Oct 14 14 days ago 20:18 Arx 0.5.6: password/lockout fixes on Mac, Linux, Windows; Fix problems on Windows (fix.ps1); Linux pwquality read order 18:09 Arx 0.5.5: All results with status details; handover updated 17:32 Arx 0.5.4: Ready to audit screen in two rows; label Fine-tuned AI Model 11:42 Arx 0.5.3: Fix problems on Linux (fix.sh with undo), nftables detection 09:23 Arx 0.5.0: Fix problems on Mac (fix.sh + fixes.json, undo), v0.6 for 4-bit builds, website wording 08:00 Arx 0.4.3: app renamed to Arx, first-open help (installer window + website), colours 07:33 New website: computers only, download + check list + report viewer, no AI in the browser (chat and phone check removed) Oct 13 15 days ago 07:21 Chat: treat a few stray words as a garbled answer and use the knowledge base Oct 12 16 days ago 11:41 Chat: stop the AI on looping text or when too slow, answer from the knowledge base 11:16 Chat: show the detected device and tell the AI about it; download progress inside the message box 10:10 Flag repeated-text answers as not grounded in chat Oct 10 18 days ago 10:12 Rename to Arx (display name) with a new fortress icon; knowledge base: Who is Arx 09:58 Chat: instant answers from the knowledge base, AI download in the background with consent, auto-start when stored, rewrite with AI 08:54 Desktop app 0.4.0 (Ask the assistant about this report), audit-aware chat search, v0.4 pipeline, converter for 1.5B 08:24 Security assistant chat as the front page (Nox-style, WebLLM on device, grounded in the Devseis knowledge base, Run audit from chat); phone check moved to phone.html Oct 9 19 days ago 23:39 Use the fine-tuned auditor model v0.3 06:41 Mac app 0.3.0: download page, desktop-aware front page, model version from the Space, user settings folder, icon, smoke test Oct 8 20 days ago 19:59 Use fine-tuned model v0.1 (WebLLM, constrained JSON decoding, q0f16 on desktop / q4 on phones); MLC converter; v0.3 pipeline 12:40 v0.3: phone check (iPhone, Android) as the Space front page, catalog 0.3 (74 checks), shared vulnerability rules, real-CVE training data Oct 7 21 days ago 14:31 Desktop app (Electron + WebLLM), collector progress output, offline LoRA training script 
