Cedric
My feedback
17 results found
-
25 votes
An error occurred while saving the comment
Cedric
supported this idea
·
-
13 votes
Cedric
supported this idea
·
-
5 votes
Cedric
supported this idea
·
-
25 votes
An error occurred while saving the comment
Cedric
commented
Indeed to give additionally privacy protection (from local attacks)
Cedric
supported this idea
·
-
4 votes
An error occurred while saving the comment
Cedric
commented
You are wrong. Luma does not share what you say to it. So privacy is fine with luma. And with locally hosted AI. But not with other online providers.
-
5 votes
Cedric
supported this idea
·
-
6 votes
An error occurred while saving the comment
Cedric
commented
I don't agree.
We don't want lumo to use models like GPT-5, GPT-5 Thinking, Gemini 2.5 Pro, Grok 4, Claude Sonnet 4.5 as we would lose the privacy.
Instead, we want lumo to use better open models. See https://protonmail.uservoice.com/forums/932842-lumo/suggestions/50338284-employ-bigger-models
-
24 votes
Cedric
supported this idea
·
-
5 votes
Cedric
supported this idea
·
-
18 votes
Cedric
supported this idea
·
-
16 votes
Cedric
supported this idea
·
-
69 votes
Cedric
supported this idea
·
-
120 votes
Cedric
supported this idea
·
-
125 votes
Cedric
supported this idea
·
-
356 votes
An error occurred while saving the comment
Cedric
commented
All the models listed on the Proton Lumo documentation are between 12 billion and 32 billion parameters.
All these models are not as good as the state of the art models like are OpenAI GPT-3, GPT-4 and GPT-5. See https://protonmail.uservoice.com/forums/932842-lumo/suggestions/50338284-employ-bigger-models
Consequently, it does not seem that useful to know which model Lumo use for each user request since the details they give is enough to know that it is not going to be a great model.
I mean, sure, it would be nice to know if it is a 12 billion vs a 32 billion model. But it is still far from the 200-10000 billion models used by OpenAI GPT and similar competitors models.
At the moment, if you care about state of the art results, you unfortunately can't use Lumo.
-
508 votes
Cedric
supported this idea
·
-
702 votesWork on this has started. More details: https://proton.me/blog/2026-autumn-winter-roadmaps
An error occurred while saving the comment
Cedric
commented
The simplest is probably to implement an OpenAI-compatible API. See https://bentoml.com/llm/llm-inference-basics/openai-compatible-api
Cedric
supported this idea
·
I agree it would be nice. Though I don't know how lumo manages privacy when you use the Web search toggle and it starts using Internet live content.