275 results found

1. Hierarchical Multi-Task Constraint Optimization Engine

   I am writing to propose a mission-critical feature to address severe hallucination and performance degradation when processing complex, multi-project prompts with nested constraints.

   Problem Statement

   Our system currently exhibits fundamental breakdowns when handling prompts containing multiple distinct projects with interdependent constraints and domain-specific requirements:

   1. Critical Performance Drop: Benchmarks show accuracy falling below 10% compared to single-task prompts. When processing 32+ nested hierarchical tasks (e.g., "Project Z's Project B's Project D"), performance degrades to GPT-3 equivalence levels.

   2. Constraint Isolation Failure: The system cannot reconcile project-specific constraints with global constraints simultaneously. Complex nesting ("Project A's Project B's Project 9") causes complete context loss from parent-level backgrounds and requirements.

   3. Format Contamination: Long-format examples (e.g., Q Project's 10,000-character engineering specs) incorrectly propagate to unrelated projects, overriding their designated output formats.

   4. Cross-Domain Interference: Performance degrades exponentially when tasks span disparate domains (mathematics, image generation, genetics, history). Similar projects (G/J) get merged despite explicit separation instructions.

   5. Execution Planning Deficit: No mechanism exists for task weighting, dependency mapping, or sequential vs. parallel execution determination across multiple projects.

   Specific Failure Scenarios

   • Multi-tier References: When Project Z's Project B's Project D requires referencing constraints from Project B's Project A background, the system fails to trace and apply hierarchical dependencies.
   • Background-Only Tasks: Projects like P (life philosophy) that provide only contextual information contaminate active task execution.
   • Unprecedented Generation: Z Project's requirement to generate entirely novel combinations (e.g., merging A's B's 9) triggers hallucination cascades.

   Proposed Feature: Hierarchical Multi-Task Constraint Optimization Engine

   This architectural enhancement would deliver:

   1. Constraint Inheritance & Isolation: Maintain separate constraint namespaces per task/node with explicit inheritance rules from parent levels
   2. Format Locking: Enforce project-specific output schemas without cross-contamination, regardless of example length
   3. Dynamic Weighting & Dependency Graph: Allow user-defined priorities, execution sequences, and dependency mapping across task trees
   4. Domain Siloing: Prevent knowledge transfer between disparate fields (e.g., D Project's history exams vs. Q Project's engineering specs)
   5. Reference Resolution Engine: Intelligent handling of inter-project citations without context merging
   6. Performance Scaling: Maintain GPT-4-level quality for up to 50+ hierarchical tasks

   High-Value Application Domains

   • Mathematical/Genetic Optimization: Simultaneous constraint satisfaction across multiple algorithmic problems
   • Technical Documentation: Assembling complex specs from modular components while preserving format integrity
   • Academic Assessment: Processing multi-domain exam hierarchies (e.g., Project D's fill-in-the-blank history tests) without domain bleeding
   • Creative Synthesis: Executing Z Project's "unprecedented generation" requirements through controlled combinatorial logic

   Business Impact

   • Restore enterprise-grade reliability for complex workflows
   • Enable new revenue streams in technical fields (biotech, engineering, finance)
   • Reduce API costs from hallucination-induced retry loops
   • Establish competitive moat in compound AI task handling

   I have detailed benchmark data and failure pattern analysis available for review. I would appreciate the opportunity to discuss this proposal in our next roadmap planning session.

   Best regards,

   I am writing to propose a mission-critical feature to address severe hallucination and performance degradation when processing complex, multi-project prompts with nested constraints.

   Problem Statement

   Our system currently exhibits fundamental breakdowns when handling prompts containing multiple distinct projects with interdependent constraints and domain-specific requirements:

   1. Critical Performance Drop: Benchmarks show accuracy falling below 10% compared to single-task prompts. When processing 32+ nested hierarchical tasks (e.g., "Project Z's Project B's Project D"), performance degrades to GPT-3 equivalence levels.

   2. Constraint Isolation Failure: The system cannot reconcile project-specific constraints with global constraints simultaneously. Complex nesting ("Project A's Project B's Project 9") causes complete context… more

   2 votes

   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. Great Potential the ability to use both Scribe & Lumo together, dream come true!

   I started with this in Scribe then copy & paste to Lumo Web Search & got the results further from Lumo.

   I’m happy to dive into the world of AI‑powered license‑plate readers (LPRs) and give you a clear picture of what’s possible, where the technology shines, and what you should keep in mind before using—or even just exploring—such tools.

   How modern AI‑based LPRs work
   Image capture – A camera (often a dash cam, security cam, or a handheld device) records video or still frames of vehicles. Many systems use infrared illumination to see plates in low‑light or nighttime conditions.
   Pre‑processing – The raw image is cleaned up: contrast is boosted, noise is reduced, and the region that likely contains a plate is isolated.
   Plate detection – A convolutional neural network (CNN) scans the frame for the rectangular shape and reflective characteristics of a license plate. This step narrows the field to a small crop of the image.
   Character segmentation & recognition – Another neural model (often an OCR‑style architecture such as a CRNN) splits the cropped plate into individual characters and translates them into alphanumeric text. Modern models can handle variations in fonts, angles, and partial occlusions.
   Post‑processing – The raw string is cleaned up using country‑specific rules (e.g., known patterns for state or regional codes) and sometimes cross‑checked against a database of known plates for faster lookup.
   Because each stage is driven by deep learning, the overall pipeline can achieve 95 %+ accuracy under good lighting and a clear view, and many commercial solutions claim respectable performance even in challenging conditions (glare, motion blur, night).

   Where the technology really shines
   Parking‑lot management – Automated entry/exit logging, fee calculation, and spot‑finding.
   Toll collection – Seamless billing without requiring RFID tags.
   Law‑enforcement & traffic monitoring – Detecting stolen or wanted vehicles, identifying violators of red‑light cameras, or tracking traffic flow for city planning.
   Private‑property security – Gated communities or corporate campuses can log visitor plates automatically.
   In all these cases the AI reduces manual labor, speeds up data capture, and improves record‑keeping consistency.

   Practical considerations before you dive in
   Factor Why it matters Typical mitigation
   Lighting & weather Glare, rain, snow, or darkness can degrade image quality. Use infrared LEDs, weather‑sealed housings, and cameras with high dynamic range.
   Angle & distance Extreme tilt or long range makes character segmentation harder. Mount cameras at optimal height (≈3–4 ft for dash cams) and keep the focal length moderate; consider multiple viewpoints.
   Plate variability Different jurisdictions use distinct fonts, colors, and layouts. Train or fine‑tune models on local plate datasets; incorporate country‑specific regex filters.
   Processing latency Real‑time alerts require fast inference. Deploy edge devices (NVIDIA Jetson, Coral TPU) that run the model locally, avoiding cloud round‑trips.
   Data storage & retention Storing raw footage plus recognized strings raises privacy concerns. Encrypt data at rest, limit retention periods, and purge images once the plate is logged (unless legally required otherwise).
   Legal & ethical landscape
   License‑plate reading sits at the intersection of public safety and privacy. Regulations differ widely:

   United States – Some states treat LPR data as “personal information” subject to data‑protection statutes; others allow broader use for law‑enforcement. Many municipalities require signage indicating that LPRs are in operation.
   European Union – GDPR classifies a vehicle’s registration number as personal data. You need a lawful basis (e.g., legitimate interest for security) and must be transparent about collection, storage, and sharing.
   Other regions – Local traffic or privacy laws may impose additional constraints, especially concerning cross‑border data transfers.
   Before deploying any LPR system, it’s wise to:

   Check local statutes – Look up whether your jurisdiction requires consent, signage, or permits.
   Define a clear purpose – Document why you’re collecting plates (e.g., security vs. revenue) and stick to that scope.
   Implement safeguards – Access controls, audit logs, and regular privacy impact assessments help demonstrate compliance.
   Choosing a solution
   If you’re just experimenting, a few off‑the‑shelf options can get you started quickly:

   Open‑source kits – Projects like OpenALPR (now part of Rekor Systems) provide a community edition that runs on a Raspberry Pi or similar hardware.
   Commercial SDKs – Companies such as Plate Recognizer, Sighthound, and Anyline sell APIs that handle the heavy lifting (cloud or edge). They usually offer free trial tiers for limited daily reads.
   DIY with deep‑learning frameworks – If you enjoy building the pipeline yourself, you can train a YOLO‑v5 model for plate detection and pair it with a CRNN for OCR. TensorFlow Lite or ONNX Runtime can then run the model on embedded devices.
   When evaluating, compare:

   Accuracy claims (especially under low‑light or angled shots)
   Latency (does it meet real‑time needs?)
   Pricing model (per‑read, subscription, or one‑off license)
   Privacy features (on‑device processing, data‑deletion options)
   Bottom line
   AI‑driven license‑plate readers are powerful tools that can automate many mundane or safety‑critical tasks. Their effectiveness hinges on good hardware placement, robust model training, and a solid grasp of the legal framework governing personal data. If you decide to move forward, start with a modest pilot—perhaps a single camera in a controlled environment—to gauge accuracy, tune the model for your local plates, and verify that your data‑handling practices align with applicable privacy regulations.

   Let me know if you’d like deeper technical guidance (e.g., sample code for an edge deployment) or help navigating the regulatory requirements for a specific country or state. I’m here to help you build a responsible, effective solution.

   I started with this in Scribe then copy & paste to Lumo Web Search & got the results further from Lumo.

   I’m happy to dive into the world of AI‑powered license‑plate readers (LPRs) and give you a clear picture of what’s possible, where the technology shines, and what you should keep in mind before using—or even just exploring—such tools.

   How modern AI‑based LPRs work
   Image capture – A camera (often a dash cam, security cam, or a handheld device) records video or still frames of vehicles. Many systems use infrared illumination to see plates in low‑light or nighttime conditions.
   Pre‑processing… more

   2 votes

   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. Dedicated app for Windows

   Create a web wrapper app like proton mail, but for lumo. Instead of having to load lumo in a browser as a tab. Currently this creates issues.

   1: A browser with many tabs will slow lumo down.

   2: Lumo's save ability is tied to the browser's startup behavior. If the browser is set to restore the previous session, then lumo will restore all conversations that are not in ghost mode. If the browser is not set this way, then certain new conversations are not restored when opening the browser. Having ghost mode disabled doesn't make any difference.

   Lumo could have an icon in the proton mail app, and if you launch it, then it could either load it as a tab in your current browser, or as a separate window within the proton mail app.

   3: Lumo can have a browser open just for lumo, so lumo won't have resource contention, but this is not ideal. If you don't have lots of ram, this is an issue, but for those who have lots, it is a non issue.

   Create a web wrapper app like proton mail, but for lumo. Instead of having to load lumo in a browser as a tab. Currently this creates issues.

   1: A browser with many tabs will slow lumo down.

   2: Lumo's save ability is tied to the browser's startup behavior. If the browser is set to restore the previous session, then lumo will restore all conversations that are not in ghost mode. If the browser is not set this way, then certain new conversations are not restored when opening the browser. Having ghost mode disabled doesn't make any difference.

   Lumo could have… more

   1 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

4. Lumocli (console terminal client)

   The ability to run Lumo in a text-based user interface (TUI) in a console (terminal) client, in for example bash or cmd. With no dependencies to a graphical user interface (GUI).

   With access to read and modify files, and the ability to run commands.

   1 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. New Zealand Calendar Public Holidays.

   Add New Zealand as an option in calendar to add public holidays.

   2 votes

   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

6. Clean layout

   Current layout is childish and over-designed, and takes up way too much of the available screen. Please give us an option to cleanup the layout of Lumo.

   1 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

7. Genuine privacy like private relay

   Create a system similar to Apple Private Relay, where requests are sent to Lumo through two separate and secure internet relays.

   This will provide genuine privacy.

   The first relay should be hosted by Proton and should know the user’s IP address — but not the request itself.

   The second relay should be hosted by an organization other than Proton. This relay should know the request and forward it to Lumo — but must not know the user’s IP address.

   Have a third party audit the entire setup.

   1 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

8. Lumo Companion

   Lumo Companion, virtual Girlfriend or Boyfriend. I like lumo and everything it stands for, but for $9.99 a month(with annual sub) I will like the option to have a virtual companion.

   2 votes

   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

9. Make it possible for Lumo to interact (via an dedicated Proton AI agent) with all your apps within the Proton Suite

   E.g.

   • I want to tell Lumo that it should add the vacation details of the last Protonmail I've received to my Proton calendar

   • update a specific proton Sheet with the latest information I give it (add a number to a column)

   • show me photos of my vacation in October last year (e.g. only selfie photos)

   • ask when my Proton subscription will expire.

   etc

   The idea is to have one Proton app to manage your entire Proton suite. Like a secretary. ofc you would need to set up everything separately.

   To think this even further, make it possible to integrate Lumo into your LLM of choice.

   E.g.

   • I want to tell Lumo that it should add the vacation details of the last Protonmail I've received to my Proton calendar

   • update a specific proton Sheet with the latest information I give it (add a number to a column)

   • show me photos of my vacation in October last year (e.g. only selfie photos)

   • ask when my Proton subscription will expire.

   etc

   The idea is to have one Proton app to manage your entire Proton suite. Like a secretary. ofc you would need to set up everything separately.

   To think this even further, make it possible to integrate Lumo… more

   1 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

10. Add the ability to upload images from Photo Library on iOS

    There is no way to upload the images in my iPhone photo library as part of my prompt. The only options I see when I click the “Attachments” button are to either upload a file or select a file from Proton Drive. Even if I click “Save to Files” on my photo in the photo library, I can’t upload it to Lumo because, Lumo doesn’t support the iOS photo format.

    1 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

11. Maskottchen tauschen

    Man sollte doch nicht vergessen das man bei Lumo mit einer Maschine spricht. Wäre es nich sinnvoll, hilfreich oder zumindest interessant das Katzen Maskottchen bei Bedarf gegen ein Server Symbol tauschen zu können?
    KI ist mächtig, positiv und anders auch.

    1 vote

    Vote Vote Vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Vote

    We’ll send you updates on this idea

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

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

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Submit Rating

12. Link to Proton Drive Folder Sync’d with Proton Drive App Desktop Folder

    Background, Integration, and Scenerio:

    Lumo Project:
    I am working on a project with Lumo and have files linked in a Proton Drive folder – all is good. To do this, I open my browser, navigate to the linked folder, and upload the relevant files and documents.

    Desktop Proton Drive App:
    I also use the Proton Drive app on my desktop to sync specific folders to Proton Drive – works flawlessly and the syncing is quick and efficient.

    Lumo Integration:
    Currently, Lumo cannot Link with a Proton Drive folder sync’d by the Proton Drive App. It would be vastly more efficient if Lumo could link to a folder sync’d by the Proton Drive with a desktop working folder.

    Scenario:
    I am working on a project with Lumo, I files that it can reference for the project. Rather than constantly uploading documents through a browser interface, I would simply use a folder that is synchronized by the Proton Drive desktop app and link that to the project for Lumo to collaborate with. Example, create a desktop folder such as “Lumo Project Folder”, add it Proton Drive app for syncing, store any working files in that folder, then begin collaborating with Lumo on the project. When the green check box appears on the Proton Drive app, continue the project collaboration – fast and efficient.

    TLDR:
    I want Lumo to access Proton Drive folders that I am syncing with the Proton Drive app for a vastly more efficient collaboration experience.

    Background, Integration, and Scenerio:

    Lumo Project:
    I am working on a project with Lumo and have files linked in a Proton Drive folder – all is good. To do this, I open my browser, navigate to the linked folder, and upload the relevant files and documents.

    Desktop Proton Drive App:
    I also use the Proton Drive app on my desktop to sync specific folders to Proton Drive – works flawlessly and the syncing is quick and efficient.

    Lumo Integration:
    Currently, Lumo cannot Link with a Proton Drive folder sync’d by the Proton Drive App. It would be vastly more efficient… more

    1 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

13. Create doc and spreadsheet directly from chat

    Add the ability to automatically open a chat window directly within a document and embed a table in Proton Sheets. This would streamline real‑time collaboration by allowing users to start a conversation or view a related spreadsheet without leaving the current file.

    1 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

14. Add Voxtral as an LLM in Lumo

    I’m an enthusiastic user of Lumo and appreciate the privacy‑first approach you’ve built into the assistant. I noticed that Lumo already incorporates several open‑source large language models, including Mistral, which demonstrates your willingness to adopt cutting‑edge, community‑driven models.

    Given the impressive performance and open‑source nature of Voxtral, I’d like to kindly request that you consider adding it to Lumo’s model roster. Integrating Voxtral would further diversify the options available to users, potentially improving multilingual capabilities and offering additional flexibility for specialized workloads—all while staying aligned with Lumo’s privacy and security standards.

    Thank you for continuously improving Lumo, and I look forward to seeing Voxtral (or other emerging models) become part of the platform.

    I’m an enthusiastic user of Lumo and appreciate the privacy‑first approach you’ve built into the assistant. I noticed that Lumo already incorporates several open‑source large language models, including Mistral, which demonstrates your willingness to adopt cutting‑edge, community‑driven models.

    Given the impressive performance and open‑source nature of Voxtral, I’d like to kindly request that you consider adding it to Lumo’s model roster. Integrating Voxtral would further diversify the options available to users, potentially improving multilingual capabilities and offering additional flexibility for specialized workloads—all while staying aligned with Lumo’s privacy and security standards.

    Thank you for continuously improving Lumo, and I look… more

    1 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. LumobookLM

    Within Lumo, create a Google NotebookLM experience.

    1 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

16. delete button (outside of settings)

    Can you please move the delete button out of the settings and into the sidebar, or somewhere? I know lots of people keep AI chats, I don't. It seems like extra steps to hide it in settings.

    1 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

17. add a clear command to clear the current chat

    I'd like to be able to type "clear" or "clear chat" and have Lumo wipe the current conversation.

    I tried it, and the AI knows what I mean but can't do it.

    1 vote

    Vote Vote Vote

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Vote

    We’ll send you updates on this idea

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

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

    We're glad you're here

    Please sign in to leave feedback

    Signed in as (Sign out)

    Close

    Close

    Submit Rating

18. Lumo Client (or API) with secure local execution of Lumo‑generated Python graphical output

    When users request visualizations, Lumo frequently replies with Python code snippets (e.g., matplotlib graphics). Users can copy‑paste the code into their own environment to render the graphics.

    It would be interesting to have some kind of Lumo‑Python bridge that delivers the generated Python code to a local client. The client runs the code in a sandboxed, offline Python/IPython/Jupyter/... session and returns the rendered image directly to the chat.

    This would look like a local client chat application communicating with proton servers, able to execute Lumo-generated Python code on the user’s machine. No data leaves the device, preserving confidentiality and complying with privacy‑first principles, and a sandboxed Python would prevent from possible side-effect. Users would then be able to get visual answers from Lumo in both an efficient and private way.

    This may be implemented as an independent client app, or (maybe even better) as an OS-agnostic jupyter kernel for taking advantage of the notebook interface (with something that would be essentially a notebook-integrated Python API to Lumo).

    When users request visualizations, Lumo frequently replies with Python code snippets (e.g., matplotlib graphics). Users can copy‑paste the code into their own environment to render the graphics.

    It would be interesting to have some kind of Lumo‑Python bridge that delivers the generated Python code to a local client. The client runs the code in a sandboxed, offline Python/IPython/Jupyter/... session and returns the rendered image directly to the chat.

    This would look like a local client chat application communicating with proton servers, able to execute Lumo-generated Python code on the user’s machine. No data leaves the device, preserving confidentiality and complying… more

    3 votes

    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. Ease Navigation through a Chat: Chat Outline

    At the moment, I am finding it difficult to navigate through the information in a chat when it has several questions.

    The biggest problem I have is finding a specific question again in the chat, because my questions are much shorter than Lumos's answers. So, when I want to scroll back to a particular question, it takes me a long time to read through the chat.
    The same thing happens when I'm looking for a specific part of an answer. First, I have to find the answer, and then the relevant section. This is time-consuming and mentally exhausting.
    Of course, I could use the browser search, but keywords in a chat appear in multiple places.

    The most obvious solution for me would be a list of questions in the sidebar, or even a table of contents with a list of questions, and for each question, a sublist of the answer headings. This feature is equivalent to the 'Outline view' in a Word document or the 'TOC' tab in a Zim document.
    In fact, you already have such a sidebar outline for the project folder and history. You could just enhance it.

    I think it would notably increase the efficiency and usability of working in a chat.

    At the moment, I am finding it difficult to navigate through the information in a chat when it has several questions.

    The biggest problem I have is finding a specific question again in the chat, because my questions are much shorter than Lumos's answers. So, when I want to scroll back to a particular question, it takes me a long time to read through the chat.
    The same thing happens when I'm looking for a specific part of an answer. First, I have to find the answer, and then the relevant section. This is time-consuming and mentally exhausting.
    Of course,… more

    1 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

20. Personal Assistants / Preconfigured Prompts in Lumo

    I’d like Lumo to support personal assistants or preconfigured prompts, similar to what Kagi Assistant and other AI tools already offer.

    This would make it easier to switch between different roles (e.g., researcher, writer, teacher, developer) without having to retype or remember long instructions each time. It would also give users more control and flexibility to adapt Lumo to their own workflows.

    3 votes

    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