Lumo
223 results found
-
one click scroll down to most recent messages (mobile and desktop)
Currently you cannot easily scroll to the most recent answer in a conversation, it's particularly difficult on mobile. The app opens a conversation at the top, on the first query posted to Lumo. You can click the down arrow icon which scrolls partially but not to the bottom necessarily. So for very long conversations it often requires a lot of clicking or dragging of the scroll bar to get to the most recent message in conversation.
Even if you enter a new query it doesn't automatically view the most recent answer (there's a separate User Voice idea for that). Instead…
1 vote -
Unlimited Calendar Sync Size
I was hoping to switch to Proton calendar as my "source of truth" across the 2 Google and 2 Office 365 calendars I have to juggle on a daily basis. I am however unable to use it because of the "Calendar Too big" sync limitation.
Even the hack-fix of manually adding "start-min=2025-11-01T00:00:00Z" to the target calendar URL does not work. In fact the form field to paste the URL in is too short in number of characters to accept the full string like this:
This is silly and a little ( a lot actually!) embarrassing.
I am sure Proton…
1 vote -
Lumo prompt-library
Create and save prompt to reuse them with different parameters.
1 vote -
Lumo Branding / Design
Lumo Logo / Branding / Design
Suggesting an overhaul of logo-design and alignment with the Proton Product family.
As a huge Proton fan and customer of many years I frequently wonder about design choices at Proton.
This looks like a very early idea has escaped the lab, made it to market and took off prematurely.Who exactly is the Lumo cat character branding supposed to address?
Kids / pre-puberty adolescents?
Can that really be the primary market for the company's flagship AI product?
Maybe there were some kids involved with the design perhaps?
It would explain the lack of continuity…1 vote -
Feature Suggestion: Built-In Email Productivity Tools for Faster Daily Workflow
Many ProtonMail users handle a high volume of emails every day and often need small productivity tools to speed up their work. A built-in panel offering simple utilities like quick text formatting, a snippet creator, a link checker, and an email content helper could make daily communication much faster and easier.
I’ve created an external toolbox at https://toolinq.com
that provides similar utilities. If ProtonMail adds a simplified version of these features directly inside the inbox, it could make the overall user experience even more efficient.1 vote -
I would like the option to voluntarily share longer chat transcripts for model training when they contain useful corrections or insights. Wh
I would like the option to voluntarily share longer chat transcripts for model training when they contain useful corrections or insights. While the existing thumbs‑down feedback works for isolated messages, many improvements emerge only after a series of exchanges. Please add a simple opt‑in mechanism (e.g., a checkbox or toggle) that lets users grant permission for these extended conversations to be used for training, while keeping the default setting to keep all other data private.
1 vote -
starting over from the beginning is annoying
It's very annoying to have to scroll to pick up where I left off in a long chat. Please revert to the way things were before or add a setting for those who want to start the chat from the beginning.
1 vote -
proton needs to collab with greenpt
proton needs to collab with greenpt.ai to make there AI more sustainable (there AI work now better then lumo)
1 vote -
Hierarchical Multi-Task Constraint Optimization Engine
I am writing to propose a mission-critical feature to address severe hallucination and performance degradation when processing complex, multi-project prompts with nested constraints.
Problem Statement
Our system currently exhibits fundamental breakdowns when handling prompts containing multiple distinct projects with interdependent constraints and domain-specific requirements:
Critical Performance Drop: Benchmarks show accuracy falling below 10% compared to single-task prompts. When processing 32+ nested hierarchical tasks (e.g., "Project Z's Project B's Project D"), performance degrades to GPT-3 equivalence levels.
Constraint Isolation Failure: The system cannot reconcile project-specific constraints with global constraints simultaneously. Complex nesting ("Project A's Project B's Project 9") causes complete context…
1 vote -
Great Potential the ability to use both Scribe & Lumo together, dream come true!
I started with this in Scribe then copy & paste to Lumo Web Search & got the results further from Lumo.
I’m happy to dive into the world of AI‑powered license‑plate readers (LPRs) and give you a clear picture of what’s possible, where the technology shines, and what you should keep in mind before using—or even just exploring—such tools.
How modern AI‑based LPRs work
Image capture – A camera (often a dash cam, security cam, or a handheld device) records video or still frames of vehicles. Many systems use infrared illumination to see plates in low‑light or nighttime conditions.
Pre‑processing…1 vote -
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.
1 vote -
New Zealand Calendar Public Holidays.
Add New Zealand as an option in calendar to add public holidays.
1 vote -
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…
1 vote -
Why High-Performance Brazilian Mobile Proxies Are Essential ?
As the digital world continues to evolve, businesses and professionals who work with Brazil-based online platforms are facing new challenges. Whether you’re a marketer running localized campaigns, an agency managing client accounts, a developer testing geo-restricted apps, or an e-commerce operator monitoring competitors—access to reliable, fast, and authentic Brazilian IP addresses is more important than ever.
This is where Brazilian mobile proxies come into play. And among the many options available, OnlineProxy.io https://onlineproxy.io/country/brazil has emerged as one of the most trusted, secure, and high-performing providers in the market.
1 vote -
Link to Lumo app on a F-Droid, .apk (Github)
Since Google Play is not private, it should not be a big deal for a privacy company (Proton) to publish link to a Lumo Android .apk and a Github repository at https://lumo.proton.me/download and at https://protonapps.com (if that is official source). Also I would welcome F-Droid link.
There is a Github repo at https://github.com/ProtonLumo/android-lumo but the parent user shows no signs of validation as a official Proton AG account, despite Lumo claims there should be some check-mark on the user page.
1 vote -
Option to start Lumo in a floating window
As the Android Lumo app does not support Landscape orientation, not even on large screens, it would be VERY nice to have the possibility to launch Lumo in a floating window on systems that supports it.
On e.g. OnePlus tablets Lumo runs nicely when switching it over to a floating window that can be resized and moved around, BUT there is no way to launch Lumo so it always starts in a floating window.
Please, add the an option in the Lumo Android app making it possible to have it request a floating window upon start.
1 vote -
Theme
I understand that this isn’t a priority right now, but in the long term it would be great to let Lumo have the same themes that are offered in the other Proton products (Mail, Drive..). (Lumo with Ebony would be beautiful 😍)
1 vote -
Let the cat learn to speak!
Add an option where the cat starts reading the answer aloud through the speaker when we enter the message via microphone. This has the small effect of allowing children to grow up with AI in a privacy-compliant manner and give free rein to their imagination, developing stories that the cat can then read aloud. The cat can already write and develop stories, but it still can't read.
1 vote -
Private Lumo App Store for sharing & monetizing custom “MyLumos” (GDPR-safe alternative to GPT Store)
Hi Proton Team and Community,
first of all, thank you for creating Lumo — a privacy-first AI assistant that finally allows European users and businesses to use AI without compromising confidentiality or GDPR compliance. Proton has solved the fundamental problem that all other AI platforms struggle with: trust.
Now that Lumo exists, I would like to propose the next major step:
➡️ A Private Lumo App Store for creating, sharing, and monetizing custom “MyLumos”.
Just like OpenAI has custom GPTs (and a GPT Store), Proton could offer a secure and encrypted alternative — fully compliant, private, and built inside…
1 vote -
Sensitive‑Data Confirmation for Feedback
Problem
When users give a thumbs‑up/down on a response, the associated snippet (including any code or text shown) is sent for anonymous analysis. If the snippet unintentionally contains sensitive information (IP addresses, ports, encryption keys, hashes, credentials, etc.), that data could be transmitted without the user’s explicit consent.
Proposed Solution
Add a post‑feedback check that scans the rated snippet for patterns that look like sensitive data. If a match is found, display a prompt:
…“The content you just rated appears to contain potentially sensitive information (e.g., IP address, key, hash). Do you want to include this data in the feedback1 vote
- Don't see your idea?