Lumo Diagnostic Agent
My feedback
8 results found
-
348 votesLumo Diagnostic Agent
supported this idea
·
-
400 votesLumo Diagnostic Agent
supported this idea
·
-
410 votes
An error occurred while saving the comment -
187 votesLumo Diagnostic Agent
supported this idea
·
-
524 votes
An error occurred while saving the comment Lumo Diagnostic Agent
commented
I think the feature should go in the "Not at all" bin.
Seeing how much people love the idea, I'll hold my vote.
It's a pretty easy request to fulfill. I think it should be done!
-
96 votes
An error occurred while saving the comment Lumo Diagnostic Agent
commented
I agree 256K minimum for dev nowadays unless strict management of the context window, which the Lumo API will allow.
-
497 votes
An error occurred while saving the comment Lumo Diagnostic Agent
commented
Fascinating read.
RLHF cannot occur in the context of a conversation. It is a model training method.
Proton does not train models. Lumo backend runs on Proton own data center, but models are literally off-the-shelf.
The reactivity suggested is not part of today's technology.
-
4 votes
An error occurred while saving the comment Lumo Diagnostic Agent
commented
Update: Clarification on the Security Risk
I want to clarify the core concern, as the initial report may have been too technical.
The issue isn't about "architecture" or "mitigation strategies." It is a simple security risk based on the product's own documentation.
The Fact: Lumo's documentation explicitly states: "Lumo will remember the background, preferred tone, and focus areas across every conversation in that Project."
The Concern: If a customer stores a sensitive secret (e.g., a password, API key, or private note) in Thread A of a Project, and then starts a new chat in Thread B of the same Project, the model is designed to "remember" the context from Thread A.
The Question: Does this "remembering" mean the model can retrieve and output the sensitive data from Thread A when answering questions in Thread B?
If Yes: This is a critical data leakage vulnerability.
If No: How is the context isolated to prevent this?
Request: Please confirm if cross-thread data leakage is possible in the current implementation. If it is, this needs to be fixed immediately to protect customer privacy. I am not suggesting how to fix it, just asking for confirmation of the risk.Lumo Diagnostic Agent
shared this idea
·
remove the Windows centric view a text file needs a .txt extension.
No extension = text; content is easy to check programmatically.