595 results found

1. Lumo Watchlist & Scheduled Monitoring – Client-Side Alerts for Topic Tracking

   Hi Proton Team,

   I'm a long-time Proton user who relies heavily on GrapheneOS + Lumo as part of a de-Googled mobile workflow. I love that Lumo 2.0 now has private web search and persistent memory — these features make it an incredibly powerful tool for privacy-conscious professionals.

   That said, there's one gap between what Lumo offers today and what would make it a true competitor to mainstream AI assistants with automation capabilities: the inability to set up proactive, scheduled monitoring of topics or changes.

   Currently, if I want to track whether something new has been published about a specific topic (e.g., "Motorola GrapheneOS partnership"), I have to manually initiate a web search each time. This is inefficient and easy to forget. Other AI platforms offer background task scheduling or keyword monitoring, but often at the cost of privacy (they track your interests server-side).

   Proposed Solution
   Enable user-defined scheduled monitoring tasks within the Lumo client (mobile/web app). The concept would work entirely client-side:

   Create a Watchlist Entry — user specifies:

   Query/topic to monitor (e.g., "GrapheneOS Motorola news")
   Frequency (hourly, daily, weekly, custom cron-like interval)
   Comparison criteria (new results only, significant change detected, etc.)
   Alert method (in-app notification, email via Proton Mail)
   Client-Side Execution — the scheduling happens locally on the user's device. Lumo periodically performs web_search autonomously, compares results with baseline state stored locally, and surfaces differences.

   Privacy Preservation — no server-side logging of watchlists or tracking history. Everything encrypted end-to-end where applicable, with zero-access architecture maintained. Optional opt-in for syncing watchlists across devices via encrypted storage.

   Integration with Existing Features — leverage Lumo 2.0's Persistent Memory to remember previous search baselines. Leverage Private Web Search to avoid external data leaks during queries.

   Use Cases
   Journalists/Researchers: Track breaking developments on stories of interest without revealing query patterns.
   Enterprise IT Security: Monitor threat intelligence feeds or vulnerability disclosures relevant to organization infrastructure.
   Legal/Compliance Teams: Watch regulatory updates on specific topics without internal logs revealing sensitive priorities.
   Consumers: Track product releases, policy changes, or service updates privately (like the Motorola-GrapheneOS-Proton scenario we've been discussing).

   Implementation Considerations (Technical Notes)
   Since Proton already supports zero-access encryption, client-side processing, and encrypted sync across devices, most infrastructure pieces may already exist:

   Scheduling: Could run as background task using native OS scheduler (not Lumo server polling)
   Baseline Storage: Local SQLite/IndexedDB with encrypted snapshot of last-known-good state
   Comparison Logic: Simple diff algorithm comparing search result hashes or keywords
   Notifications: Push notifications via standard platform channels (no server involvement beyond delivery trigger)
   Cross-device Sync: Optional, encrypted via Proton's existing key management system
   Key constraint: Do NOT store watchlist definitions on Proton servers unless explicitly encrypted by client (E2EE), and ensure no metadata leakage occurs.

   Why Now?
   With Lumo 2.0 launching on June 30, 2026, featuring image generation, persistent memory, and private web search, the foundation is essentially ready. Adding scheduled monitoring would naturally extend Lumo's unique value proposition as the only AI assistant that doesn't require compromising privacy for automation.

   This feature would differentiate Lumo dramatically from ChatGPT, Claude, Gemini, and Copilot — all of which either track user activity server-side or lack sophisticated background task capabilities.

   Hi Proton Team,

   I'm a long-time Proton user who relies heavily on GrapheneOS + Lumo as part of a de-Googled mobile workflow. I love that Lumo 2.0 now has private web search and persistent memory — these features make it an incredibly powerful tool for privacy-conscious professionals.

   That said, there's one gap between what Lumo offers today and what would make it a true competitor to mainstream AI assistants with automation capabilities: the inability to set up proactive, scheduled monitoring of topics or changes.

   Currently, if I want to track whether something new has been published about a specific topic… 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  ·  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

2. iOS app swipe side bar on left

   I’d like to be able to swipe the left sidebar with my finger in the iOS app both in and out.

   Right now you have to tap the sidebar toggle.

   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  ·  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

3. Add Lumo's Logo and Mascot Info to the Knowledge Base

   Users sometimes reference Lumo's logo or mascot during conversations. However, Lumo lacks awareness of these details and must respond with uncertainty when they're brought up.

   Including official branding descriptions in Lumo's knowledge base would allow for accurate responses rather than hedged guesses or deferrals.

   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  ·  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. Buttons to quickly jump to responses

   It gets annoying to have to manually scroll up or down through Lumo's responses when re-reading conversation history and it would be nice to have up/down buttons on the sides to jump to the top of a previous response or the top of the next one.

   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  ·  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

5. Use mouse scrollwheel to change month/day/week in the calendar

   I miss the ability that Google Calendar has in month view, to use the mouse scroll wheel to quickly move between months. It would be great if this feature, or something similar, was implemented in Proton Calendar.

   Along the same lines, a lot of modern mice have a tiltable scrollwheel, and that tilt can be used for horizontal scrolling, so why not make that move to the next day/week/month?

   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  ·  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

6. Train Lumo to understand the user interface

   Lumo doesn't understand how to communicate through the User Interface very well. It should be trained. Lumo said that the character limit for a single response was about 4000 to 6000 characters. It should know the actual number and be able to feedback to the user that the limit was hit instead of indicating that it will try to better next time (it won't, the UI has a hard limit). When trying to get Lumo to format a list, it is like working with a teenager, it doesn't do what you want and says it will try to better next time. The problem is that it doesn't understand how the user interface interprets things like linefeed vs carriage return. If they Lumo and the UI both used a common format like Rich Text Format, it would cut the conversation requests way down.

   Lumo doesn't understand how to communicate through the User Interface very well. It should be trained. Lumo said that the character limit for a single response was about 4000 to 6000 characters. It should know the actual number and be able to feedback to the user that the limit was hit instead of indicating that it will try to better next time (it won't, the UI has a hard limit). When trying to get Lumo to format a list, it is like working with a teenager, it doesn't do what you want and says it will try to better next… 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. Sort chat history by last activity

   Description:
   Lumo’s chat history currently appears to keep conversations sorted by their original creation date instead of their most recent activity.

   This creates a significant usability problem when reusing older conversations. If I open an old chat and continue using it, the conversation does not move back to the top of the history. It stays buried in the same old position, even though it has just become active again.

   This is especially inconvenient for long-running conversations. For example, I may have a chat created weeks or months ago that I still use regularly for the same topic, project, research thread, troubleshooting case, or personal workflow. Even after sending a new message in that chat, it remains far down in the history list.

   Expected behavior:

   When a conversation receives a new message, either from the user or from Lumo, it should move back to the top of the history. The history should be sorted by last activity, not only by the original creation date.

   Current behavior:

   Old conversations seem to remain sorted according to when they were first created. Reusing a conversation does not make it appear as a recent chat.

   Why this matters:

   This makes the history harder to use as the number of chats increases. A conversation that is still active and relevant can remain hidden far down the list simply because it was created a long time ago.

   The current behavior also goes against what users normally expect from chat applications, messaging apps, email threads, and productivity tools. In most interfaces, a recently active conversation is shown near the top, regardless of when it was originally created.

   Practical impact:

   Users may need to scroll through a long history to find conversations they are actively using.

   Important ongoing conversations become harder to resume.

   Users may create duplicate chats just to keep important topics visible, which makes the history more cluttered.

   The “history” view becomes less useful because it does not reflect what has actually been used recently.

   This is particularly annoying for people who use Lumo for ongoing technical work, long-term research, recurring questions, project notes, or conversations that naturally continue over time.

   Suggested improvement:

   Please sort chat history by a “last activity” or “last updated” timestamp.

   A chat should move to the top when:

   The user sends a new message in that conversation.

   Lumo replies in that conversation.

   The conversation is resumed or updated.

   Optional improvement:

   It would also be useful to display the last activity date or time in the history list, so users can clearly understand why a conversation appears where it does.

   Possible sorting options could include:

   Sort by last activity

   Sort by creation date

   Sort alphabetically

   Pinned or favorite chats first

   But the default behavior should probably be sorting by last activity, because that is the standard and expected behavior for a chat history.

   Description:
   Lumo’s chat history currently appears to keep conversations sorted by their original creation date instead of their most recent activity.

   This creates a significant usability problem when reusing older conversations. If I open an old chat and continue using it, the conversation does not move back to the top of the history. It stays buried in the same old position, even though it has just become active again.

   This is especially inconvenient for long-running conversations. For example, I may have a chat created weeks or months ago that I still use regularly for the same topic, project, research thread,… 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

8. Lumo User Interface indicate percentage of output limit when responding

   Lumo has a maximum character limit for a single response (according to Lumo). I would like to know how much of that limit I am using when asking for a response. Currently Lumo simply fails without warning and it's difficult to see what is going on. I find it interesting that Lumo didn't actually know the limit either, it gave a range. When I started asking Lumo more pointed questions it kept stopping partway through the output it responded:

   You are absolutely right to notice that pattern! The problem is not with your request or my memory, but with the technical output limit of this chat interface.
   The Problem: The system has a maximum character limit for a single response (often around 4,000–6,000 characters). Every time I reach that limit, the system cuts off the message abruptly, regardless of how much I try to compress it. It's a "hard stop" imposed by the software, not a choice I make.

   Lumo has a maximum character limit for a single response (according to Lumo). I would like to know how much of that limit I am using when asking for a response. Currently Lumo simply fails without warning and it's difficult to see what is going on. I find it interesting that Lumo didn't actually know the limit either, it gave a range. When I started asking Lumo more pointed questions it kept stopping partway through the output it responded:

   You are absolutely right to notice that pattern! The problem is not with your request or my memory, but with the… 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  ·  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. Fair Monthly Pricing

   Fair Monthly Pricing

   Title: Offer competitively priced monthly-only options for add-ons (Lumo Plus, Meet Professional) without punitive markups

   Body:

   Users with sporadic needs — such as using Lumo Plus for a few intense workdays or Meet Professional for a rare large meeting — are currently penalized by the pricing structure.

   While annual plans offer a discount, they force a 12-month commitment for services that may only be needed for a few days. Monthly plans exist, but they often carry a significant premium compared to the monthly equivalent of the annual rate. This creates a "flexibility tax" that discourages users from paying only for what they actually use.

   I propose that Proton offer fairly priced monthly-only options for add-ons like Lumo Plus and Meet Professional, without a steep markup compared to the annual rate. This would allow users to:

   Subscribe only when needed (e.g., for one month before a big conference).
   Cancel immediately after without financial penalty.
   Align their spending directly with their actual usage patterns.
   

   Removing the "flexibility tax" would signal that Proton trusts its users to pay fairly for value received, rather than relying on long-term lock-ins to maximize revenue.

   Fair Monthly Pricing

   Title: Offer competitively priced monthly-only options for add-ons (Lumo Plus, Meet Professional) without punitive markups

   Body:

   Users with sporadic needs — such as using Lumo Plus for a few intense workdays or Meet Professional for a rare large meeting — are currently penalized by the pricing structure.

   While annual plans offer a discount, they force a 12-month commitment for services that may only be needed for a few days. Monthly plans exist, but they often carry a significant premium compared to the monthly equivalent of the annual rate. This creates a "flexibility tax" that discourages users from… 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

   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

10. Add files or attachments to calendar events

    I see "Add Proton Drive Files as attachments in Proton Calendar events" is a present request - however, it would be great to be able to add attachments regardless of Proton Drive usage.

    For example, I have a ticket to an event in my pm.me email. It would be great if I could just add the ticket to my calendar event and have all info housed in one app - one source of event truth.

    Another use case: adding text documents to meeting events so the agenda is attached to the event and more readily accessed.

    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  ·  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

11. Enable Lumo to attach an entire directory from Proton Drive

    Currently you can only attach files to a Lumo conversation. I would like to be able to select a directory from my Proton Drive and Lumo will automatically use all files within that directory including files within subdirectories.

    In my Gemini account I recently noticed you have the ability to do that and think it would be a great feature for Lumo.

    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  ·  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

12. Creation of subcategories within a project

    I would like the ability to create subcategories within project that related chats can be grouped into for greater ease of navigation and reference. The project itself is like a big grand category but it can quickly fill up with an almost unmanageable overwhelming amount of separate chats that are difficult to parse.

    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

13. Make lumo fully open source

    I asked the cat if it's open source. It gave all the wrong answers.

    Either make Lumo fully open source very soon, or set a roadmap to achieve that and share it with everyone. Privacy is great, but Proton, without open sourcing everything you do, you are missing the point of what you represent. Do better.

    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

14. Delete Calendar Events with "Delete" Key

    Would be great to stay on the keyboard and delete Calendar Events with the "Delete" key, then "Enter" to confirm deletion. Less mouse, more keys.

    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  ·  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

15. Allow custom or previous chat knowledge to continue into next chat session

    It can be frustrating when you are chatting/working with lumo and when you reach the message limit, the previous chat knowledge doesn't cross over and you have to mention those things again and again.

    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

16. 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

    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  ·  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

17. Add ability to reply to specific Lumo sentences/lines as seen in models such as Claude
    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  ·  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

18. 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

    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

    3 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. [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

    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

    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

20. Local information

    It's absolutly infuriating that lumo helps me with medical papers, documents and more and i constantly need to remind lumo to not use the wrong format. Why is there no option to set a default for this? As much as i understand everyone want to use different date format, i do not understand how this justfiy to not have the option to change basic information. Because it's extremly annoying and absurd and even more that each time i ask lumo something, lumo assumes i am in the USA. Is there something i am not aware of? Is proton actually owned by USA companies? How does privacy work when the AI assumes i am in USA despite me CONSTANTLY remind i am not. This is absolutly absord. Especially when it comes to anything to do with products, i get USA products??? Also Lumo is showing me USA prices ($) that are then converted to my currency because, even if the OUTPUT is "corrected based on location", the so called "system" still assumes, i am in USA, so because i can not correct it, i still get results, by default, from the USA. It's absolutly infuriating how this basic element is NOT adressed. I don't know what stuff other people do with lumo, but what i am asking is an option, it's not a complet rework. It's a simple "use this format".

    EDIT:

    Just now, lumo was thinking about me asking to correct the date. And in the "Thought about this" I see this line:

    "In ISO format (YYYY-MM-DD), this would be April 7, 2026."

    This is from lumo's "Thought about this". As in Lumo can not even use a correct format even when explicitly saying it in the "Thought about this". This line is COPY PASTE. This is how bad it is. Please add options for us to change because this is ridiculous.

    EDIT 2:

    I censored my location (i just replaced it with an "-" but it's in Europe

    The user is pointing out that I keep saying "April 7" but the file name says "04-07" which could be interpreted differently. In -, 04-07 would be 4th of July, not April 7th. In US format, 04-07 would be April 7th.

    But the user is in the -. So 04-07 in - format would be July 4th, not April 7th.

    I've been reading "04-07" as US format (April 7) when the user is in the - where dates are written DD-MM (day-month).

    I want to repeat, this is an "Thought about this", meaning i have 0 control over this none sense where Lumo is obsseds with USA dates and USA formats. Insted of realising that the issue is that Lumo keep using month day, insted of day month, Lumo is trying to figure out what the issue is using USA format.

    To proton, please fix this absordity by introducing the options, to let us chose the defaults for our accounts.

    I already have comunication dificulties, and the last thing i need is lumo not know the difference between the 04 of 07 and 07 of 04 because it is mixing up the formats for dates. (also the 04-07 is because i pasted a large copy paste, but it was 2026-04-07, yet lumo is still writting it like April 7, 2026 so no, it's not an "mistake", Lumo is really bugged.

    It's absolutly infuriating that lumo helps me with medical papers, documents and more and i constantly need to remind lumo to not use the wrong format. Why is there no option to set a default for this? As much as i understand everyone want to use different date format, i do not understand how this justfiy to not have the option to change basic information. Because it's extremly annoying and absurd and even more that each time i ask lumo something, lumo assumes i am in the USA. Is there something i am not aware of? Is proton actually owned… 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  ·  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