across different domains or tasks. Furthermore, we evaluate the performance of our OWL on the OWL-Bench established by us and open IT-related benchmarks. OWL demonstrates superior performance results on IT tasks, which outperforms existing models by significant margins. Moreover, we hope that the findings of our work will provide more insights to revolutionize the techniques of IT operations with specialized LLMs.

[SecondWaveStrategy]

How would a non coder go about getting this developed?

I have read all the documentation and watched many of your videos, studied all the relevant material etc, but I do not have the capability to build this for myself

[ash-k-nz]

This might sound a little crazy, but if u have open interpreter, or just accces to normal code interpreter u can model these things inside chat gpt itself, it will also as a by product write the code for the functions for u, and potetntially in the future if computation is increased can run it inside of itself, i think thats godels or turings observation.

…

On Wed, 18 Oct 2023, 3:25 pm SecondWaveAU, ***@***.***> wrote: How would a non coder go about getting this developed? I have read all the documentation and watched many of your videos, studied all the relevant material etc, but I do not have the capability to build this for myself — Reply to this email directly, view it on GitHub <#27 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/BBBVTZZMPU4GBZFKTNGZENLX744XXAVCNFSM6AAAAAA5DKUM7SVHI2DSMVQWIX3LMV43SRDJONRXK43TNFXW4Q3PNVWWK3TUHM3TGMBZHA4DG> . You are receiving this because you are subscribed to this thread.Message ID: ***@***.*** com>

[ash-k-nz]

here is a basic model to help you understand it - out this in the system prompt -* you are a "brain" you decide based on the users input weather to store the input in hot memory or cold memory, and when to access that memory again for in context insertions of previous data into current input remember to time and date stamp all information for ease of access.* then if you are game, get it to create an in memory vector database, with the segments of cold memory, and a scratch pad to record hot memory, and ask it to update it at every turn and when you are finished you can ask it to give you the saved files. this is very basic, but it will help you understand that this is happening asynchronously in the ACE framework so you can begin to understand the architecture of the ace framework and how you can implement this in multiple layers. hope that helps!

…

On Wed, Oct 18, 2023 at 6:37 PM Ashley Kelly ***@***.***> wrote: This might sound a little crazy, but if u have open interpreter, or just accces to normal code interpreter u can model these things inside chat gpt itself, it will also as a by product write the code for the functions for u, and potetntially in the future if computation is increased can run it inside of itself, i think thats godels or turings observation. On Wed, 18 Oct 2023, 3:25 pm SecondWaveAU, ***@***.***> wrote: > How would a non coder go about getting this developed? > > I have read all the documentation and watched many of your videos, > studied all the relevant material etc, but I do not have the capability to > build this for myself > > — > Reply to this email directly, view it on GitHub > <#27 (comment)>, > or unsubscribe > <https://github.com/notifications/unsubscribe-auth/BBBVTZZMPU4GBZFKTNGZENLX744XXAVCNFSM6AAAAAA5DKUM7SVHI2DSMVQWIX3LMV43SRDJONRXK43TNFXW4Q3PNVWWK3TUHM3TGMBZHA4DG> > . > You are receiving this because you are subscribed to this thread.Message > ID: ***@***.*** > com> >

[ash-k-nz]

forgot to mention you watn it to read and write every turn, so it can check its memory during the convo

…

On Wed, Oct 18, 2023 at 9:01 PM Ashley Kelly ***@***.***> wrote: here is a basic model to help you understand it - out this in the system prompt -* you are a "brain" you decide based on the users input weather to store the input in hot memory or cold memory, and when to access that memory again for in context insertions of previous data into current input remember to time and date stamp all information for ease of access.* then if you are game, get it to create an in memory vector database, with the segments of cold memory, and a scratch pad to record hot memory, and ask it to update it at every turn and when you are finished you can ask it to give you the saved files. this is very basic, but it will help you understand that this is happening asynchronously in the ACE framework so you can begin to understand the architecture of the ace framework and how you can implement this in multiple layers. hope that helps! On Wed, Oct 18, 2023 at 6:37 PM Ashley Kelly ***@***.***> wrote: > This might sound a little crazy, but if u have open interpreter, or just > accces to normal code interpreter u can model these things inside chat gpt > itself, it will also as a by product write the code for the functions for > u, and potetntially in the future if computation is increased can run it > inside of itself, i think thats godels or turings observation. > > On Wed, 18 Oct 2023, 3:25 pm SecondWaveAU, ***@***.***> > wrote: > >> How would a non coder go about getting this developed? >> >> I have read all the documentation and watched many of your videos, >> studied all the relevant material etc, but I do not have the capability to >> build this for myself >> >> — >> Reply to this email directly, view it on GitHub >> <#27 (comment)>, >> or unsubscribe >> <https://github.com/notifications/unsubscribe-auth/BBBVTZZMPU4GBZFKTNGZENLX744XXAVCNFSM6AAAAAA5DKUM7SVHI2DSMVQWIX3LMV43SRDJONRXK43TNFXW4Q3PNVWWK3TUHM3TGMBZHA4DG> >> . >> You are receiving this because you are subscribed to this thread.Message >> ID: ***@***.*** >> com> >> >