--- id: personal-web-surfing-models title: Personal web surfing models and an ought-driven tab feed version: 1 published: '2026-10-27' updated: '2026-10-27' author: Hiina produced-by: Claude deep-research run with citation checking model: claude-opus-5-5 sources-through: '2026-10-26' status: current takeaway: Don't train a generative model on one person's browsing; pair a local ranker on implicit labels with an editable goals profile applied by an LLM rerank, starting with a weekend ought-triage tab feed. topics: - web-browsing - recommender-systems - agents - personalization sections: 9 --- Index of everything on this site: https://ai.hiina.space/index.md # Personal web surfing models and an ought-driven tab feed - Author: Hiina (hiina@hiina.space) - Produced by: Claude deep-research run with citation checking - Version: 1 · published 2026-10-27 · updated 2026-10-27 · status: current - Canonical: https://ai.hiina.space/reports/personal-web-surfing-models.md (this version as one file: https://ai.hiina.space/reports/personal-web-surfing-models/v1.md) - Takeaway: Don't train a generative model on one person's browsing; pair a local ranker on implicit labels with an editable goals profile applied by an LLM rerank, starting with a weekend ought-triage tab feed. - Topics: web-browsing, recommender-systems, [agents](https://ai.hiina.space/topics/agents.md), personalization - Model: claude-opus-5-5 - Sources through: 2026-10-26 - Whole report as one file (51 KB; fetch tools may truncate it, so prefer the section pages below or download with curl): https://ai.hiina.space/reports/personal-web-surfing-models/full.md The question behind this report: could a model trained on one person's open-web history rank links or tabs for that person, or for the research agents working on their behalf? And could such a model rank by what the person *ought* to read, given their current goals, rather than by what they habitually click? The motivating case is someone who uses open tabs as a read-later queue and sometimes opens the browser just wanting to be distracted. A secondary question is whether such models could be shared: could you call up "Gwern's view of the web" the way you call any other tool? ## Contents - [1. Summary](https://ai.hiina.space/reports/personal-web-surfing-models/01-summary.md) (included below) - [2. Gwern's Guardian Angels, and how browsing fits](https://ai.hiina.space/reports/personal-web-surfing-models/02-gwern-s-guardian-angels-and-how-browsing.md) (2 KB) - [3. Existing web surfing models](https://ai.hiina.space/reports/personal-web-surfing-models/03-existing-web-surfing-models.md) (9 KB) - [4. Feasibility of a personal surfing model from browser history](https://ai.hiina.space/reports/personal-web-surfing-models/04-feasibility-of-a-personal-surfing-model-from.md) (7 KB) - [5. Sharing and remixing surfing models](https://ai.hiina.space/reports/personal-web-surfing-models/05-sharing-and-remixing-surfing-models.md) (4 KB) - [6. Tab triage and an ought-not-engagement feed](https://ai.hiina.space/reports/personal-web-surfing-models/06-tab-triage-and-an-ought-not-engagement.md) (5 KB) - [7. Prototype options](https://ai.hiina.space/reports/personal-web-surfing-models/07-prototype-options.md) (6 KB) - [8. Conclusion](https://ai.hiina.space/reports/personal-web-surfing-models/08-conclusion.md) (1 KB) - [9. Sources](https://ai.hiina.space/reports/personal-web-surfing-models/09-sources.md) (9 KB) ## 1. Summary No one has published a personal web surfing model: a model trained on one person's open-web history and used to rank links or tabs for them or an agent. The neighbours are mature: next-page prediction, session-based recommendation, web agents and personal LLMs. A useful version is buildable on commodity hardware now. It just shouldn't be a generative model trained on a person's URL stream. - **History encodes what you did, distraction included.** Kleinberg et al. formalize how optimizing for revealed behavior can raise engagement while lowering welfare. Gwern himself warns that passive lifelog data mostly encodes routine. A pure imitation model of someone's browsing would learn their "please distract me" scrolling. - **The workable architecture has two layers.** - A local ranker trained on implicit labels (dwell, revisit, saved, closed unread) supplies the "is". - An editable natural-language profile (Gwern's `PRINCIPAL.md`), applied by an LLM rerank against the current task, supplies the "ought". - The literature on LLM user profiles and retrieval favors this over raw-history prompting. TALLRec shows a LoRA reranker can learn from under 100 labeled pairs once the labels exist. - **Sharing works best through public curation, not models trained on private history.** Browsing histories are about 99% unique, so they act as fingerprints. A "Gwern view" is buildable from his public link-annotation database, tags and newsletters as retrieval plus a profile-prompted judge. [Knowledge](https://knowledge-web.org) already does this for about 450 people as an MCP server. - **The ought feed has close precedents but no tab version.** - BONSAI (an intent-specified Bluesky feed) and Intent Assistant (CHI 2026: state an intention, an LLM nudges toward it) both worked in small field studies. Compass did the same for YouTube Shorts. - Every tab tool groups tabs by similarity or age; none ranks by a stated goal. - The evidence says: clarify the intention each session, make archiving safe so the pile can shrink, and answer "distract me" with a redirect and an explicit leisure option, not a block. **Most promising first build:** a weekend ought-triage feed. A local 7 to 8B model scores the open tabs against a goals file and a per-session intention. It returns "now", "archive" and one "unwind" pick. Pair it with a tab logger that starts collecting labels for a later personal-ranker MCP tool. Details are under Prototype options. One thing to do today: Chrome's history may expire after about 90 days, and Firefox's per-visit interaction data is off by default (`browser.places.interactions.enabled`). Start archiving now if you want training data later. Next section: https://ai.hiina.space/reports/personal-web-surfing-models/02-gwern-s-guardian-angels-and-how-browsing.md --- Text licensed CC BY 4.0 (attribution: Hiina, ai.hiina.space). Source: https://github.com/hiinaspace/ai-hiina-space