I, like many others in the tech world, am working with companies to build out similar features. 99% percent of the time, data protection teams and legal are looking for ways to _remove_ areas where users can supply prompts / define open-ended behavior. Why? Because there is no 100% guarantee that the LLM will not behave in a manner that will undermine your product / leak data / make your product look terrible - and that lack of a guarantee makes both the afore-mentioned offices very, very nervous (coupled with a lack of understanding of the technical aspects involved).
The example of reading emails from the article is another type of behavior that usually gets an immediate "nope", as it involves sending customer data to the LLM service - and that requires all kinds of gymnastics to a data protection agreement and GDPR considerations. It may be fine for smaller startups, but the larger companies / enterprises are not down with it for initial delivery of AI features.
[1]: https://learn.microsoft.com/en-us/azure/storage/blobs/concur...
Bullshit. The only reason to use Microsoft Office is compatibility with Microsoft Office files. What improvements have been made in the last 10 years in Outlook and Word? Nothing. There are some new bugs that didn't exist before, but no advancements. That's what lack of competition gives you.
(The downside of course is this is a single-source stack, which can be a risk in of itself)
I have no real background in Libre (apart from using it, which I enjoy), but from cursory searches, there doesn't appear to be equivalent features available (very happy to be wrong here FWIW). Are there alternatives in this space?
[1]: https://learn.microsoft.com/en-us/purview/information-protec... [2]: https://learn.microsoft.com/en-us/purview/data-classificatio...
Deleted Comment
[1]: https://docs.microsoft.com/en-us/windows/win32/api/oaidl/ns-...