Show HN: Cursed Browser – a VLM reads the HTML and hallucinates the page
Cursed Browser is a new rendering engine that uses visual large language models (VLMs) to interpret HTML and create unique visual representations of web pages. Each page load results in a different artistic rendering, making it a novel approach to browsing. The project is currently open-source and aims to eliminate unnecessary dependencies on traditional web infrastructure.
- ▪Cursed Browser uses an LLM to interpret HTML and generate visual representations of web pages.
- ▪Each page load results in a unique rendering, described as a work of art.
- ▪The current version is open-source and aims to break away from legacy web dependencies.
Hacker News (Newest) files mainly under programming. We currently carry 5,306 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | GitHub |
| Canonical URL | https://github.com/scosman/cursed_browser |
| Publication time | Mon, 25 May 2026 17:53:14 +0000 |
| Retrieval time | 2026-05-25T18:07:39.397Z |
| Last seen | 2026-05-25T18:07:39.397Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | rGZA2vaGppQ6 |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Cursed Browser: Rendering Engine using Visual-LLMs Cursed Browser asks an LLM to look at the page's HTML and draw what it thinks it looks like. Every page load is a surprise. Every render is a work of art. It's better than correct, it's AI Native. Examples: Cursed vs Safari Compared to other "AI Native" browsers Feature Arc Dia Comet Atlas Cursed HTML parsed by an LLM token-by-token ❌ ❌ ❌ ❌ ✅ CSS interpreted via next-token prediction ❌ ❌ ❌ ❌ ✅ Pixels hallucinated by a VLM ❌ ❌ ❌ ❌ ✅ All hyphens upgraded to em—dashes ❌ ❌ ❌ ❌ ✅ Roadmap V1: An LLM looks at HTML and draws what it thinks a browser would show. Technically a browser. Legally, probably also a browser. Morally, questionable.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.