AI Safety paper scout
Data, no key needed:
- Paper index by direction:
https://raw.githubusercontent.com/wuyoscar/AISafetyHot/main/daily-papers/topics/<slug>.json — every paper pushed so far under that direction: title, titleZh, line (what the paper does, one line), topics, venue (arXiv id or conference), date, url, site, authors.
- Daily lists:
https://raw.githubusercontent.com/wuyoscar/AISafetyHot/main/daily-papers/<year>/<YYYY-MM-DD>.json.
- Direction slugs and definitions: MCP
aisafetyhot_get_topics.
- This week's newest picks: MCP
aisafetyhot_get_latest (window: "7d") → paperPicks.
Steps:
- Map the user's request to 1–3 slugs with
aisafetyhot_get_topics (e.g. "prompt injection" → prompt-injection, "jailbreak" → jailbreak).
- Fetch each slug's JSON; merge, drop duplicates by
id; add paperPicks that match.
- Rank: what the user asked for first, then newer first; keep up to 15 unless asked for more.
- Output a table: title (linked), one line on what it does (from
line), venue, date. Offer the AI Safety HOT reading link (site) when present.
- If asked for citations, emit BibTeX: for
arXiv <id> use @misc{<firstword><year>, title={...}, eprint={<id>}, archivePrefix={arXiv}, url={https://arxiv.org/abs/<id>}}; for conference papers use @inproceedings with the venue and year and the url. Use authors from the index for author = {A and B and ...}; never invent authors.
Related work. When the user gives a title, abstract or idea: list its 2–4 core ideas, map each to slugs, keep papers whose title or line matches, group them into 2–4 lines of work (one paragraph each: what the line does, the papers as [n], how the user's work differs — only from what the user said), then the numbered references and BibTeX. Say "per the paper's one-line summary" where you only have line, and tell the user which directions had few matches.
Today's papers. For "what's new today", read the newest daily-papers/<year>/<YYYY-MM-DD>.json and list its papers with their line.
The index grows by 30 hand-picked papers a day (well-known authors, top labs, strong groups); each entry also lists authors; the full library and readings are at https://aisafetyhot.com/zh/papers.
1---2name: aisafety-paper-scout3description: Find AI safety papers on a direction (jailbreaks, prompt injection, agent security, backdoors, reward hacking, interpretability, evals, AI control, privacy...) from the AI Safety HOT paper library, with one-line takeaways and BibTeX. Use when the user asks for today's new papers, papers or a reading list on an AI safety topic, or a related-work section with citations for their own paper or idea.4metadata:5 source: https://skillmd.com/skills/wuyoscar/aisafety-paper-scout6---78# AI Safety paper scout910Data, no key needed:11- Paper index by direction: `https://raw.githubusercontent.com/wuyoscar/AISafetyHot/main/daily-papers/topics/<slug>.json` — every paper pushed so far under that direction: `title`, `titleZh`, `line` (what the paper does, one line), `topics`, `venue` (arXiv id or conference), `date`, `url`, `site`, `authors`.12- Daily lists: `https://raw.githubusercontent.com/wuyoscar/AISafetyHot/main/daily-papers/<year>/<YYYY-MM-DD>.json`.13- Direction slugs and definitions: MCP `aisafetyhot_get_topics`.14- This week's newest picks: MCP `aisafetyhot_get_latest` (`window: "7d"`) → `paperPicks`.1516Steps:171. Map the user's request to 1–3 slugs with `aisafetyhot_get_topics` (e.g. "prompt injection" → `prompt-injection`, "jailbreak" → `jailbreak`).182. Fetch each slug's JSON; merge, drop duplicates by `id`; add `paperPicks` that match.193. Rank: what the user asked for first, then newer first; keep up to 15 unless asked for more.204. Output a table: title (linked), one line on what it does (from `line`), venue, date. Offer the AI Safety HOT reading link (`site`) when present.215. If asked for citations, emit BibTeX: for `arXiv <id>` use `@misc{<firstword><year>, title={...}, eprint={<id>}, archivePrefix={arXiv}, url={https://arxiv.org/abs/<id>}}`; for conference papers use `@inproceedings` with the venue and year and the `url`. Use `authors` from the index for `author = {A and B and ...}`; never invent authors.2223**Related work.** When the user gives a title, abstract or idea: list its 2–4 core ideas, map each to slugs, keep papers whose `title` or `line` matches, group them into 2–4 lines of work (one paragraph each: what the line does, the papers as [n], how the user's work differs — only from what the user said), then the numbered references and BibTeX. Say "per the paper's one-line summary" where you only have `line`, and tell the user which directions had few matches.2425**Today's papers.** For "what's new today", read the newest `daily-papers/<year>/<YYYY-MM-DD>.json` and list its papers with their `line`.2627The index grows by 30 hand-picked papers a day (well-known authors, top labs, strong groups); each entry also lists `authors`; the full library and readings are at https://aisafetyhot.com/zh/papers.