Data Security Credentials
It would be a great idea to provide Official QVAC documentation that outlines all the security credentials that this product provides. I understand that, implicitly, the product is designed for privacy and security, but having an official document outlining all the security certificates that this product complies with would help for faster adoption by companies that require this type of documentation for Audit purposes.
Zlatko Zahirovic 2 months ago
Data Security Credentials
It would be a great idea to provide Official QVAC documentation that outlines all the security credentials that this product provides. I understand that, implicitly, the product is designed for privacy and security, but having an official document outlining all the security certificates that this product complies with would help for faster adoption by companies that require this type of documentation for Audit purposes.
Zlatko Zahirovic 2 months ago
Persistent memory and context
Without some persistent memory and context , unfortunately the dependence on other models remains very high. I am a data engineer and I can’t carry on a data project if I have to explain what we’re doing every time I ask a question. And I can’t get help with social-media writing either. Also the fact that always says “Hello” is a little bit annoying :) I think it would be great if Qvac’s strength were that it remembers my information, while keeping it private.
Tundra Parisi 2 months ago
Persistent memory and context
Without some persistent memory and context , unfortunately the dependence on other models remains very high. I am a data engineer and I can’t carry on a data project if I have to explain what we’re doing every time I ask a question. And I can’t get help with social-media writing either. Also the fact that always says “Hello” is a little bit annoying :) I think it would be great if Qvac’s strength were that it remembers my information, while keeping it private.
Tundra Parisi 2 months ago
Registry Files Not Cleaned Up on Uninstall - PC
It’s very interesting. Anyway, was messing around with the Delegated Inference to phone on PC and it mashed everything up. Had to Uninstall and Reinstall - but the lack of a clean uninstall is created file conflicts with the old registry entries, which probably should not be there anyway.
John Lillywhite 3 months ago
Registry Files Not Cleaned Up on Uninstall - PC
It’s very interesting. Anyway, was messing around with the Delegated Inference to phone on PC and it mashed everything up. Had to Uninstall and Reinstall - but the lack of a clean uninstall is created file conflicts with the old registry entries, which probably should not be there anyway.
John Lillywhite 3 months ago
Online learning llm
The flow llm generate text user does some updates or corrections corrected text is used as finetuning data Next time similar prompt appears, LLM uses learned patterns and user needs to make less corrections over time
Olya Sirkin 3 months ago
Online learning llm
The flow llm generate text user does some updates or corrections corrected text is used as finetuning data Next time similar prompt appears, LLM uses learned patterns and user needs to make less corrections over time
Olya Sirkin 3 months ago
Federated Learning for Image Generation
Derivated from https://qvacbytether.featurebase.app/p/local-image-generation Federated learning can definitely enhance the quality of diffusion models while offering a privacy-preserving alternative to centralized solutions. Unlike these solutions, where user data (prompts, generated images or seed uploads) is sent to servers for processing (and potentially retained), FL enables collaborative model training across decentralised devices without sharing raw data. It remains to be solved how good this can get, how scalable it is and what nodes have more incentive in handling this effort for the benefit of all. Universities could be an example.
QVAC | Product Team 3 months ago
Harnessing feedback
Federated Learning for Image Generation
Derivated from https://qvacbytether.featurebase.app/p/local-image-generation Federated learning can definitely enhance the quality of diffusion models while offering a privacy-preserving alternative to centralized solutions. Unlike these solutions, where user data (prompts, generated images or seed uploads) is sent to servers for processing (and potentially retained), FL enables collaborative model training across decentralised devices without sharing raw data. It remains to be solved how good this can get, how scalable it is and what nodes have more incentive in handling this effort for the benefit of all. Universities could be an example.
QVAC | Product Team 3 months ago
Harnessing feedback
Local Image Generation
Introducing a way for people to create images locally, easily and cross-platform seems really useful for any number of applications. Cloud services expose us to risks that something like this can eliminate: exposure: there are default public galleries and no opt-out for training on some providers, which means the images are shared and used to improve models. server retention: aside from caching upload (even sensitive ones) aside from promises that data is stored in segregated locations, “deleted” content is not clear and while its claimed to not be used for training, data retention policies change all the time. Without verification, the current policies basically equate to indefinite storage. costs: generating locally is not free (has some costs) but for scale (like design schools, etc.) it’s certainly cheaper Federated learning can complement this to ensure that the models keep improving for all - based on everyone’s information - but without all the implications above.
Hugo 3 months ago
Harnessing feedback
Local Image Generation
Introducing a way for people to create images locally, easily and cross-platform seems really useful for any number of applications. Cloud services expose us to risks that something like this can eliminate: exposure: there are default public galleries and no opt-out for training on some providers, which means the images are shared and used to improve models. server retention: aside from caching upload (even sensitive ones) aside from promises that data is stored in segregated locations, “deleted” content is not clear and while its claimed to not be used for training, data retention policies change all the time. Without verification, the current policies basically equate to indefinite storage. costs: generating locally is not free (has some costs) but for scale (like design schools, etc.) it’s certainly cheaper Federated learning can complement this to ensure that the models keep improving for all - based on everyone’s information - but without all the implications above.
Hugo 3 months ago
Harnessing feedback