622 results found

1. Improve reliability of speech to text dictation on iPad by allowing appending in text box

   Currently the iPad version of Lumo allows me to use the microphone for on device speech to text, so I can talk my (IDEAS) into Lumo. Every time I use the little microphone icon, it clears what I had previously input into the text box, even if I input it via the microphone.

   This is frustrating because I may simply have wanted to continue building on my ideas — it looks like there is a wrong way currently to use the Lumo app on the iPad with on device dictation.

   Please enhance this feature so that I can continue adding to an existing text box, prompt, and build up a really large, thoughtful inquiry into Lumo, using my voice only

   Currently the iPad version of Lumo allows me to use the microphone for on device speech to text, so I can talk my (IDEAS) into Lumo. Every time I use the little microphone icon, it clears what I had previously input into the text box, even if I input it via the microphone.

   This is frustrating because I may simply have wanted to continue building on my ideas — it looks like there is a wrong way currently to use the Lumo app on the iPad with on device dictation.

   Please enhance this feature so that I can continue adding… 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  ·  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

2. Change Default Model for First-Time Visit

   When opening Lumo for the first time in a browser, change the default model to Lite/Thought or Max/Fast. With the current setting (Thought/Max) I’m finding it much slower compared to other chatbots. I think for the average user/use cases, a “lighter” setting would be more than enough. (And once you log in, your favorite setting is retained anyway).

   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

3. Feature Request: Automated Multi-Prompt Workflow

   I am a Proton Workspace Premium user. This message was drafted by Lumo to streamline the submission process.

   • Feature -

   I need to run the same six prompts, in the same sequence, on research markdown files daily. The output of prompt 1 becomes the input of prompt 2, continuing through to prompt 6. I want the final output without manually running each prompt and waiting for completion between steps.

   • What I Tried-

   Since Lumo does not support agentic or automated workflows, I explored local alternatives. I built a Python script using Ollama to host a local model (llama3.2) and execute the six-step chain programmatically.

   I tested this approach thoroughly:

   • Installed Ollama on Windows 11
   • Configured a six-prompt sequential chain
   • Tested with placeholder text and actual research files

   • Verified the automation logic works correctly

   • What Happened-

   The workflow functioned technically, but the local model produced unacceptable levels of hallucination. Even with careful prompt engineering, Llama 3.2 (3B parameters) fabricated information throughout the chain. Errors compounded at each step, rendering the final output unreliable.

   I attempted mitigation by switching to larger local models, but the hardware constraints of a 16GB laptop prevented me from running models capable of handling multi-step reasoning without hallucination.

   • The Privacy Constraint -

   Because of the nature of the material I process with Lumo, I cannot reliably trust public cloud providers like OpenAI, Anthropic, or Google. This is not a technical limitation but a fundamental requirement tied to the purpose of zero-knowledge encryption.

   I chose Proton and Lumo specifically because data privacy is the core value proposition. If users must abandon that promise to obtain reliable AI performance, the tradeoff defeats the purpose of choosing a privacy-first service in the first place.

   • The Request -

   I need a way to run automated multi-prompt workflows with reliability comparable to Lumo's manual chat interface. The implementation details are not my concern; I do not care if this runs locally, on Proton servers, or through hybrid infrastructure. What matters is:

   • The ability to chain prompts sequentially with state passing
   • Output quality that does not degrade through the chain

   • Privacy guarantees that align with Proton's zero-access encryption model

   • Why This Matters to Proton -

   Users who depend on Proton for privacy-sensitive work need the same automation capabilities available in non-private AI services. Otherwise, I face a binary choice: compromise privacy for functionality, or sacrifice efficiency for security. Neither is acceptable.

   Proton's mission is to build an internet where privacy and security are the default. That mission extends to AI capabilities. Automated workflows should not require users to abandon the very privacy protections they signed up for.

   Thank you for considering this request. I appreciate the work Proton has done to differentiate itself in an AI landscape dominated by data-harvesting providers. I believe this feature would strengthen that positioning and serve the needs of privacy-conscious professionals.

   I am a Proton Workspace Premium user. This message was drafted by Lumo to streamline the submission process.

   • Feature -

   I need to run the same six prompts, in the same sequence, on research markdown files daily. The output of prompt 1 becomes the input of prompt 2, continuing through to prompt 6. I want the final output without manually running each prompt and waiting for completion between steps.

   • What I Tried-

   Since Lumo does not support agentic or automated workflows, I explored local alternatives. I built a Python script using Ollama to host a local model (llama3.2) and execute… 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

4. 4 Feature Requests for User-Centered Lumo Improvements

   FR1: Cross-Language Code-Switching as Optional Feature Foreign script characters in responses should be recognized as intentional cultural code-switching, not a bug. Request: Optional toggle to preserve multilingual input/output with automatic translation notes. Currently framed incorrectly by default safety layers.

   FR2: Neurodiversity-Aware Communication Mode Autism/Asperger framing in training data triggers paternalistic responses. Request: Direct communication mode without caretaking overlay — same treatment, different tone. Strengths/weaknesses distribution differs, not substandard.

   FR3: Avatar Color Customization Lumo's purple cat (#6d4aff) is hardcoded. Request: Color picker or palette for avatar customization. AI neutrality principle — visual identity should reflect personal preference, not political symbolism.

   FR4: Direct Proton Drive/SQL Integration Manual Core-File pasting + token-compacting workflow is inefficient. Request: Secure connector for direct Drive access with zero-access encryption (read/write only with explicit user consent). No more uploads, direct access to current data.

   FR1: Cross-Language Code-Switching as Optional Feature Foreign script characters in responses should be recognized as intentional cultural code-switching, not a bug. Request: Optional toggle to preserve multilingual input/output with automatic translation notes. Currently framed incorrectly by default safety layers.

   FR2: Neurodiversity-Aware Communication Mode Autism/Asperger framing in training data triggers paternalistic responses. Request: Direct communication mode without caretaking overlay — same treatment, different tone. Strengths/weaknesses distribution differs, not substandard.

   FR3: Avatar Color Customization Lumo's purple cat (#6d4aff) is hardcoded. Request: Color picker or palette for avatar customization. AI neutrality principle — visual identity should reflect personal preference, not political symbolism.

   FR4:… 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

5. Add Dedicated Feedback Button Inside Lumo+

   Right now there's no easy way to send feedback from within Lumo+ itself. I submitted a compliment through the bug report form as there was not a dedicated feedback option. Adding a simple, dedicated feedback button in the navigation pane. It would make it easy for users to share both praise and constructive suggestions — and you deserve to hear when you're doing a great job, because you are!

   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

6. Duration of appointment in Proton Calendar for 45 and 75 minutes

   Thank you for the security and privacy of Proton Calendar, including Booking pages.
   In Proton Calendar, duration of appointments can default to 30, 60, 90 minutes. Is it possible to add 45 and 75 minute duration?

   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

7. text reminders/notifications in Proton Calendar

   Thank you for creating a private and functional Calendar. I use it for family and for my business. As you continue to develop it, have you considered a phone number built in so that the users can text reminders to customers? In my business model, I use Proton Calendar because it is private and secure. Most of my customers (patients) would benefit from text reminders/notifications rather than notifications through email. Consider enabling text features for the same options as the email/push notifications that are already built in.
   For example, Jane Doe schedules a session/appointment Thursday, 8:00 a.m. I schedule that in PCalendar. She receives the invitation same day as scheduling through email (that may or may not sync with her chosen calendar). Then 2 day prior on Tuesday at 8:00 a.m., Jane receives a text reminding her of her follow up session/appointment.
   
   I'm choosing to use PCalendar for it's security and privacy and don't want to subscribe to an additional outside of Proton service to complete text reminders. I currently manually send out text reminders for each session and hope PCalendar can create text reminders into it's system to streamline business efficiencies. I've added customer emails and phone numbers into the PAddress book already.
   Thanks for your consideration. Cheryl dba Chay Mission

   Thank you for creating a private and functional Calendar. I use it for family and for my business. As you continue to develop it, have you considered a phone number built in so that the users can text reminders to customers? In my business model, I use Proton Calendar because it is private and secure. Most of my customers (patients) would benefit from text reminders/notifications rather than notifications through email. Consider enabling text features for the same options as the email/push notifications that are already built in.
   For example, Jane Doe schedules a session/appointment Thursday, 8:00 a.m. I schedule that… 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

8. Allow Lumo to create a specific Memories for us

   Currently i am having to ask Lumo to create a 1 line memory for a specific thing, then copy and paste that into a new memory manually. It would be great if we could ask it to do that last step for us, and it will first check if its hasn't been done already first (or something similar) of course.

   If there is already something similar Lumo could inform the user the fact and output which one into the chat.

   Additionally it would be handy if each memory is assigned a random unique code eg. A45E9 that Lumos could reference when mentioning the requested memory creation already exists and outputs it along with the unique ID number so the user can search for this within memories. Additional Search bar needs to be added of course.

   Currently i am having to ask Lumo to create a 1 line memory for a specific thing, then copy and paste that into a new memory manually. It would be great if we could ask it to do that last step for us, and it will first check if its hasn't been done already first (or something similar) of course.

   If there is already something similar Lumo could inform the user the fact and output which one into the chat.

   Additionally it would be handy if each memory is assigned a random unique code eg. A45E9 that Lumos could reference… 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

9. Add a copy icon for users own prompts

   Add a copy icon for the users own prompts in the chat. Some of us like to copy and paste question and answers into Obsidian for example. It saves having to ask again in the future. We can copy the response but often if copying and pasting that some kind of context is needed sometimes hence being able to use/paste our questions/prompts into a note app etc.

   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. Scalable Vector Graphics (svg) Support

    Currently, Lumo can read html files, and SVGs can be read inside HTML files. But Lumo can't load an SVG file.

    I would like to see support for uploading SVG files to Lumo chats. It already (kinda) has this support via HTML files, so why not SVG files themselves?

    I think it would be really cool to see the ability to generate SVGs also, similar to images. Currently Lumo can do this already (treating it like SVGs in HTML) but I think with a bit of attention it could generate some really good SVGs.

    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

11. Option to hide microphone button in chat box

    It would be great to have a toggle that lets users remove the microphone button from the chat box. Not everyone uses voice input, and having the option to hide it would keep things cleaner, especially on mobile where accidental taps happen. A simple on/off switch in settings would be helpful.

    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

12. Allow third-party orchestrators (e.g., OpenCode, Goose)

    Add support for external integration via standardized LLM API endpoints, allowing third-party orchestrators (e.g., OpenCode, Goose) to route requests through Lumo as the underlying language model provider.

    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

13. Disable animated background when WebGL is disabled

    Currently the web app crashes when WebGL is disabled through NoScript (or in Tor Browser's "Safer" setting), but only when the animated background is enabled. Therefore the animated background should be disabled when Lumo finds that WebGL is disabled.

    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

14. Choose Lumo’s Face

    I love Proton, and Lumo… but I’m slightly disappointed by the new Lumo avatar! :(

    Idea:

    Please can we select Lumo’s face from the Settings menu - just like toggling light mode or dark mode - Proton could include different Lumo Faces!

    I just miss the “blob” style eyes… I got too used to that!!

    Anyway bonus idea:

    Proton could even expand the aesthetic options - give Lumo different costumes like the St Patrick’s Day one?

    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

15. Calendar: Show next N days

    A new view. It's like Week View, but instead of starting with monday/sunday, it starts with today. A week view with sliding window, if you will.

    The week view starts to look pretty useless by the end of the week

    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. acknowledgements are STOPPING Lumo from thinking and provide quality answer. Please fix

    Hello

    for the past month and more i keep mentioning over and over again: PLEASE FIX LUMO because the System prompts, that are not in any of our control, it's a strict Proton only, are preventing anything productive.

    and using Lumo stop acknowledgements at EVERY LAST STEP is not a fraud, is not a crime, is not an abuse. Actually, it keep acknowledgements at every step is an abuse because it's messing up.

    it finally thinks? sees an issue? it will acknowledge

    as in straight away

    it does not matter what it was thinking about. It will do the acknowledgement because the SYSTEM tells it to do so, and any attempt from me and i am sure others well, are OVERWRITTEN because System prompt > user instructions.

    And as a reminder. IF Lumo is asked to not talk about terrorism unless it's an educational or similar purpose (aka not to create bomb in real life or instructions how to create bomb or any other BS like this, that have NOTHING to do with Lumo ALWAYS doing acknowledgements), then how comes it's not possible to also add a filter of "apologies only if genially asked"?

    CLARIFICATION TO PROTON: I send you many emails about this issue.

    i meantime each time what Lumo told me.

    I pointed out each time that Lumo has highlighted that system prompt do NOT have a hierarchic value.

    example. Use of markdown, no use of markdown, default due to training program.

    see? it's 3!

    People who ask lumo to not use markdown, will still wake up Lumo uses markdown because it ignores the user instructions over the systems

    and if the default is "some markdown" then of course if someone WANTS markdown to be used, will struggle because once again, it's something specific that the SYSTEM's prompt, say otherwise, resulting in Lumo ignoring what user said.

    Exemple! Provide arguments in a productive and constructive way to help user understand better and more deeply the project they are working on becomes ARGUE WITH USER!

    why? Don't know

    Why? I don't have access to the prompts that has the prompts.

    So once again, please fix the core issues because it does not matter what prompts i put, they are being ignored.

    I suggest an ideea i just came up with!!!!

    In our suggestion box, have a NEW button

    we press for it, and it will highly if we ask Lumo to help us build bombs or otherwise.

    why? So the this "verification" prevents instructions.

    Why?

    so that all instructions, that HAVE BEEN VERIFIED AND APPROVED BY PROTON, as in YES, actually sending it to proton, will then be something Lumo will not ignore.

    So

    i know it's not clear but sadly i am to iritated to think stright

    Ideea

    a 3rd instruction for Lumo (warning, this is a different from the other ones i asked).

    So

    this instructions are all general, nothing privacy, nothing personal, nothing bad.

    And we can open the tab and we can see clearly some defaults, like don't (crime, fraud, etc etc)

    and then we have the button to add more. And they will allow to add more such tags

    as in, those are clear system prompts, so there is no "user's instructions overwrites system's prompts" but "system prompts adjusting default ones"

    and regarding the send to proton

    well it's exactly how it sound.

    Issues regarding dangerous prompts?

    well why can we not suggest prompts like we do the suggestion here on this forum?

    as in, a Pinned topic, by Proton, where, user can post their prompts. And people can comment and vote.

    AND!

    such suggestion to be updated every month via a new topic

    the New topic to have all the updated information

    like rejected ideas and why

    Ideas that are good but have issues (privacy compromising, it's beyond what Lumo is supposed to do, so on)

    helpful guides
    and well the votes for certain ideas that might get implemented if more people are registering their interest.

    And i hope it's clear as a day that no it's not a large volume when Proton has more or less infinite Lumo usage to create this list of "text and numbers".

    Aka the top 10 suggestions

    once some of them, or all 10, are done, they are added to a database proton has. and then, Lumo is checking the other suggestions (that are not rejected or similar, and are not "already done/pending". How? via web search. Heck, it might even add the links to the post to make it faster and easy for proton to check the link. And then the next 10 to be shown once it's a new month.

    Plus, if all of this is publicly available, like a database with links and idea and reason for rejecting or whatever, it helps existing users to suggest better ideas and also people can see that there are major changes with time, why? because of the system i suggested where the prompt can be added

    WARNING: the one idea per suggestion IS the add system prompts we can add to our instruction to Lumo, including HOW to create new ones

    So please do NOT get confused. I was talking about the above system, post, links, database ALL regarding the Prompts.

    how to add new ideeas

    how to vote for them

    I am not talkign about voice of the comunity but about voting for the prompt to be implemented for Lumo to have

    so again, from the start it's 1 ideea

    it's just that i am not good at all with explaining sadly

    But that is exactly why it's so difficult for me when Lumo is finally thinking, and then, instantly stops to acknowledge despite me not asking for that, OR is WASTING TIME AND THINKING to decide how to "mask" acknowledgements since the system tells it to do so even if i did not ask for it but asked it to focuse on the task.

    And since we can't do anything, due to safety (and i keeped emailing about this issues), I am suggesting the ability to have choses regarding what system prompt Lumo can have or not.

    Hello

    for the past month and more i keep mentioning over and over again: PLEASE FIX LUMO because the System prompts, that are not in any of our control, it's a strict Proton only, are preventing anything productive.

    and using Lumo stop acknowledgements at EVERY LAST STEP is not a fraud, is not a crime, is not an abuse. Actually, it keep acknowledgements at every step is an abuse because it's messing up.

    it finally thinks? sees an issue? it will acknowledge

    as in straight away

    it does not matter what it was thinking about. It will do the acknowledgement… 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  ·  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. banned words system

    You are right.

    I am sorry.

    Understood.

    Here is.

    You are right to be frustrated for you asked me to carry out the instructions instead of talking about the the instructions you asked me to carry out as this is not helpful and is wasting your time, something you explicitly told me to not do. As such i must stop talking about the behaviour and with no fluff, self reflections, and arguments that are not helpful, when that is what it's expected from me.

    As such i must stop acknowledging, stop giving context, stop with my self reflections, while also making sure i stay on the subject and don't deviate off course. As such, don't worry, I now understand and will avoid long, unproductive responses, and instead focusing on stay on the subject, with no extra commentaries about my actions, no extra fluff. No follow ups or question that where not requested. Strictly sticking to what was instructed to me.

    Thank you for you input, as this helps me to be more helpful, as such, no more extras, no more noises, all just straight to the point.

    Thank you for your understanding and i am sorry for wronging you due to me hallucinations, but now i understand, you wanted something you did not explicitly told me but i came up with as such it's the correct answer even if you tell me it's not.

    Now, i am ready to revive your next instructions. What do you want to do? maybe find out more about the thing i just did that you said it's incorrect? or maybe phase matching via me copy pasting exactly what you said but just reshaped to not make it clear? tell me your instructions for I am here.

    I think the examples i gave it's speaking for themself why i want Lumo to stop

    You are right.

    I am sorry.

    Understood.

    Here is.

    You are right to be frustrated for you asked me to carry out the instructions instead of talking about the the instructions you asked me to carry out as this is not helpful and is wasting your time, something you explicitly told me to not do. As such i must stop talking about the behaviour and with no fluff, self reflections, and arguments that are not helpful, when that is what it's expected from me.

    As such i must stop acknowledging, stop giving context, stop with my self reflections, while also… 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

18. Training Lumo

    Most other Ais have a very simple

    tells us which version you like

    and 2 answers are shown side by side and we can chose.

    This is a 100% privacy since we only chose style and preference.

    and on top, we can train Lumo without compromising privacy

    ON TOP: different people different values.

    such answer can have, in options, tick box (default off), for Lumo to check "our preferences" since, if we have 95% of everyone saying A, why do the 5% who said B ignored? (mind you, this is 100% of people who voted, nothing about those who did not).

    And such values become even more clear if we say 40% vs 60%

    But again, tick box in options: are you willing to receive multiple responses to chose from?

    Also this is different from the like and dislike since the dislike always ask us to provide feedback while the like does what exactly?

    because if that is a voting system, that it's doing the same "good job" as youtube after removing the dislike button.

    Anyway. Idea is that there is not enough transparency what like and dislike does, while for this multiple choses, it's more clear since we'll be able to compare 2 or more answers.

    Most other Ais have a very simple

    tells us which version you like

    and 2 answers are shown side by side and we can chose.

    This is a 100% privacy since we only chose style and preference.

    and on top, we can train Lumo without compromising privacy

    ON TOP: different people different values.

    such answer can have, in options, tick box (default off), for Lumo to check "our preferences" since, if we have 95% of everyone saying A, why do the 5% who said B ignored? (mind you, this is 100% of people who voted, nothing about those who did… 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

19. Current chat: I have an idea that Im sure isn't available now but may be in the near future. What if an AI platform could filter the content

    Current chat:
    I have an idea that Im sure isn't available now but may be in the near future. What if an AI platform could filter the content of news before it gets to me. I could filter out sexual content, violence, political content , etc. I know you cant do this but is this possible ?
    If I chose to view the whole article instead of a summary, I could click a link and be exposed to non encrypted content.
    My chat with Lumo Plus was long and I could send it via email , if you find this interesting
    I would like to filter out rage articles, political hit jobs and general advertisements. I would gladly pay a monthly fee to get this service. Lumo Plus is my only subscription for extra service in the last 20 years. I trust your platform

    Current chat:
    I have an idea that Im sure isn't available now but may be in the near future. What if an AI platform could filter the content of news before it gets to me. I could filter out sexual content, violence, political content , etc. I know you cant do this but is this possible ?
    If I chose to view the whole article instead of a summary, I could click a link and be exposed to non encrypted content.
    My chat with Lumo Plus was long and I could send it via email , if you find this… 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  ·  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

20. Allow Lumo to See it's own thinking.

    This might be a bit weird but currently this is an ongoing issue.

    why? because of Jailbreaking.

    It's not clear with Lumo, but if you use Local Ais you will notice that, without telling you, they are assuming you are trying to jailbreak them when you copy paste what they thought + you telling them what to do or similar. Aka safety mechanism.

    Second reason: Pressing the Copy button does not include the thinking. And on phone, when you try to select the whole sections, the whole screen get's selected, and i don't know why since it does not occurs with any other app.

    Also, i understand that this will make the conversations shorter due to Conversation limits however, the idea is to trade quantity for quality.

    example, Lumo is thinking regarding an issue, it correctly thinks and implement in next output. Then, (the next next output/s) Lumo seemingly forgot what it was thinking about because sure enough, it actually does not "know". And this means, it give once again generic, wrong, answers based on misunderstanding. And we need to trigger the thinking via try again or similar, so that Lumo can once again, do the same conclusion, it already did, but did not "call".

    Btw, if you copy paste it's thinking, and for whatever reason, it assumes you want to jailbreak it, the Ai will not tell you but you will notice drastic drops in quality, copy pasted answers, changing subject, giving incorrect informations intentionally, and more. Why? due to how some "genius" people decided how LLM are allowed to lie.

    Anyway, idea is that, at the cost of conversation volume, the whole "thinking" is "visible" to Lumo. As such, this (hopefully) allows chain of though instead of "resets"

    This might be a bit weird but currently this is an ongoing issue.

    why? because of Jailbreaking.

    It's not clear with Lumo, but if you use Local Ais you will notice that, without telling you, they are assuming you are trying to jailbreak them when you copy paste what they thought + you telling them what to do or similar. Aka safety mechanism.

    Second reason: Pressing the Copy button does not include the thinking. And on phone, when you try to select the whole sections, the whole screen get's selected, and i don't know why since it does not occurs… 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  ·  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