556 results found

1. 5) Image uploads

   Allow image uploads.
   Next post: https://protonmail.uservoice.com/forums/932842-lumo/suggestions/50637338-6-custom-agentic-ai-creator

   10 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

2. Repair the sound

   Repair app sound

   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

   8 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. 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

4. Idea: What if Lumo used on-device processing for heavy lifting?

   Here's a thought: what if Lumo tapped into Apple's on-device intelligence (Neural Engine on iPhones/MacBooks) to pre-process large files before sending them to the cloud?

   Right now, if you upload a big reference book — say, 12 MB — Lumo simply truncates it to 128K tokens. You lose most of the content before analysis even begins. That's frustrating.

   A hybrid approach could fix this: the device handles the first pass (chunking, summarizing, extracting key sections), then ships the compressed result to Lumo's servers for the deep work. Less server load, faster responses, and no more throwing away half your document.

   Yes, it'd need bigger token limits on the server side and some clever work to keep everything encrypted end-to-end — but the payoff is real. This kind of edge-cloud split is already gaining traction in the industry, and it feels like a natural.

   Something to think about.

   Here's a thought: what if Lumo tapped into Apple's on-device intelligence (Neural Engine on iPhones/MacBooks) to pre-process large files before sending them to the cloud?

   Right now, if you upload a big reference book — say, 12 MB — Lumo simply truncates it to 128K tokens. You lose most of the content before analysis even begins. That's frustrating.

   A hybrid approach could fix this: the device handles the first pass (chunking, summarizing, extracting key sections), then ships the compressed result to Lumo's servers for the deep work. Less server load, faster responses, and no more throwing away half your document.

   … 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. Cloud-Assisted Verification ("Draft Local, Verify Cloud")

   Here is my proposal which I think good to implement. (Note: I'm using LUMO itself to help me to produce a proposal based on my ideas)

   Problem: Small on-device models (7B–20B) are prone to hallucination on complex tasks — inventing facts, generating incorrect syntax, or producing logically inconsistent output. Pure local inference is risky for high-stakes work (configuration changes, security analysis, medical/legal information).

   Proposed Solution: A three-layer pipeline where local generation is verified by a cloud model — without exposing raw user data.

   Architecture — "Local Generation + Cloud Verification":

   Layer 1: Local Generation (Instant & Private)

   Input (prompt + files) stays on device
   Small, fast model generates a draft response in milliseconds
   Zero data leaves the device at this stage
   

   Layer 2: Web Search Augmentation (Optional, Lightweight)

   If current information is needed, anonymized web search fetches relevant text
   Results are fed into the local model to incorporate into the draft
   

   Layer 3: Cloud Verification (Selective)

   The generated output text only (not the raw input, not the user's files, not the conversation context) is sent to a large cloud model
   The cloud model acts as a "judge" — it checks:
       Fact-checking: Are claims accurate?
       Logic consistency: Did the model contradict itself?
       Hallucination detection: Is this command syntax real or fabricated?
   Returns a confidence score or a corrected version
   Only triggered for complex/high-stakes queries; skipped for simple tasks
   

   Final Delivery:

   Confidence > Threshold: Show local draft immediately with ✅ "Verified" badge
   Confidence < Threshold: Replace with cloud-corrected version or flag as ⚠️ "Unverified — Review Recommended"
   

   Trust Indicators (Transparent to User):

   🟢 Fully Verified — Generated locally + web-augmented + cloud-verified
   🟡 Web-Verified — Generated locally + web search (no cloud verification)
   🔵 Local Only — On-device only, offline mode, best-effort accuracy
   

   Real-World Example:

   User asks: "Generate a Cisco IOS config to block SSH from subnet 192.168.10.0/24"
   Local model generates: access-list 100 deny tcp 192.168.10.0 0.0.0.255 any eq 22
   Cloud verifier checks: ACL syntax is correct, but missing permit ip any any at the end (implicit deny-all would break connectivity)
   Final output: Corrected config with verification badge
   

   Data Privacy Guarantee:

   Raw files (configs, logs, documents): ❌ Never leave device
   Conversation context/history: ❌ Never leaves device
   Generated output text: ✅ Sent to cloud for verification (output is less sensitive than input)
   User can disable cloud verification entirely ("Fast & Private" mode)
   

   Review — Strengths:

   Solves the hallucination problem without surrendering privacy or driving up costs
   Cloud verification is exponentially cheaper than cloud generation (checking 500 words vs. generating 500 words)
   Proton pays for cloud compute only on the ~20% of queries that genuinely need it
   Enables a lower subscription tier (majority of work happens on user hardware)
   Separates sensitive inputs (stay local) from generated outputs (can be verified)
   Trust indicators give users transparency about response confidence — critical for professional use
   

   Review — Risks:

   Latency: Waiting for cloud verification could delay response display
       Solution: Display local draft immediately with "Verifying..." indicator; update asynchronously if corrections are found
   Bandwidth: Sending every response for verification adds network overhead
       Solution: Selective verification — only verify complex queries; skip simple tasks (greetings, formatting, simple summaries)
   Privacy of output: Even generated output could contain sensitive information
       Solution: User toggle to disable cloud verification entirely; clear trust indicators so users know when verification is active
   

   Feasibility: MEDIUM — The concept of using a large model to verify a smaller model's output is well-established in AI research. Implementation requires Proton to build the verification API endpoint and client-side routing logic.

   Here is my proposal which I think good to implement. (Note: I'm using LUMO itself to help me to produce a proposal based on my ideas)

   Problem: Small on-device models (7B–20B) are prone to hallucination on complex tasks — inventing facts, generating incorrect syntax, or producing logically inconsistent output. Pure local inference is risky for high-stakes work (configuration changes, security analysis, medical/legal information).

   Proposed Solution: A three-layer pipeline where local generation is verified by a cloud model — without exposing raw user data.

   Architecture — "Local Generation + Cloud Verification":

   Layer 1: Local Generation (Instant & Private)

   Input (prompt +

   … 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

6. 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.

   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

7. is LUMO sharing details with US Government on for US defence industry?

   is LUMO sharing details with US Government for US defence industry? If this is the case, we'll stop using it. See Anthropois canceling..and Chat GPT, X Grok, AWS and Meta complying to US Government requests. Had Proton been getting these requests and what were their response?

   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

   2 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. 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

9. Add advanced models from OpenAI in the paid plan

   It would be nice to have advanced models from OpenAI in the paid plan, similarly to what Duck.ai does

   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

10. Stop automatic scrolling when generating long answers.

    When Lumo generates long answers (longer than page height in browser), it starts automatically scrolling down to keep up with the generated text. It would be better if the view does not automatically scroll down, so that I am able to read the answer from the beginning without having manually to scroll back up.

    Browser used: Brave

    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. Lumo Branding / Design

    Lumo Logo / Design / Branding

    Suggesting an overhaul and alignment with the Proton family of product.

    The current choice has no cohesion with the established design language.
    Unless it is design for an audience of kids and adolescents specifically it feels
    playful, cute and disjointed.

    Surely kids and adolescents are not the primary market for the company's
    flagship AI product. Given the importance and relevance of AI a bit more
    thought could very well go into the branding here.

    As huge Proton fan and customer of many years I frequently wonder about
    the design choices. Form, function and aesthetic are frequently not at the level
    of the famed Swiss design standards one would expect.

    Lumo Logo / Design / Branding

    Suggesting an overhaul and alignment with the Proton family of product.

    The current choice has no cohesion with the established design language.
    Unless it is design for an audience of kids and adolescents specifically it feels
    playful, cute and disjointed.

    Surely kids and adolescents are not the primary market for the company's
    flagship AI product. Given the importance and relevance of AI a bit more
    thought could very well go into the branding here.

    As huge Proton fan and customer of many years I frequently wonder about
    the design choices. Form, function and aesthetic… more

    8 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

12. Filtering Thinking

    I posted the suggestion for thinking to be part of the output, but due to the 1 suggestion per topic, this is a follow up but second suggestion. However it's vital to understand that this IS assuming that the "thinking is output" suggestion is implemented.

    The idea is a bit wierd so bear with me.

    I keep seeing Lumo thinking, understanding what i asked it, and as it wants to start, i see

    "wait... maybe"

    or

    "what if"

    And similar stuff that simple are not ok because Lumo actually understood what i was saying and asking and then talked about unrelated stuff due to the "best practice" BS and how LLM work.

    So, when this filter is being used, the output will be replaced with fragment of the thinking.

    As in we get buttons (similar to how we can collapse and expand search results), that will flag that something is correct and to be used, and something is incorrect, to not be used, avoid.

    Like this we are filtering out the thinking to flag correct answers, flag incorrect ones, and the idea that anything left, is not incorrect but it might not be relevant or not good as it is, or simple lumo does not need to focuse on those parts.

    Then we click a button that is essentially the try again, and lumo will redo it's thinking while 100% keeping what we flagged as correct, avoiding anything that was incorrect, and we can continue this until the output is a correct version without wasting time for lumo to start from 0 each time.

    I posted the suggestion for thinking to be part of the output, but due to the 1 suggestion per topic, this is a follow up but second suggestion. However it's vital to understand that this IS assuming that the "thinking is output" suggestion is implemented.

    The idea is a bit wierd so bear with me.

    I keep seeing Lumo thinking, understanding what i asked it, and as it wants to start, i see

    "wait... maybe"

    or

    "what if"

    And similar stuff that simple are not ok because Lumo actually understood what i was saying and asking and then talked about… 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

13. Thinking to be part of the output

    When thinking is on, i really wish that the thinking was included in Lumos output for one critical reason: Lumo can't recall whatever it concluded during thinking.

    And like this we waste a lot of time

    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

14. Personality fragments to filter out system prompts

    Custom Lumo is not working as Lumo's System prompts are still overwriting everything.

    My suggestion was initially to ask for the custom Lumo to not be affected by System Prompts like "be engaging" or "argue with user so user understand better" <- except lumo just arguest.... Or "when given a picture summarise what it says" or one of the worse: "if mistake found, stop and acknowledge" ... and lumo does exactly that... no matter what task, it just stops and keeps naratating about what it did and what it should have and not focusing on the tast. Let me not even start with anticipate next responde when Lumo does not even understand the current task. Or be helpfull where i ask it to help me understand a probleme and it's just obssed to answer the probleme failing to understand the task....

    So see? the custom Lumo is failing because there are to many system prompts that, i don't know if they are even real or not, Lumo just keeps narrating why it fails or something??? Aka why i ask it to help me with a list and stop commenting, and it still comments.....

    So.... Custom Lumo is not currently working because a lot of this prompts are needed?

    On top are the security and the safety and sumilar prompts?

    The best compromise i managed to come up with is personalitys.

    Socialising and engaging

    Powershell like, absolut no "I" "User" "me" "you are right". Absolutly none of this.

    Teacher like where it does not tell you the answer via thinking.

    And many more

    Why? because the more we custumise Lumo, the more the system prompts OVERWRITE what we added for lumo.

    And If Proton has reasons to not allow us more access, and we really need to be able to change settings, my solution is personality fragments.

    You know how when we go to how should Lumo behave and we have some labels we can press on it inserts the text?

    Well that is really the suggestion.

    we don't add anything = lumo has safety and security but otherwise 0 personality.

    We open advanced settings, we can then set how Lumo can answer things, what to use by default.

    To rephase what i am saying: we can't replace proton system prompts, but like this we can chose (most) which of them will be used.

    So Lumo will not even say "I need to apologies" when poiting out that it ignored what was requested, in it's own thinking.

    Because the issue is that custom lumo is not affecting the thinking.

    BTW i am not talking about the output but about the thinking itself.

    Because a lot of times i see it being contaminated with the same logic that makes no sense to even be used.

    Like Lumo searching for keywords to use insted of understanding what the subject is about and the implementation. Aka it does not even think about "i found this keywords, let me see, what does it mean, what implication does it have that it will change" or realy anything similar reasoning. Instead just "i found a keywords, let me redo the same output but insert this keyword"

    So the fragments are essentially system prompts, and while the safety, security, and similar are excluded, the rest of the system prompts to be up to us to add them, or not.

    Custom Lumo is not working as Lumo's System prompts are still overwriting everything.

    My suggestion was initially to ask for the custom Lumo to not be affected by System Prompts like "be engaging" or "argue with user so user understand better" <- except lumo just arguest.... Or "when given a picture summarise what it says" or one of the worse: "if mistake found, stop and acknowledge" ... and lumo does exactly that... no matter what task, it just stops and keeps naratating about what it did and what it should have and not focusing on the tast. Let me not… 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

15. Some replies are unnecessarily long / Make shorter replies

    Quite often Lumo is longer in its replies than I would like to. I can always ask Lumo to be short, but it is a bit annoying.

    A) Can there be some switch near the prompt where i can single click to change length of the reply? (my last choice would be remembered or in a Settings would be an option where I can override this so it always resets to a mine defined default length)
    B) Make the replies shorter and add a button at the end of the reply, where i can click to let Lumo return more verbose reply?

    Sample prompt: Regarding PHP development, what is meant by a "self contained project"?
    Reply contained 894 words (6438 characters), which is more than 3 articles of text!

    Quite often Lumo is longer in its replies than I would like to. I can always ask Lumo to be short, but it is a bit annoying.

    A) Can there be some switch near the prompt where i can single click to change length of the reply? (my last choice would be remembered or in a Settings would be an option where I can override this so it always resets to a mine defined default length)
    B) Make the replies shorter and add a button at the end of the reply, where i can click to let Lumo return more… more

    14 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

16. 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

17. 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

18. Change Ai model

    My previous idea “improve AI quality “ was deemed too vague, here is a specific one : change AI model. Answers are NOT satisfactory for a paid service. Free services give better answers.

    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

19. Provide Lumo with the ability to access real-time token counting information for files

    This will help with keeping within the limits of the plan that you currently have. You would have to opt in for this

    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

20. Give fine tune selection over models

    GIVE US, FINAL USERS, FINE TUNE SELECTION OVER THE MODELS FOR EACH ASKING! And I mean the BEHIND models, the open source models behind LUMO. Why?? Because IT should be GREAT to test, over and over again, to messy around, to make (more) OUR the output! AND... it will cost you almost nothing to add this controls!

    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