Viewing profile — hgaddipa001
hgaddipa001
HN member- Joined
- Sat, May 25, 2024, 1:37 PM UTC
- HN karma
- 46
- Public activity
- 55 items
- HN profile
- View on Hacker News ↗
About hgaddipa001
No profile information was provided.
Recent public activity
- story
-
comment
Comment #47789588
[flagged]
-
comment
Comment #47251375
What results have you seen so far?
-
story
Full secure meeting platform (Granola proof)
I have a friend who made a completely secure meeting platform. It changes the audio signal to audio drivers, so that granola and other "unseen" notetakers don't work. He's just a p…
-
comment
Comment #45133809
Why wouldn't we be indexing at scale?
-
comment
Comment #45133749
Yep we're using Oauth, so it's easy for a user to disconnect.
-
comment
Comment #45133744
Fair enough makes sense to not have trust! We like to believe we're pretty trustworthy, and do our best to make everything secure.
-
comment
Comment #45133739
Thanks! Don't worry have worked with a few friends experienced in prompt injection to help with the platform. But will read these too :)
-
comment
Comment #45132745
We do a lot of processing on our backend to prevent against prompt injection, but there definitely still is some risk. We can do better on as is always the case. Need to read up on…
-
comment
Comment #45132251
Hmm this is a good idea too
-
comment
Comment #45132246
Not sure we haven't ever done volume that size for one person, but in theory should be able too! We use indexing similar to glean (but a bit less elegant without the ACLs) Can talk…
-
comment
Comment #45131690
Unfortunately have an NDA with them so can't disclose (most of our providers are still in stealth)
-
comment
Comment #45131682
Hmm that's fair, we're definitely not the most exciting launch out there compared to others in our batch. I'd like to think the fact we do what we promise is exciting, but without …
-
comment
Comment #45131522
Ohh we don't give it computer use access or anything like that. We inject tokens post tool call, so to protect users from the agent doing anything malicious.
-
comment
Comment #45131366
Why do you think privacy? Security I understand, but if you consent to giving it access would it not be fine for privacy.
-
comment
Comment #45131145
Hmm ig yeah I can be more granular. Yeah we store our user credentials on our side and manage them. Along with refreshing tokens and so forth
-
comment
Comment #45131136
Have you tried out Slashy? What makes you say that
-
comment
Comment #45130971
It's useful for quality. For example we can read and attach pdfs to gmail which not a lot of people can, since we have our own internal storage api.
-
comment
Comment #45130829
What would you like to see? Can tell you :)
-
comment
Comment #45130825
Runs on AWS for now!
-
comment
Comment #45130819
Oh I used Screen Studio :) Thanks for the compliment. Not worried about browser agents, as we actually have pretty deep integrations (we include semantic search as well as user act…
-
comment
Comment #45130631
We did a lot of internal testing but no official benchmark. We find that the less the agent knows, the more it hallucinates
-
comment
Comment #45130617
Yep! That's our goal long term to get better templates
-
comment
Comment #45130608
Smart
-
comment
Comment #45130605
ooh good idea!