What's new in
LumiChats.

LumiChats Desktop — our native Windows app — gets a dedicated spot in this changelog for the first time, catching up on ten releases of real fixes and one genuinely new feature. The headline is the Originality Report: score any document for how much of it reads as AI-generated, with a graded meter, flagged paragraphs, and a branded downloadable PDF, now running as its own dedicated tab instead of a chat request. Image understanding in chat, which never actually worked in any prior release, is now fixed and faster. Sign-in, PDF reading, and Word document support are all more reliable, and a run of security hardening closes several file-access edge cases.

Study Mode just got more reliable and more secure. We fixed a rare timing issue where switching PDFs while one was still building its search index could carry the wrong document's content into the new session, closed a gap where a failed quiz generation could leave you on a blank screen with no way back, and made document search fall back to a full scan on longer PDFs so questions about content outside the initial index are never missed. We also patched a security gap in how session usage was verified, and Study Mode's error messages no longer expose internal details.

We nearly doubled the AI model comparison library (435 → 903 side-by-side pages) with 13 in-demand models, gave comparison, glossary, feature and use-case links their own clean share-preview cards, fixed three pages that had no preview at all, broadened the blog's image variety, and made this changelog load smoothly as you scroll.

Claude Sonnet 5 is now available on LumiChats — Anthropic's newest and most agentic Sonnet, with near-Opus quality at Sonnet pricing — and you can pick it from the model menu today. We also published four new guides on the new model lineup, expanded the model-comparison library by 110 head-to-head pages (now 435 total), and refreshed the homepage to reflect the 45,000+ developers and students on the platform.

Every blog post now gets its own branded share image. When you or your readers share a LumiChats article on WhatsApp, X, LinkedIn, Slack, iMessage or anywhere else, the link unfurls into a clean, custom preview card built from that exact post — its headline, category and author — instead of a generic stock photo. The cards are generated automatically for every published article and every future one, at the exact size each platform expects, so shared links look professional and far more clickable.

Blog post pages are now significantly faster for users landing directly on an article. Five navigation paths that used to trigger full page reloads — logo, back to blog, next read, mobile sticky bar, and related posts — are all instant SPA transitions. Google Fonts inside the post page also moved from a render-blocking @import to a parallel <link> tag, cutting LCP time on first visit.

Blog font loading is now faster on every visit. DNS pre-resolution hints added for Google Fonts so browsers begin the lookup the moment the page starts parsing — improving font load times on older browsers and reducing layout shift on first paint.

Streaming responses are now visibly smoother and faster — especially in longer conversations. A focused performance overhaul of the chat engine eliminates the processing work that used to run on every single token, replacing it with a lightweight instant lookup. The result is a noticeably snappier feel as the AI types, with no stutter even at the end of a long session.