323 results found

1. To make Lumo more human

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

   Dear Research and Engineering Team,

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

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

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

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

   Key Proposed Features

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

   Potential Benefits

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

   Next Steps

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

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

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

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

   Dear Research and Engineering Team,

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

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

   … more

   1 vote

   Vote Vote Vote Vote

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Vote

   We’ll send you updates on this idea

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

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

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Submit Rating

2. Add support for Skills

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

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

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

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

   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

3. Responsive email templates

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

   1 vote

   Vote Vote Vote Vote

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Vote

   We’ll send you updates on this idea

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

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

   We're glad you're here

   Please sign in to leave feedback

   Signed in as (Sign out)

   Close

   Close

   Submit Rating