Markdown version: https://ai.hiina.space/reports/personal-web-surfing-models/05-sharing-and-remixing-surfing-models.md · index

Index of everything on this site: https://ai.hiina.space/index.md

Personal web surfing models and an ought-driven tab feed: 5. Sharing and remixing surfing models

• Section 5 of 9 of the report "Personal web surfing models and an ought-driven tab feed" by Hiina (v1, updated 2026-10-27)
• Report overview and contents: https://ai.hiina.space/reports/personal-web-surfing-models.md
• Previous: https://ai.hiina.space/reports/personal-web-surfing-models/04-feasibility-of-a-personal-surfing-model-from.md
• Next: https://ai.hiina.space/reports/personal-web-surfing-models/06-tab-triage-and-an-ought-not-engagement.md

5. Sharing and remixing surfing models

No one has published a trained model of a public figure's link choices. The working version of "call Gwern's view of the web" today is retrieval over that person's public link trail, plus an LLM judge prompted with their profile. Privacy pushes the same way: a model trained on raw history is close to a fingerprint, so anything shared should be built from public curation, not private browsing.

Prior art

• Memex trails. In Bush's "As We May Think" (1945), a user builds a trail of their interest and can copy it to a colleague. Bush even predicted a profession of "trailblazers". That is the sharing idea, as static trails rather than models.

• Knowledge (README, site) is the closest working system. It builds public per-person libraries for about 450 people, including Karpathy, Olah and Willison, from their GitHub stars, X likes, HN submissions and Hugging Face likes. That comes to about 440k documents under ColBERT search, with an MCP server offering search within one person's library, search across libraries, and feed and intersection tools. It is retrieval, not a trained model. I couldn't tell whether Gwern is included.

• Trail and annotation tools.

  • Are.na channels: open API, mostly without auth.

  • Hypothesis public annotations: exportable per user.

  • Pinboard public bookmarks.

  • Memex by WorldBrain: shared collections, little activity.

  • Histre: public member pages, hosted.

  • None of these models anyone.

• Simulated users for recommenders. RecAgent, Agent4Rec (SIGIR 2024) and USimAgent build LLM agents seeded from real users' histories. They simulate populations, not named individuals.

• Personal models from screen activity. GUM (Shaikh, Bernstein et al. 2025) turns screenshots, browsing included, into weighted propositions about the user. Its assistant uses expected utility to decide when to interrupt. GUM is a close relative of both the personal surfing model and the ought feed.

• Imitating specific people. In TwinVoice (2025), models fall below the human baseline at matching specific people's opinions and style.

Bootstrapping a Gwern model from public data

Gwern's site is unusually well suited to this. Its build code shows the data available:

• The link-annotation database. GTX.hs defines records holding the URL, title, authors, date, tags and his abstract or commentary.

• Supporting tables. The code also builds a backlinks database, tag directories and per-page link bibliographies. A similar-links embedding index is built with GenerateSimilar.hs.

• Newsletters. Monthly issues are topic-sorted link lists with short glosses (example).

All of this is public as HTML. I could not confirm that a bulk .gtx dump can be downloaded: robots.txt refused my fetcher, and I couldn't check the repo. Assume the per-page bibliographies may have to be scraped.

Three ways to frame it, cheapest first:

1. Retrieval baseline. Embed his annotated corpus and score candidate links by similarity to his library. Add an LLM judge prompted with a generated Gwern PRINCIPAL.md, the same augmentation his essay proposes. This is a weekend's work once the corpus is scraped.

2. Link choice in context. For each essay sentence that cites a link, the cited link is the positive. Plausible uncited links are the negatives, such as arXiv papers or HN posts on the same topic from the same week. That yields a pairwise dataset for a LoRA reranker.

3. Annotation as preference. Predict his tags or gloss from an item's abstract. What he chooses to say about a paper shows what he finds salient.

The gap that matters is that public data shows what he kept and never what he opened and dropped. A "Gwern view" built this way models his curation, not his browsing. For the purpose here, learning which sources he favors or ignores, curation is arguably the better signal.

The shareable artifact is then a bundle: a profile file, a public link library and optionally a small LoRA reranker. A browser extension or MCP tool takes a topic and candidate links, and returns that person's ranking with a one-line reason for each. A user could compare their own ranking with his side by side to see what he would skip.

Text licensed CC BY 4.0 (attribution: Hiina, ai.hiina.space). Source: https://github.com/hiinaspace/ai-hiina-space