Istoricul versiunilor pentru YourAIGuard - 3 versiuni
YourAIGuard de vspendyala
Istoricul versiunilor pentru YourAIGuard - 3 versiuni
Atenție la versiunile vechi! Aceste versiuni sunt afișate pentru testare și ca referință.Trebuie să folosești întotdeauna cea mai recentă versiune a unui supliment.
Ultima versiune
Versiunea 3.0.1
Lansată în 22 mart. 2026 - 15,39 MBFuncționează cu firefox 142.0 și versiunile ulterioareWhat's New in 3.0.1
Bug Fixes- Fixed: responses skipped on thinking models — ChatGPT's o3 and gpt-5-4-thinking models render response text inside a nested prose element rather than directly in the
assistant container. The extension now looks inside prose/markdown/message-content child elements to extract the actual response text. - Fixed: first response permanently skipped when model is still loading — If the background model hadn't finished loading when the first response arrived, the response was
silently marked as processed and never retried. The extension now clears the processed marker on failure so the next DOM update triggers a fresh attempt. - Fixed: background not ready treated as a permanent failure — The background page now signals notReady explicitly, allowing the content script to distinguish a transient
loading state from a real error and retry automatically.
Codul sursă lansat sub Mozilla Public License 2.0
- Fixed: responses skipped on thinking models — ChatGPT's o3 and gpt-5-4-thinking models render response text inside a nested prose element rather than directly in the
Versiuni mai vechi
Versiunea 3.0.0
Lansată în 20 mart. 2026 - 15,39 MBFuncționează cu firefox 142.0 și versiunile ulterioareYourAIGuard 3.0.0
What's New- 7-criterion reasoning quality scoring — each AI response is now evaluated across seven dimensions: relevance to prompt, directly addresses question,
step-by-step/structured reasoning, uses justification or explanation, internal consistency, acknowledges uncertainty when needed, and sufficient completeness. Replaces the
previous 5-rung cosine similarity approach. - Temporal instability pipeline — implements the published methodology from "Temporal Instability Phases Precede and Predict Reasoning Error in Generative Pre-Trained
Transformers" (Pendyala).
After 10 conversation turns, the extension computes a continuous instability index I_t from three signals (failure-burden shift, error burst rate,
per-criterion degradation) and classifies each turn into a latent state: Low, Intermediate, or High instability. - Timeline chart — an SVG line chart shows the I_t instability score across your conversation, with colored rung-track dots and a shaded confidence area.
- All-local inference — scoring uses a bundled MiniLM-L6-v2 model and logistic regression weights trained on the paper's dataset. No data leaves your browser.
Changes
- Calibration period reduced from 20 turns to 10 turns
- Duplicate indicator bug fixed for conversations with search stepsCodul sursă lansat sub Mozilla Public License 2.0
- 7-criterion reasoning quality scoring — each AI response is now evaluated across seven dimensions: relevance to prompt, directly addresses question,
Versiunea 2.1.0
Lansată în 9 mart. 2026 - 15,37 MBFuncționează cu firefox 142.0 și versiunile ulterioareCodul sursă lansat sub Mozilla Public License 2.0