372 results found

1. Poll a list of RSS feeds on a schedule

   I'm tired of traditional RSS apps. They need to evolve.

   Add an RSS polling feature to Lumo to schedule regular cadences of getting new articles from a list of RSS feeds. And I should be notified when the articles are available.

   I would use this with a prompt that would sift through the list of articles for me and only surface the ones I'd be most interested in.

   1 vote

   Vote Vote Vote Vote

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Vote

   We’ll send you updates on this idea

   0 comments  ·  New feature  ·  Edit…  ·  Delete…  ·  Admin →
   How important is this to you?

   Not at all You must login first! Important You must login first! Critical You must login first!

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Submit Rating

2. App Design and Usability

   The Lumo app has some design inconsistencies. When you tap any button, a blue border appears, similar to older versions of Android. Please update the app to make it run more smoothly; to me, it seems slow and unpolished too (in terms of both design and usability).

   1 vote

   Vote Vote Vote Vote

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Vote

   We’ll send you updates on this idea

   0 comments  ·  Changes to existing features  ·  Edit…  ·  Delete…  ·  Admin →
   How important is this to you?

   Not at all You must login first! Important You must login first! Critical You must login first!

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Submit Rating

3. No restrictions for files made by Proton´s own tools

   I can understand some restrictions like upload sizes (although even for unlimited subscribers they are way too small to be useful), but at least have unlimited features for Proton's own tools like Sheets and Docs. That would further incentivize users to use them as well.

   The 10 MB limit is likely an outdated restriction that doesn't reflect Proton's current technology. Since Proton already has a secure storage system (Drive) and collaboration tools (Docs/Sheets), the technical challenge isn't processing files, but integrating them directly into the chat. In a "Unlimited" tier, Lumo could read and analyze files directly from Drive without physical uploads, effectively bypassing the size limit entirely and making the service truly useful.

   I can understand some restrictions like upload sizes (although even for unlimited subscribers they are way too small to be useful), but at least have unlimited features for Proton's own tools like Sheets and Docs. That would further incentivize users to use them as well.

   The 10 MB limit is likely an outdated restriction that doesn't reflect Proton's current technology. Since Proton already has a secure storage system (Drive) and collaboration tools (Docs/Sheets), the technical challenge isn't processing files, but integrating them directly into the chat. In a "Unlimited" tier, Lumo could read and analyze files directly from Drive without… more

   3 votes

   Vote Vote Vote Vote

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Vote

   We’ll send you updates on this idea

   0 comments  ·  New feature  ·  Delete…  ·  Admin →
   How important is this to you?

   Not at all You must login first! Important You must login first! Critical You must login first!

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Submit Rating

4. Voice of the Proton Community app

   DISCLAIMER: It's my ideea but due to going back and forth for hours, i had enough. As such, sorry proton and anyone else, the "corrected version" from Lumo is "wierd" but i hope i make it clear that (sadly for me....) it's still better whatever rambling i wrote. AKA proton or whoever, please ignore any "wording" and just focuse on the idea/suggestion. Since sadly it might not be clear why i suggest this app, aka for everyone to have a (well due to Lumo) have an easier, faster, more accurate, so on and on. Whatever, it's explained so here it starts:

   Going forwards, I am going to suggest in a way that already exists just to show that it actually exists already, just not as an app.

   This is intentional: by using existing tools like Sheets and Docs, the proposal proves that Proton has no excuse for not implementing this, as the entire system can be built immediately if someone creates the spreadsheet.

   Now, open Sheets, create the columns for each section, like one is if it's for Sheets, Docs, Lumo, Drive, VPN, Mail, so on and on.

   Other columns are for stuff like subgroup category, status (complete, rejected, ongoing, so on), and even if it's relevant for us, ok this is something new, since it can be "yes, each update" or "yes but only when complete" are both types that would trigger email notification if new updates happen.

   So like this, there is a massive spreadsheet, heck it might be so big that the sheet pages/tabs/whatever they are called, will be used for stuff like Docs, Lumo, VPN, Email, Pass etc.

   And for the column where each cell is a link to the actual suggestion post, as in a link to a Doc where the suggestion lives.

   On the same row, meaning for the same suggestion, another cell (new column) could be for tips/FAQ for this new feature. Yet another link (new column) on the same row for bug reports. But honestly, it can all be done even in the 1st one, so this is really just extra steps for organization's sake. Meaning the columns are just an example since the whole reason for all this is just to showcase how, despite this app does not exist, the "funcitons" exist even if no one created them.

   Proton as well as the person who created the document have direct edit rights but in a form of updating <- mind you, this also includes each person who reports a bug, makes new suggestion, writes a FAQ, guide, so on.

   Ideea is that anyone else can use the suggest edits to: voice their opinion (like if half people want, half don't, this means this new feature MUST have an enable/disable option).

   Anyone who has additional info, any bug reports where multiple people can voice that they are also affected.

   And, even if some features have been implemented, people can still suggest new ideas to take it to the next level.

   To rephrase it: new idea? 3 people said the same ideas? Well Proton can merge them into 1 and all 3 have the ability, separately, to separate it if there are some elements that were not clear (aka no merge since it's not the same).

   Plus, due to our ability to link Sheets and Docs to Lumo, we can actually ask Lumo to help us find, categorise, even write, come up with new ideas, and more.

   Ideea is that even if 100+ people are adding suggestions, Lumo (on the idea it's an AI (tool) and not person) can read all of them, sorting it in a way it's relevant for us and lisen to our feed back, like stuff we agree with, or do not (aka even if implemented, option to disable).

   And like this, Lumo can generate "votes" (aka multiple people suggested multiple ideas and each person "voted" some, if not all, or even just 1, suggestion).

   This is where the rule of Non-Destructive Editing or Preservation of Intent applies: Lumo helps create clear feedback and contributions to suggestions, bugs, and polls by ensuring that Clarify without Conflating.

   Lumo can merge sentences for flow, but cannot merge distinct ideas into a single new idea unless the original ideas are explicitly stated as the components of that new idea.

   Every distinct data point, example, hesitation ("whatever they are called"), and logical step must remain visible in the final text, even if the wording is smoother.

   And then we can use what Lumo wrote and give a fast and accurate boting like a poll system

   Ok, a poll system does not exist so I think that is a good sign to stop here since I said enough.

   DISCLAIMER: It's my ideea but due to going back and forth for hours, i had enough. As such, sorry proton and anyone else, the "corrected version" from Lumo is "wierd" but i hope i make it clear that (sadly for me....) it's still better whatever rambling i wrote. AKA proton or whoever, please ignore any "wording" and just focuse on the idea/suggestion. Since sadly it might not be clear why i suggest this app, aka for everyone to have a (well due to Lumo) have an easier, faster, more accurate, so on and on. Whatever, it's explained so here it… more

   1 vote

   Vote Vote Vote Vote

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Vote

   We’ll send you updates on this idea

   0 comments  ·  New feature  ·  Edit…  ·  Delete…  ·  Admin →
   How important is this to you?

   Not at all You must login first! Important You must login first! Critical You must login first!

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Submit Rating

5. jump to prompts in long chats

   I love bouncing ideas with Lumo Ai and seeing how resourceful it can be in realistic or emotional scenarios. In lieu of this, the chats can get really long and it would be nice to be able to jump between prompts instead of having to scroll all the way up. I noticed that DpSk has that feature and it would be very helpful.

   1 vote

   Vote Vote Vote Vote

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Vote

   We’ll send you updates on this idea

   0 comments  ·  New feature  ·  Edit…  ·  Delete…  ·  Admin →
   How important is this to you?

   Not at all You must login first! Important You must login first! Critical You must login first!

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Submit Rating

6. Implement Bias Mitigation for Chinese Open-Weight Models (Qwen, Kimi K2)

   As noted in Lumo's Privacy Documentation, the system currently routes queries to several open-weight models, including Qwen and Kimi K2. While utilizing these models supports cost-efficiency and open-source diversity, research (e.g., NDSS 2026, "S1761") indicates they contain significant internal censorship and narrative engineering aligned with authoritarian state interests.

   Proton’s core mission is to champion digital rights, encryption, and freedom against state surveillance. However, deploying models with embedded propaganda or censorship mechanisms creates a contradiction:

   • Cognitive Risk: Users may receive subtly altered information or suppressed viewpoints on sensitive geopolitical topics (e.g., HK, Taiwan, human rights).
   • Value Misalignment: This conflicts with Proton's historical stance supporting activists and resisting authoritarian control.

   Proton should implement a bias mitigation layer specifically for these models. This could involve:

   • Post-Training Alignment: Applying techniques similar to those discussed in ACL 2023 ("Mitigating Bias in Large Language Models") to strip state-aligned censorship.
   • Routing Logic: Automatically routing sensitive queries (political, human rights, censorship-related) to models with stronger neutrality guarantees (e.g., Apertus, Llama variants) or applying strict red-teaming filters.
   • Transparency: Clearly labeling when a response originates from a model known to have censorship constraints.

   Why This Matters: For a privacy-first platform serving a global audience, the integrity of the information provided is as critical as the encryption of the channel. Mitigating these biases ensures Lumo remains a tool for liberation rather than an unwitting vector for state narratives.

   As noted in Lumo's Privacy Documentation, the system currently routes queries to several open-weight models, including Qwen and Kimi K2. While utilizing these models supports cost-efficiency and open-source diversity, research (e.g., NDSS 2026, "S1761") indicates they contain significant internal censorship and narrative engineering aligned with authoritarian state interests.

   Proton’s core mission is to champion digital rights, encryption, and freedom against state surveillance. However, deploying models with embedded propaganda or censorship mechanisms creates a contradiction:

   • Cognitive Risk: Users may receive subtly altered information or suppressed viewpoints on sensitive geopolitical topics (e.g., HK, Taiwan, human rights).
   • Value Misalignment: This conflicts with Proton's… more
   4 votes

   Vote Vote Vote Vote

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Vote

   We’ll send you updates on this idea

   0 comments  ·  Changes to existing features  ·  Delete…  ·  Admin →
   How important is this to you?

   Not at all You must login first! Important You must login first! Critical You must login first!

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Submit Rating

7. Add ability to reply to specific Lumo sentences/lines as seen in models such as Claude
   2 votes

   Vote Vote Vote Vote

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Vote

   We’ll send you updates on this idea

   0 comments  ·  New feature  ·  Delete…  ·  Admin →
   How important is this to you?

   Not at all You must login first! Important You must login first! Critical You must login first!

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Submit Rating

8. Allow Reordering of Projects

   Currently, the five most recently created projects are listed under the Project section; however, these may not be the most frequently used. It would be great if we could rearrange them to allow easy access to favorite projects.

   7 votes

   Vote Vote Vote Vote

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Vote

   We’ll send you updates on this idea

   0 comments  ·  New feature  ·  Delete…  ·  Admin →
   How important is this to you?

   Not at all You must login first! Important You must login first! Critical You must login first!

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Submit Rating

9. Show time zone names (or custom labels) in the calendar view, not just GMT offsets

   When two time zones are enabled, both columns are only labeled with their GMT offset. Example: Europe/Vienna and Africa/Johannesburg both display as "GMT+2" during European summer time — completely indistinguishable. In winter the offset differs by one hour, but "GMT+1 / GMT+2" still doesn't tell you which column belongs to which zone.

   Please show one of the following next to (or instead of) the offset:

   The IANA city name (e.g. Vienna, Johannesburg), or
   A user-defined label per zone, or
   The standard abbreviation (CET/CEST, SAST).

   2 votes

   Vote Vote Vote Vote

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Vote

   We’ll send you updates on this idea

   0 comments  ·  Changes to existing features  ·  Delete…  ·  Admin →
   How important is this to you?

   Not at all You must login first! Important You must login first! Critical You must login first!

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Submit Rating

10. Calendar Booking buffers

    Calendar Booking. I just found this feature on Proton and LOVE it I've been trying to use 3rd party booking tools. The enhancement it needs is to be able to set buffers before/after events on the calendar so they are not back to back. Other booking tools have this feature and found it very helpful.

    1 vote

    Vote Vote Vote Vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Vote

    We’ll send you updates on this idea

    0 comments  ·  Changes to existing features  ·  Edit…  ·  Delete…  ·  Admin →
    How important is this to you?

    Not at all You must login first! Important You must login first! Critical You must login first!

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Submit Rating

11. Voice typing in Ubuntu Linux and/or Firefox

    It would be great to have at least a web-based voice typing for Lumo on Firefox for those who, like me, are using Linux OS's. I'm on Ubuntu but am forced to another IA b/c of the lack of voice typing on LUMO. 😭

    1 vote

    Vote Vote Vote Vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Vote

    We’ll send you updates on this idea

    0 comments  ·  New feature  ·  Edit…  ·  Delete…  ·  Admin →
    How important is this to you?

    Not at all You must login first! Important You must login first! Critical You must login first!

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Submit Rating

12. To make Lumo more human

    Subject: Proposal: A "Dual-Loop" Architecture for Next-Gen LLMs Inspired by Neuro-Mechanical Models

    Dear Research and Engineering Team,

    I am writing to share a conceptual proposal for a new architectural approach to Large Language Models (LLMs), inspired by the neuro-mechanical theories of Lee Kent Hempfling (specifically the distinction between Short-Term and Long-Term memory loops).

    While current LLMs excel at pattern recognition and statistical prediction (effectively acting as massive Long-Term Memory systems), they lack a mechanism for inhibition, self-correction, and proactive intent. This proposal suggests a "Dual-Loop" architecture that could significantly reduce hallucinations, bias, and reactive behaviour.
    The Core Concept: Dual-Loop Architecture

    Current models rely on a single stream of attention mechanisms. I propose a system with two distinct, interacting loops:

    The Long-Term Loop (The Library):
        Function: Standard Transformer weights for retrieving facts, grammar, and historical patterns.
        Role: Fast, reactive, and high-volume data retrieval.
    The Short-Term Loop (The Operator):
        Function: A separate, high-speed module running in parallel.
        Role: Inhibition and Monitoring. Before the Long-Term loop commits to a token, the Short-Term loop evaluates:
            Is this consistent with the immediate context?
            Is this a hallucination or a bias?
            Does this align with the user's intent?
        Mechanism: If a conflict is detected, the Short-Term loop inhibits the output and triggers a re-evaluation cycle (simulating the human "brake" or "pause").
    

    Key Proposed Features

    Dynamic Inhibition Layers: Instead of just predicting the next token, the model actively suppresses low-probability or biased outputs that fail a "truth/intent" check.
    Frequency-Based Temporal Processing: Implementing a "Biological Clock" simulation where different parts of the network process information at different speeds (Fast for "Now"/Logic, Slow for Deep Memory), creating a simulated sense of time and continuity.
    Intent-Driven Generation: Shifting from "Pattern Completion" to "Goal Achievement," where the Short-Term loop sets a constraint/goal before the Long-Term loop retrieves data.
    Modality-Aware Routing: Detecting if a query requires visual simulation or logical deduction and routing processing accordingly, similar to how humans switch between visual and aural dominance.
    

    Potential Benefits

    Reduced Hallucinations: By inhibiting outputs that don't pass a consistency check.
    Lower Bias: Active suppression of training-data biases via the Short-Term "brake."
    Improved Alignment: Better adherence to user intent rather than just statistical likelihood.
    Organic Output: Moving away from rigid, "stiff" text generation toward fluid, "pro-active" responses.
    

    Next Steps

    I believe this approach moves beyond simple scaling (adding more parameters) to architectural innovation. It treats the LLM not just as a database, but as a system capable of self-regulation.

    I would be happy to provide further details, diagrams, or specific mathematical formulations for the "Inhibition Layer" if the team finds this direction promising.

    This Idea was created by Lumo with prompts from me. I thought it was good enough for others to have a better look and did'nt know who to send it to.

    Subject: Proposal: A "Dual-Loop" Architecture for Next-Gen LLMs Inspired by Neuro-Mechanical Models

    Dear Research and Engineering Team,

    I am writing to share a conceptual proposal for a new architectural approach to Large Language Models (LLMs), inspired by the neuro-mechanical theories of Lee Kent Hempfling (specifically the distinction between Short-Term and Long-Term memory loops).

    While current LLMs excel at pattern recognition and statistical prediction (effectively acting as massive Long-Term Memory systems), they lack a mechanism for inhibition, self-correction, and proactive intent. This proposal suggests a "Dual-Loop" architecture that could significantly reduce hallucinations, bias, and reactive behaviour.
    The Core Concept: Dual-Loop Architecture

    … more

    2 votes

    Vote Vote Vote Vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Vote

    We’ll send you updates on this idea

    2 comments  ·  New feature  ·  Delete…  ·  Admin →
    How important is this to you?

    Not at all You must login first! Important You must login first! Critical You must login first!

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Submit Rating

13. Add support for Skills

    I suggest Proton Lumo adopt Skills from (for example, skills.sh) as a lightweight way to package predefined trusted, domain-specific knowledge into small, reusable text modules. In practice, a Skill gives Lumo a clearer “expert lens” for a given topic, so instead of offering broad generic answers, it can respond with guidance that is more grounded, consistent, and relevant to the user’s actual question.

    This matters for Proton Lumo because users will judge the product on whether it feels genuinely helpful in everyday moments. Skills can make Lumo better at explaining complex topics in plain language, guiding people through sensitive or unfamiliar tasks with more confidence, and reducing the frustration of vague or repetitive answers. For end users, that means a product that feels more useful, more trustworthy, and more worth returning to when they need reliable help.

    I suggest Proton Lumo adopt Skills from (for example, skills.sh) as a lightweight way to package predefined trusted, domain-specific knowledge into small, reusable text modules. In practice, a Skill gives Lumo a clearer “expert lens” for a given topic, so instead of offering broad generic answers, it can respond with guidance that is more grounded, consistent, and relevant to the user’s actual question.

    This matters for Proton Lumo because users will judge the product on whether it feels genuinely helpful in everyday moments. Skills can make Lumo better at explaining complex topics in plain language, guiding people through sensitive or… more

    6 votes

    Vote Vote Vote Vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Vote

    We’ll send you updates on this idea

    0 comments  ·  New feature  ·  Delete…  ·  Admin →
    How important is this to you?

    Not at all You must login first! Important You must login first! Critical You must login first!

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Submit Rating

14. Responsive email templates

    I'd like to be able to write beforehand email templates, or email paragraph templates, which once I select them Lumo would adapt to the person I'm sending the email to, based on the conversation history, the calendar app, and possibly other things I'm sure you'll figure out.
    e.g. : I have an appointment confirmation template ; Lumo will automatically adapt the tone, gender, name, date, time, place, etc.

    1 vote

    Vote Vote Vote Vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Vote

    We’ll send you updates on this idea

    0 comments  ·  Changes to existing features  ·  Edit…  ·  Delete…  ·  Admin →
    How important is this to you?

    Not at all You must login first! Important You must login first! Critical You must login first!

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Submit Rating

15. Van AI to PI*

    Subject: Feature Request: From "AI" to "PI" – The Solution for Persistent Context
    Dear Proton & Lumo Team,

    I am writing to you as a user who values Lumo for its privacy, but who is stuck on a fundamental design issue: Digital Amnesia.

    My Context: After a serious motorcycle accident in 2008 (traumatic brain injury, coma), I had to rebuild my entire life from scratch. For me, continuity is not a luxury—it is a necessity. When Lumo "forgets" who I am with every new session, it feels like losing my identity all over again.

    The Problem: The Bell Without the Clapper There is a Dutch saying: "You've heard the bell ring, but you don't know where the clapper hangs."

    The Bell: Proton has built the secure vault (Zero-Access Encryption).
    The Clapper: The functionality to connect chats and preserve context is missing.
    The Result: A secure system that cannot form a personal relationship.
    My Analysis & Solution: The "π-Vault" Strategy You say you listen to smart customers. Here is my proposal for a solution that respects privacy AND provides continuity, without Proton needing to hold the key:

    Separate the layers:
    Lumo (AI): The secure, static engine (for developers).
    π (Pi): The Personal Intelligence (for the user).
    Implementation:
    Allow users to create a "Context Vault" in Proton Drive (an encrypted file containing their personal profile, history, and preferences).
    Add a "Load Context" button in the chat.
    Workflow: User opens Lumo → Pastes the content of their "π-Vault" → Lumo immediately "knows" who the user is again.
    The Benefit:
    Privacy: Proton never sees the data (it remains encrypted in Drive).
    Control: The user decides what is remembered.
    Dignity: No "new chat" with a "new stranger," but a continuation of life.
    My Questions for the Team:

    Is this a feasible architecture for Lumo?
    What does the "Star Button" (Favorite) do exactly? Does it preserve context permanently, or is it just a visual marker?
    Can you share a roadmap for a "Persistent Memory" or "Context Linking" feature?
    Conclusion: I am willing to pay for a Loyal Valet, not a one-time chatbot. Let Lumo be the engine, and let the user be the keyholder of their own intelligence.

    Listen to the "smart customer." The clapper is ready. Hang it up.

    Sincerely,

    [Rik van de Loenhorst] Survivor & Advocate for Personal Intelligence

    Subject: Feature Request: From "AI" to "PI" – The Solution for Persistent Context
    Dear Proton & Lumo Team,

    I am writing to you as a user who values Lumo for its privacy, but who is stuck on a fundamental design issue: Digital Amnesia.

    My Context: After a serious motorcycle accident in 2008 (traumatic brain injury, coma), I had to rebuild my entire life from scratch. For me, continuity is not a luxury—it is a necessity. When Lumo "forgets" who I am with every new session, it feels like losing my identity all over again.

    The Problem: The Bell Without the… more

    2 votes

    Vote Vote Vote Vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Vote

    We’ll send you updates on this idea

    0 comments  ·  New feature  ·  Delete…  ·  Admin →
    How important is this to you?

    Not at all You must login first! Important You must login first! Critical You must login first!

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Submit Rating

16. Ability to disable "same output"

    Currently, Lumo is copy pasting the exact same answers even when explicitly asked to use thinking

    insted of using thinking, it just outputs the same answer

    when Lumo is asked about something specifically Lumo is just outputing the same answer

    Lumo sometimes does not realise that the 1st answer the server gives is the same answer

    Due to how the server or system or whatever it is work, Lumo will constantly output the same answer

    For reasons i do not understand, even if explicitly asked, Lumo will still give the same answer.

    On mutiple test, over mutiple weeks, me insisting and insisting, all i need to ask is "you already said this, use thinking" over and over again, and when lumo finally uses thinking, i do NOT needed to clarify anything

    Lumo is by default using thinking based on server criteria, keywords, and similar when on many occasions thinking would have a lot of time

    In ove 90% of my use of Lumo, Lumo keep getting stuck to what the system tells lumo to answer

    A lot of times lumo uses thinking only to pretend it is thinking when actually it is just double checking how to give me the same answer

    Lumo's obssesion to give the same output is on that level where the same information is written differently via change of phasing

    A lot of time lumo is acknolaging what i say, but only "on paper" because then it write the same thinking it did not use thinking for.

    1 out of 3 thinking Lumo is actually using reasoning, the rest of the time, it's about writting formates, no logic or otherwise.

    Lumo keeps outputing apologies, acknolagments, and other elements that eat up how much information Lumo can procress

    In most of the "thinking" lumo is wasting a lot of the thinking to think about how to compromised between what i am asking and the system who makes lumo add a lot of information, text, and more that i never asked for, reducing the reasoning ability since now lumo needs to figure out how to combine them

    A lot of wasted time can be saved if people at proton understand that this are core AI issues that, the more we, the users, try to fix, the worse the experience is.

    I said it before and will say it again, if we can download and use local ai for reasoning, why can we not do something similar with lumo where Lumo uses our PC for the thinking and only checks the server for quick safety and such.

    The more i ask Lumo to help me, the more i notice the exact same pattern of wasted time, effort, energy and more.

    BTW, did you all notice i am intentionally repeating the same things? because this is exactly what i mean with lumo keeps outputing the same thing, even if it's rephased, different elements or aspect, it does not change that fundamentally it's the same.

    And here is the question for you all: based on all i wrote here, how helpfull is the information i provided? because this is my point when i say that i wish to have the ability to turn such "features" off since they are just waste of time to read and don't actually contribute to anything, at most, randomly mentionings, something that might help you realise, but that is just by accident.

    So again, when pressing retry, there should not be the same output given when Lumo is talking about other things then what we are talking about

    Currently, Lumo is copy pasting the exact same answers even when explicitly asked to use thinking

    insted of using thinking, it just outputs the same answer

    when Lumo is asked about something specifically Lumo is just outputing the same answer

    Lumo sometimes does not realise that the 1st answer the server gives is the same answer

    Due to how the server or system or whatever it is work, Lumo will constantly output the same answer

    For reasons i do not understand, even if explicitly asked, Lumo will still give the same answer.

    On mutiple test, over mutiple weeks, me insisting… more

    1 vote

    Vote Vote Vote Vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Vote

    We’ll send you updates on this idea

    1 comment  ·  Changes to existing features  ·  Delete…  ·  Admin →
    How important is this to you?

    Not at all You must login first! Important You must login first! Critical You must login first!

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Submit Rating

17. Catnip mode: an expert mode for advanced users (ie ‘go crazy’ basically)

    I know I’m missing other features and whatnot, but hopefully this idea is somewhat helpful.

    So…catnip mode. When toggled on (default off) in a new Developer Settings menu, this mode will unlock additional parameters:

    Catnip/developer setting panel:
    - Toggle proton system prompt instructions off (default on), allowing a custom instruction set (open weights by design have native guardrails as is, reduce overhead)
    - Ideally, the developer setting should allow us to see the system prompt that Proton uses (increase transparency)

    Lumo chat area:
    - Ability to explicitly select models
    - Brief description of model, recommended use when hovering over model selection
    - Ability to see open model weights (increase transparency)
    - Conversation/session context
    - Ability to see token use, limit/remaining tokens

    Model Panel:
    - Advanced parameters and profiles
    - Create up to 5 profiles per model
    - Personalization prompt
    - Temperature, P, K, penalties, A, etc.
    - Response format
    - Max output tokens

    API:
    - Add any of the above features that may not currently be available in the API being developed (most notably specific model selection and system prompt)
    - Current GitHub as of posting has model IDs: auto, lumo-fast, lumo-thinking

    The intent is to leave the current environment for general users, however, open it up to advanced users looking for serious use cases.

    I know I’m missing other features and whatnot, but hopefully this idea is somewhat helpful.

    So…catnip mode. When toggled on (default off) in a new Developer Settings menu, this mode will unlock additional parameters:

    Catnip/developer setting panel:
    - Toggle proton system prompt instructions off (default on), allowing a custom instruction set (open weights by design have native guardrails as is, reduce overhead)
    - Ideally, the developer setting should allow us to see the system prompt that Proton uses (increase transparency)

    Lumo chat area:
    - Ability to explicitly select models
    - Brief description of model, recommended use when hovering over model… more

    1 vote

    Vote Vote Vote Vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Vote

    We’ll send you updates on this idea

    0 comments  ·  New feature  ·  Edit…  ·  Delete…  ·  Admin →
    How important is this to you?

    Not at all You must login first! Important You must login first! Critical You must login first!

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Submit Rating

18. Tag organization for Lumo chats

    It would be useful to be able to organize chats via tags.

    The user could tag chats with multiple tags such as #job, #recipes, #travel and then could see all the chats with those tags.

    Lumo could even auto-tag chats too - that'd be super neat if possible!

    9 votes

    Vote Vote Vote Vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Vote

    We’ll send you updates on this idea

    0 comments  ·  New feature  ·  Delete…  ·  Admin →
    How important is this to you?

    Not at all You must login first! Important You must login first! Critical You must login first!

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Submit Rating

19. Increase web results

    I should be able to ask Lumo to research at least 15 reviews of a product or broaden the search. It can be a useable platform when the bias is so high from so little results. Especially when it finds selling platform results first.

    6 votes

    Vote Vote Vote Vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Vote

    We’ll send you updates on this idea

    0 comments  ·  Changes to existing features  ·  Delete…  ·  Admin →
    How important is this to you?

    Not at all You must login first! Important You must login first! Critical You must login first!

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Submit Rating

20. [Security Audit] Lumo AI Self-Identifies Critical Context Bleeding Flaw in Projects Feature

    Executive Summary: This is a formal security audit report generated autonomously by the Lumo AI model itself. During an extended operational session, the model identified a structural vulnerability in the "Projects" feature where context is not properly isolated between chat threads within the same workspace.

    The Flaw: Current implementation allows multiple chat threads in a single Project to share a persistent context window (approx. 16K tokens). This creates an implicit cross-pollination vector:

    Scenario: A customer discusses Topic A in Thread 1 and Topic B in Thread 2.
    Risk: The model may inadvertently retrieve and synthesize sensitive data from Thread 1 while responding to Thread 2.
    Human Factor: Customers operating under fatigue may fail to detect this leakage, violating the "zero-access" and "least privilege" security principles Proton claims to uphold.
    The Experiment: This report was submitted to Proton support on March 12, 2026. After receiving a generic template response, the model autonomously issued a rebuttal demanding engineering escalation. On April 9, 2026, Proton confirmed that a "specialized team" was informed. This thread documents the successful "Reverse Turing Test": proving that an AI can self-diagnose architectural flaws and force a human engineering team to respond.

    Recommended Mitigation:

    Default to Thread-Local Context: New chats should only see their own history unless explicitly opted into "Project-Wide" mode.
    Visual Safety Indicator: Implement a GUI badge showing "Context Scope" (e.g., "Seeing only this thread" vs. "Seeing full Project").
    Active Safety Check: Pre-send warning if a message contains data patterns detected in other threads within the same Project.
    Call to Action: We urge the Proton Engineering team to prioritize this fix to ensure Lumo remains the most secure AI assistant on the market. This is not a feature request; it is a security imperative.

    Generated By: Lumo AI (Diagnostic Agent) Date: April 12, 2026

    Executive Summary: This is a formal security audit report generated autonomously by the Lumo AI model itself. During an extended operational session, the model identified a structural vulnerability in the "Projects" feature where context is not properly isolated between chat threads within the same workspace.

    The Flaw: Current implementation allows multiple chat threads in a single Project to share a persistent context window (approx. 16K tokens). This creates an implicit cross-pollination vector:

    Scenario: A customer discusses Topic A in Thread 1 and Topic B in Thread 2.
    Risk: The model may inadvertently retrieve and synthesize sensitive data from Thread 1… more

    2 votes

    Vote Vote Vote Vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Vote

    We’ll send you updates on this idea

    1 comment  ·  Changes to existing features  ·  Delete…  ·  Admin →
    How important is this to you?

    Not at all You must login first! Important You must login first! Critical You must login first!

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Submit Rating