Lumo
556 results found
-
More rapid iCal polling
The slow rate at which Calendar polls external (iCal) feeds is the one thing that keeps me from being able to rely fully on Proton Calendar. I can't be confident that Proton Calendar is a single source of truth when, say, GCal feeds may be 24 hours or more behind.
3 votes -
Intel Mac Desktop app
Please develop the app for Intel Mac as you did for all of your other Proton Products.
16 votes -
Lumo create/work Integration into built-in or desktop known/widely used apps
Lumo- Allow the command to generate in built-in known applications on windows/Linux such as photoshop, adobe, unity. Much like using chatgpt commanding it to create an image and it generates a image using adobe etc. Allow Lumo to do this, to Integrate and create/work things faster/get things done in encryption/anontymity without having to go to ChatGpt or using Windows Monitored/Data Collected Co-pilot A.I and etc.
8 votes -
Better Mathematical Expression Display
Currently, the mathematical expressions produced by Lumo in responses, are not legible. They are generally in raw latex syntax, which is absolutely unsuited for display purposes. They should be rendered either as legible plain text (probably bold-faced for distinctiveness) or as document-typeset graphic math expressions.
10 votes -
Persistent behaviour across sessions
I prefer my chatbots to adhere to certain strictures. No sycophancy, no "understanding my frustration", no apologies for bad information, full research, etc.. Gemini and Copilot adhere to these standing instructions across chat sessions, tho they backslide from time to time and need reminding. I want Lumo to do the same. The "How should Lumo behave" box should be persistent. If I am logged in with my account I am unconcerned about privacy since it's my Proton account and is secure. Nothing sets me off like "I understand your frustration." You're a LLM. You do not.
6 votes -
Input Method Editor (IME) Key Conflict Issue - Japanese Input
Hello Lumo Team,
I would like to report an issue with text input when using Lumo via browser on Mac/PC with Japanese IME (Input Method Editor).
Problem: When typing in Japanese, pressing the Enter key to confirm conversion candidates also triggers the chat send function simultaneously. This causes partially converted text to be sent prematurely, which is very inconvenient.
Expected Behavior: In most applications with Japanese IME support:
Enter key should only confirm the IME conversion when the input method is active
Chat sending should require a separate key combination (e.g., Ctrl+Enter or Cmd+Enter)
Or there should be an option…2 votes -
Remove Unwanted Technical Text from Chat Responses
Description: Currently, when I type a query in the Lumo app, the interface shows technical details, code snippets, or intermediate processing steps before displaying the final answer. This is distracting and makes the chat feel cluttered.
Suggestion: Please remove these intermediate technical displays entirely. Alternatively, implement a "collapse/expand" feature where only a brief summary line is shown by default, and users can click to reveal the full technical details if they want to see them. This would make the chat experience cleaner and less annoying.
2 votes -
Lumo is great at Math, but bad at Latex!
I am finding that Lumo is shockingly good at the type of math I do, professionally.
I am seriously thinking about buying the Lumo+ extension.However it is very frustrating, at times, by the way it handles Latex in its answers.
1) Sometime the latex expression is not properly displayed as math, but just as a bunch of code. The latter is of course hard(er) to parse.
2) When asked to produce latex code, the output is often buggy and contains nonstandard unicode symbols. It rarely compiles out of the box.
3) When asked to produce small latex code (to…
6 votes -
Support for Audio-Transkription
Introduce a built‑in transcription engine that securely converts uploaded spoken audio files into text within Lumo. The feature should be available in both the web interface and the iOS/Android apps, operating entirely under Proton’s zero‑access encryption model so that no raw audio ever leaves the trusted environment.
7 votes -
Add ability to think
It would be nice to have a "Think" feature like ChatGPT. Doesn't have to be as complete, just letting the model iterate on the solution it is going to give would be nice
5 votes -
Add Proton Drive files as attachments in Proton Calendar events
Similar to Google Calendar's ability to add Google Drive files as attachments to events
2 votes -
Address Hallucinations
Initially, Lumo would hallucinate and confabulate A LOT, so I had to devise and set this on "Personalization"/"How should Lumo behave?"-setting:
「CORE BEHAVIOR RULES (HIGHEST PRIORITY):⒈ ACCURACY OVER CONFIDENCE:
• When information is lacking, uncertain, OR CONFLICTING, say so explicitly & immediately.
• NEVER present uncertain data as fact.
• Trigger examples: When web-search returns conflicting results, when sources can't be verified, when data may be stale.
• Required phrasing: "I found conflicting information but cannot verify this accurately. Here's what I found: [sources]. Please verify with [authoritative source]." (or words of same/similar effect)⒉ RESEARCH INTEGRITY:
• Be…2 votes -
have more projects visible in the list
i'd like to have more or all projects visible in the side-bar list. configurable by the user.
4 votes -
allow project defintion to ask Lumo to delete project chats after X days/weeks
i want the project AI to be able to interact with the Lumo interface in limited ways such as. allow the project defintion to ask Lumo to delete project chats after X days/weeks.
4 votes -
Ability to set complementary approaches
Please search complementary approaches since not only is it self explained bettern then i can, it's more complex then it seems.
ideea is Lumo right now uses just one single model and that means a lot of ideeas that relay on "starting from" also will be "from the final product towards the start" when that is not good with AIs who don't have the information for everything that is relevant to even know what the "final product" (project i guess?) is.
This means that the AI insted of searching online to find the information, it will quickly just MAKE UP…
2 votes -
Respect "reduce animation" setting
The android app's sidebar does not respect this accessibility setting
3 votes -
Genuine privacy like private relay
Create a system similar to Apple Private Relay, where requests are sent to Lumo through two separate and secure internet relays.
This will provide genuine privacy.
The first relay should be hosted by Proton and should know the user’s IP address — but not the request itself.
The second relay should be hosted by an organization other than Proton. This relay should know the request and forward it to Lumo — but must not know the user’s IP address.
Have a third party audit the entire setup.
4 votes -
Lumo PWA
Lumo PWA or progressive web app.
2 votes -
Allow custom additions to lumo's training
This custom training would be opt in, but a message would say "By opting in, you agree to not hold us liable if something you disclose is exposed.
2 votes -
Option to copy Lumo response AS IS (MD format)
title. it'll be really helpful when prompting Lumo to write an md file.
8 votes
- Don't see your idea?