Skip to content

Interfaces, voice and devices

Items from the discussions that mention this topic, oldest first. Generated 2026-10-28T19:00:09. Current status of features is in feature-status; the owner's source of truth outranks anything said in a discussion.

Decisions

  • 2026-W07 CONFIRMED: Use Telegram instead of WhatsApp for the bot interface due to official API support and cost efficiency. (src-7d6f99df81 @ 00:00:00)
  • 2026-W40 CONFIRMED: The team will not build a fixed UI upfront, but rather generate dynamic on-the-spot interfaces based on prompt specifications. (src-13fc0f9115)

Plans

  • 2025-W42 PLANNED: Build an interactive Sinhala/English Citta-Cetasika website sourced from the provided Excel sheet. (src-1380d0e6e4 @ 00:00:00)
  • 2025-W50 PLANNED: [name withheld] will generate English and Sinhala Dhamma analyses and musical descriptions for approximately 220 to 230 songs using Claude prompts. (src-bb1e0e327c @ 00:35:00)
  • 2026-W09 PLANNED, medium confidence: Expose the validated website data via an MCP tool interface so external voice models and LLMs can accurately query and respond on Abhidhamma topics. (src-49fef1fd41 @ 00:35:00)
  • 2026-W09 PLANNED, medium confidence: The third milestone is developing visual representation components for Abhidhamma Citta and [doctrine term] causal relationships. (src-49fef1fd41 @ 00:40:00)
  • 2026-W28 PLANNED: Expose the CLI config harness through a local web server bridge to connect with front-end dynamic UI designs. (src-dadb4daf5f @ 00:20:00)
  • 2026-W39 PLANNED: Showcase the depth of Machine World, Inner Realm, and Marga Sakaccha together by creating story-driven visual episodes demonstrating real workflow automation. (src-3b4db21ed4)
  • 2026-W41 PLANNED: Open source the Machine World interface harness so users can load it across CLI, desktop, and web environments. (src-165c55b513)

Proposals

  • 2025-W36 PROPOSED, medium confidence: Explore running native voice-interactive chat bots using Vercel AI SDK or AWS Bedrock integration. (src-157495739d @ 00:40:00)
  • 2025-W39 PROPOSED, medium confidence: Add four clickable navigation buttons or a scroll indicator beneath the top landing section so users notice content below the fold. (src-6bb5a72d51 @ 00:00:00)
  • 2025-W42 PROPOSED: Expose the Citta-Cetasika website as an MCP server for AI agents to query mental states and enable voice navigation. (src-1380d0e6e4 @ 00:00:00)
  • 2026-W03 PROPOSED: Create fan-made short video edits connecting English/Sinhala songs to the US 'Walk for Peace' monks viral trend. (src-cfd51c6172 @ 01:05:00)
  • 2026-W09 PROPOSED: Utilize AI models supporting Sinhala, such as Gemini, along with OCR to assist in cross-checking and validating Dhamma text data against books. (src-49fef1fd41 @ 00:50:00)
  • 2026-W10 PROPOSED, medium confidence: Digital simulation interfaces are designed to be connected eventually to physical embodiment, enabling direct control in the physical plane. (src-c77b42478f @ 00:10:00)

Action items

  • 2025-W36 PLANNED: Fix the mobile heading styling and replace server profile content. (src-157495739d @ 00:00:00)
  • 2025-W50 PLANNED: [name withheld] or [name withheld] will schedule a screen-sharing session to teach [name withheld] basic Git and repository commit workflows. (src-bb1e0e327c @ 00:35:00)
  • 2026-W01 PLANNED: Move the comparison action buttons (clear selections, compare, export) to the top of the interface. (src-b9713fb12a @ 00:20:00)
  • 2026-W01 PLANNED: Redesign the 'About' section UI by enlarging logos and adding distinct links/logos for Marga Sakaccha, Inner Realm, and Machine World alongside YouTube and Facebook. (src-b9713fb12a @ 00:25:00)
  • 2026-W40 PLANNED: The team should create an initial UI artifact prototype using Claude Design and share the artifact link with Speaker 1. (src-13fc0f9115)

Problems

  • 2025-W36 CONFIRMED: The website 3D effect heading appears too large on mobile screens, leaving only one line centered. (src-157495739d @ 00:00:00)
  • 2025-W50 CONFIRMED: Sinhala Unicode text extraction from the PDF fails across multiple OCR solutions and vision models. (src-bb1e0e327c @ 00:10:00)
  • 2026-W01 CONFIRMED: The large table with numerous columns and rows displays fine on desktop but breaks on mobile view. (src-b9713fb12a @ 00:15:00)
  • 2026-W03 CONFIRMED: In the Marga Sakaccha graph interface, lines and tree nodes are visually overlapping, creating an unreadable UI. (src-cfd51c6172 @ 00:35:00)
  • 2026-W39 UNRESOLVED: Local Sinhala AI language modeling research remains underfunded and underdeveloped, forcing reliance on external multilingual models connected via tools like Whisper. (src-3b4db21ed4)

Features mentioned

  • 2025-W31 PROPOSED: The website should feature audio-reactive visual models where visual elements dynamically groove and blend based on audio frequency patterns. (src-1a1fced380 @ 00:10:00)
  • 2025-W33 PROPOSED: The website should enable cross-navigation between all seven song versions, showing each version's story, audio narrative, visual music patterns, and creation tools. (src-8fd4bc579e @ 00:00:00)
  • 2025-W33 PROPOSED: User interactions, conversations, and UI preferences should be saved in dedicated user folders to allow personalized session re-generation like advanced cookies. (src-8fd4bc579e @ 00:25:00)
  • 2025-W42 IMPLEMENTED: Inner Realm website background visualizer updated to subtly shake image art corresponding to the playing track. (src-1380d0e6e4 @ 00:04:00)
  • 2025-W51 PROPOSED, medium confidence: The user interface will feature generative UI where dashboards and visualizations are created conversationally on demand. (src-cb9cd2e6f3 @ 00:15:00)
  • 2026-W06 PLANNED: The final product is planned to be voice-only, using an intermediary mini-agent to synthesize concise spoken summaries rather than reading raw text. (src-b612a1e5b0 @ 00:15:00)
  • 2026-W41 PROPOSED: Machine World interface harness connects connected devices including mobile phones, TVs, laptops, and home appliances with dynamic rendered context. (src-165c55b513)
  • 2026-W42 IMPLEMENTED: System terminal instances are controlled and monitored via MCP (Model Context Protocol) integration using Cmax. (src-93d91aeca1)

Technical details

  • 2025-W32 PLANNED, medium confidence: An audio frequency analysis pipeline using a Python package should extract audio frequency spectrums to modulate background visuals dynamically. (src-23e82f4d71 @ 00:10:00)
  • 2025-W33 PROPOSED: Machine World aims to generate dynamic UIs dynamically per user using four context/data layers rather than hosting static predefined backends. (src-8fd4bc579e @ 00:00:00)
  • 2025-W36 PROPOSED: For music visual sync in Inner Realm, extract stems (drums, guitars) using AI, plot audio frequency graphs, and bind them to the animation timeline. (src-157495739d @ 00:45:00)
  • 2025-W42 PROPOSED, medium confidence: Use WavePad Sound Editor, DaVinci Resolve, or ElevenLabs Voice Isolator to remove silences and clean audio for Dhamma recordings. (src-1380d0e6e4 @ 00:23:00)
  • 2025-W50 PROPOSED: The visualisation should dynamically highlight causal antecedent factors and subsequent resultant cittas when a user selects a specific mind state. (src-bb1e0e327c @ 00:20:00)
  • 2025-W51 PROPOSED: Machine World is conceptualized as an AIware system rather than conventional software, interacting natively through conversational and CLI interfaces. (src-cb9cd2e6f3 @ 00:00:00)
  • 2026-W01 IMPLEMENTED: The network view renders interactive connections between Akusala Citta and Cetasika nodes, though overlapping connector lines require visual cleanup. (src-b9713fb12a @ 00:00:00)
  • 2026-W01 IMPLEMENTED: Speaker 2 uses Gboard voice typing to digitize Sinhala Abhidhamma texts because OCR solutions (including local LLaMA models) failed. (src-b9713fb12a @ 00:35:00)
  • 2026-W06 CONFIRMED, medium confidence: Kling AI 3.1 produces high-quality, cinematic video snippets suitable for short music visuals. (src-b612a1e5b0 @ 00:55:00)
  • 2026-W10 CONFIRMED: Audio visualization in the system separates rupa (form, characters, visual palette) from nama (underlying concept and meaning) to allow flexible skill transformation. (src-c77b42478f @ 00:05:00)
  • 2026-W28 CONFIRMED: Edge model capabilities require 12GB, 15GB, or 24GB RAM devices to execute larger operational tasks locally. (src-dadb4daf5f @ 00:10:00)
  • 2026-W39 IMPLEMENTED: Speaker 2 built an automated video generation pipeline using Claude to handle screen recording, automatic captions, and intro/outro voice stitching. (src-3b4db21ed4)
  • 2026-W40 CONFIRMED: The harness is defined purely declaratively as a description containing a system part and a user part, which a runner dynamically renders into a UI. (src-13fc0f9115)
  • 2026-W41 IMPLEMENTED: Speaker 1 uses cmux on macOS as an MCP-driven terminal tool to orchestrate Claude CLI sessions and agent swarms. (src-165c55b513)

References to earlier work

  • 2026-W10 CONFIRMED: Inner Realm songs use blended skills and mind blends to present multiple distinct visual stories supporting a single underlying meaning. (src-c77b42478f @ 00:05:00)