---
id: personal-web-surfing-models/02-gwern-s-guardian-angels-and-how-browsing
title: 'Personal web surfing models and an ought-driven tab feed: 2. Gwern''s Guardian
  Angels, and how browsing fits'
report: https://ai.hiina.space/reports/personal-web-surfing-models.md
section: 2
version: 1
updated: '2026-10-27'
author: Hiina
---

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

# Personal web surfing models and an ought-driven tab feed: 2. Gwern's Guardian Angels, and how browsing fits

- Section 2 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/01-summary.md
- Next: https://ai.hiina.space/reports/personal-web-surfing-models/03-existing-web-surfing-models.md

## 2. Gwern's Guardian Angels, and how browsing fits

In [Guardian Angels](https://gwern.net/guardian-angel), Gwern proposes a personal LLM that emulates one person in order to amplify them. The essay never proposes a browsing or link-choice model. Its framework still carries over almost unchanged.

- **The idea.** A Guardian Angel (GA) is a per-person model. The principal acts like a board that decides what is worth doing, and the GA works out how. It also screens incoming information, scams and prompt injections. Two of his principles are "enhancement, not replacement" and "mental sovereignty". He treats engagement as a cost: the aim is "zero *wasted* interruptions", not zero interruptions.

- **Training.** He would fine-tune an off-the-shelf model under 100B parameters on commodity hardware, starting from about 1GB of his own text:

  - IRC logs, his site's Markdown, and his link-annotation database

  - Twitter, HN and LessWrong exports

  - later, email, clippings, flashcards and archived web pages and PDFs

- **Keeping it current.** Dynamic evaluation (online LoRA updates with replay) keeps the model up to date. Active learning has it ask him questions. Synthetic augmentation includes a generated `PRINCIPAL.md` profile.

- **Evaluation.** Held-out loss on his recent comments, plus blinded A/B tests that he judges himself.

- **Caveats.** Dynamic evaluation costs about 3 times normal inference, and he suggests a budget above \$1,000 a month. Only the principal can grade the model. A footnote matters for a browsing model: passive lifelogging data is worth less than expected, because routine behavior is predictable and says little about deeper preferences.

Mapping the browsing idea onto his:

- Browser history is the equivalent of his IRC logs, but it is mostly the passive kind his footnote warns about.

- The `PRINCIPAL.md` profile is the piece that carries the "ought". It is also the piece that is cheap to build, edit and share.

- The nearest thing to a browsing model in Gwern's orbit is a June 2026 reader response on LessWrong, [Screencasts could be scalable data and evals for single-user emulation](https://www.lesswrong.com/posts/NwrbrHmkDuKPXgLFb/screencasts-could-be-scalable-data-evals-for-single-user). Its first proposed benchmark is predicting which tweets a user clicks in a held-out browsing session.

- Gwern also proposed simulated LessWrong commenters, including a "virtual-gwern" that critiques drafts ([2024](https://gwern.net/blog/2024-virtual-comments)). That is a per-person model used as a critic, close to the "Gwern's view" idea.

---

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