{"id":2749,"date":"2026-03-14T07:43:56","date_gmt":"2026-03-14T07:43:56","guid":{"rendered":"https:\/\/suprmind.ai\/hub\/?p=2749"},"modified":"2026-03-14T07:44:01","modified_gmt":"2026-03-14T07:44:01","slug":"suprmind-changelog-february-20-march-14-2026","status":"publish","type":"post","link":"https:\/\/suprmind.ai\/hub\/insights\/suprmind-changelog-february-20-march-14-2026\/","title":{"rendered":"Suprmind Changelog – February 20 – March 14, 2026"},"content":{"rendered":"\n

We’ve shipped nearly 200 updates in the last three weeks. From voice input and output, to a brand new way to see where AI models agree and disagree, to smarter context handling behind the scenes – this is one of our biggest update cycles yet. Here’s what’s new.<\/p>\n\n\n\n

New Solution – the Adjudicator<\/h2>\n\n\n\n

The addition of the Adjudicator enables you to move from multi-AI disagreement to a recommended decision direction with one simple click.<\/p>\n\n\n\n

The Adjudicator reads every hallucination, contradiction, correction, and blind spot across your AI conversation \u2014 then tells you exactly what to do about them.
Read more about the adjudicator at this link<\/a>.<\/p>\n\n\n\n

\n\n\n\n

New Features<\/h2>\n\n\n\n
    \n
  • Voice Input & Output<\/strong> \u2014 Speak your prompts with Speech-to-Text and listen to AI responses with Text-to-Speech. A floating audio player lets you auto-continue playback across multiple responses<\/li>\n\n\n\n
  • AI Power Selector<\/strong> \u2014 Pro and Frontier users can toggle between Full Power and Balanced mode to control model reasoning vs. cost per response<\/li>\n\n\n\n
  • Disagreement & Correction Index (DCI)<\/strong> \u2014 See exactly where AI models agree and disagree on each turn, available as a dedicated tab in the sidebar<\/li>\n\n\n\n
  • Adjudicator<\/strong> \u2014 Get an independent, detailed decision brief and proposed direction based on D&CI notes for more informed decisions and further chat continuation, with one-click export option<\/li>\n\n\n\n
  • Auto-Follow Chat<\/strong> \u2014 Toggle auto-scroll to always see the latest response as it streams in, with full visibility of the current bubble and the next AI’s activity indicator<\/li>\n\n\n\n
  • Document Export<\/strong> \u2014 Export Master Documents as DOCX or PDF directly from the app<\/li>\n\n\n\n
  • Gemini Native Web Fetch<\/strong> \u2014 Gemini can now read URLs you share in conversation at no extra cost<\/li>\n\n\n\n
  • GPT-5.4<\/strong> \u2014 Now available for Frontier and Enterprise tier users<\/li>\n\n\n\n
  • LinkedIn Login<\/strong> \u2014 Sign in or sign up with your LinkedIn account<\/li>\n\n\n\n
  • Forgot Password<\/strong> \u2014 Reset your password directly from the login screen<\/li>\n\n\n\n
  • Spark Free Trial<\/strong> \u2014 Try Suprmind free for 7 days. Cancel anytime<\/li>\n\n\n\n
  • Tool Usage Transparency<\/strong> \u2014 See which tools each AI used (web search, file analysis, etc.) in a footer below every response<\/li>\n\n\n\n
  • Smart Selector<\/strong> \u2014 Let Suprmind automatically pick the best AI model tier for your question<\/li>\n\n\n\n
  • Changelog Notifications<\/strong> \u2014 A bell icon in the sidebar keeps you up to date on new features and improvements<\/li>\n\n\n\n
  • Auto-Recovery for Streaming<\/strong> \u2014 If a response stream drops mid-way, the system automatically reconnects and resumes from where it left off<\/li>\n<\/ul>\n\n\n\n

    Improvements<\/h2>\n\n\n\n
      \n
    • Smarter Web Search<\/strong> \u2014 Web search is now available on all tiers including Spark, with citation URLs shown alongside every response<\/li>\n\n\n\n
    • Better Context Handling<\/strong> \u2014 Major upgrade to how conversation context is built and shared across AI models \u2014 token-based compression, dynamic history windows, and smarter summarization improve response quality in longer threads<\/li>\n\n\n\n
    • Improved Document Export Quality<\/strong> \u2014 Fixed table formatting, page breaks, character spacing, and color rendering across both PDF and DOCX exports<\/li>\n\n\n\n
    • Refined Default AI Order<\/strong> \u2014 Gemini now responds first for faster initial results<\/li>\n\n\n\n
    • Master Documents Auto-Save<\/strong> \u2014 Copying or downloading a master document automatically saves it to your project knowledge<\/li>\n\n\n\n
    • Better Error Messages<\/strong> \u2014 AI provider errors are now shown in plain language instead of technical codes<\/li>\n\n\n\n
    • Bot Protection<\/strong> \u2014 Added Cloudflare Turnstile to login and signup for improved security<\/li>\n\n\n\n
    • Polished Settings Page<\/strong> \u2014 Redesigned profile tab with a cleaner two-column layout and theme toggle<\/li>\n\n\n\n
    • PWA Support on iOS<\/strong> \u2014 Proper spacing for iPhone notch and Dynamic Island<\/li>\n\n\n\n
    • Wider Project Sidebar<\/strong> \u2014 More room to view your project context, knowledge, and Scribe insights<\/li>\n\n\n\n
    • Cleaner Adjudicator Cards<\/strong> \u2014 Simplified card design with left-border accents instead of colored backgrounds<\/li>\n\n\n\n
    • More Readable Scribe Notes<\/strong> \u2014 Bumped small fonts and simplified category icons for better readability<\/li>\n<\/ul>\n\n\n\n

      Bug Fixes<\/h2>\n\n\n\n
        \n
      • Fixed @mentions incorrectly triggering on attached file content<\/li>\n\n\n\n
      • Fixed Claude occasionally returning an empty response after using too many tools<\/li>\n\n\n\n
      • Fixed GPT-5.2 getting stuck in a tool-use loop<\/li>\n\n\n\n
      • Fixed mic button sometimes not responding to tap-to-stop<\/li>\n\n\n\n
      • Fixed file attachment count showing incorrect number<\/li>\n\n\n\n
      • Fixed signup and checkout flow reliability (loading states, redirect timing, embed sizing)<\/li>\n\n\n\n
      • Fixed onboarding questionnaire responding slowly to clicks<\/li>\n\n\n\n
      • Fixed occasional app crash related to state synchronization<\/li>\n\n\n\n
      • Fixed auto-scroll not showing the full message bubble<\/li>\n\n\n\n
      • Fixed light theme inconsistencies across the app<\/li>\n\n\n\n
      • Fixed Gemini thinking mode configuration for more consistent responses<\/li>\n<\/ul>\n