← Back to chatSources & Prompts
This chat routes each question to one knowledge domain and answers only from that domain's sources. Below is exactly what each domain draws from (with licenses and links) and the prompts it uses — including links to the raw prompt text so you can read it yourself.
EA Careers [ea_careers]
effective-altruism CAREER advice — choosing high-impact careers, career capital, specific job paths, earning to give, policy/biosecurity/animal-advocacy CAREERS, skill-building, switching jobs, applications. Sources: 80,000 Hours, Probably Good, Animal Advocacy Careers.
retrieval: ea_densemodel: claude-opus-4-8Status: available
Sources it draws from
High-impact career research and problem profiles.
License: Non-commercial ToS (personal/learning use; publishing needs 80k's permission).
Impact-focused career guidance and path profiles.
License: Snippets used with attribution + link; non-commercial.
Career guidance for high-impact animal-advocacy work.
License: Snippets used with attribution + link; non-commercial.
Prompts it uses
View prompts →raw JSONAI Safety (Stampy replica) [ai_safety]
AI existential risk, AI alignment, technical alignment research, AI governance arguments, interpretability, misalignment, AGI/ASI risk, the case for/against AI danger. Sources: Alignment Research Dataset (LessWrong, Alignment Forum, MIRI, arXiv, etc.).
retrieval: densemodel: claude-opus-4-8Status: available
Sources it draws from
Dense index of high-value alignment prose (LessWrong, Alignment Forum, MIRI, arXiv, blogs, etc.). 3,191 chunks / 1,096 docs.
License: Aggregated third-party content under mixed upstream licenses; cited snippets + deep-link to the original url (what Stampy itself does); arXiv capped.
The Stampy embed -> top-k -> dedup -> numbered-citable-fragments retrieval path and prompt assembly, ported (logic) and reused (prompt text verbatim).
License: MIT License. Original copyright the StampyAI authors.
Prompts it uses
View prompts →raw JSONAnimal Advocacy [animal_advocacy]
animal advocacy, veganism, animal welfare/rights, factory farming, and how to respond to common anti-vegan objections/myths (e.g. plants feel pain, protein, humane farming, 'personal choice'). The SUBSTANCE of animal-ethics arguments and advocacy — NOT careers in animal advocacy (those are ea_careers). Sources: Vegan Hacktivists animalsupportbot myth-rebuttals, Open Paws / VEG3.
retrieval: densemodel: claude-opus-4-8Status: available
Sources it draws from
Curated myth -> rebuttal knowledge base for common anti-vegan objections. All 40 enabled pairs ingested (46 chunks).
License: GPL-3.0 (covers code). DATA reused with attribution; ingest code is an independent reimplementation, so no GPL bleed into this codebase.
Persona-conditioned animal-advocacy reasoning Q&A. Filtered subset of 150 English, non-adversarial rows (313 chunks).
License: Apache-2.0 (attribution kept).
Prompts it uses
View prompts →raw JSONEA / Rationality Community [ea_community]
the effective-altruism & rationality COMMUNITY and movement: cause prioritization debates, movement-building, EA philosophy/critiques, rationality and epistemics, community norms and discussion. General EA/LessWrong essays — NOT specific career advice (ea_careers) and NOT technical alignment substance (ai_safety). Sources: top EA Forum + LessWrong posts.
retrieval: densemodel: claude-opus-4-8Status: available
Sources it draws from
Top high-karma community posts (cause prioritization, movement-building, EA philosophy/critiques). Top 120 by karma.
License: User-generated content under site ToS; cited snippets + link back to the original post only, attributed to author + site; non-commercial, rate-limited.
Top high-karma rationality/epistemics community posts. Top 120 by karma (240 posts / 240 chunks across both sites).
License: User-generated content under site ToS; cited snippets + link back only, attributed to author + site; non-commercial, rate-limited.
Prompts it uses
View prompts →raw JSONEffective Giving [effective_giving]
WHERE TO DONATE money: which charities are most effective, whether a specific charity/nonprofit is a good or effective place to give, GiveWell/ACE/GWWC/The Life You Can Save recommendations and methodology, cost per life saved, donation cost-effectiveness, choosing a cause area or fund FOR A DONATION, tax-deductible effective giving. NOT career choice (ea_careers), NOT general EA philosophy/movement debates (ea_community), NOT AI-risk substance (ai_safety), NOT global-health/poverty facts or what-works intervention evidence (human_welfare).
retrieval: densemodel: claude-opus-4-8Status: available
Sources it draws from
Top charities, program reviews, cost-effectiveness analyses, giving funds, archived per-year top-charity lists
License: CC BY-NC-SA 3.0 US
Cross-cause best-charities list, charity/fund pages, evaluating-the-evaluators, giving FAQs
License: All rights reserved — snippets + link back
Recommended animal charities + full charity reviews + methodology
License: All rights reserved — snippets + link back
22 recommended charities fighting extreme poverty, cause funds, evaluation framework
License: All rights reserved — snippets + link back
Prompts it uses
View prompts →raw JSONGlobal Health & Development [human_welfare]
GLOBAL HEALTH & DEVELOPMENT and human welfare SUBSTANCE: poverty and extreme poverty, disease burden (malaria, TB, HIV, diarrheal disease, child/maternal mortality), nutrition and hunger, clean water and sanitation, vaccines, life expectancy and living conditions, what interventions actually work to help people (evidence from RCTs, J-PAL, WHO data, Our World in Data), and 'how do I actually help people / improve human welfare'. NOT which charity to donate to (effective_giving), NOT career choice (ea_careers), NOT EA movement/philosophy debates (ea_community).
retrieval: densemodel: claude-opus-4-8Status: available
Sources it draws from
Articles and topic pages on poverty, global health, disease burden, child mortality, nutrition, water/sanitation, vaccines, and development
License: CC BY 4.0
The full WHO fact-sheet library (diseases, health risks, health systems)
License: CC BY-NC-SA 3.0 IGO — non-commercial, attributed
Top posts by karma under the Global Health & Development tag
License: User-generated content under site ToS; cited snippets + link back, attributed, non-commercial
Evidence summaries of what works in development (randomized evaluations)
License: All rights reserved — snippets + link back
Problem profiles relevant to human welfare (global health, growth, mental health, tobacco, migration)
License: Personal/non-commercial ToS — ingest for learning only (same caveat as ea_careers)
Prompts it uses
View prompts →raw JSONPost Quality / Writing Feedback [post_quality]
grading or critiquing the QUALITY of an EA/rationality post, essay, or argument, or asking for writing/epistemic feedback on a draft ('how good is this post', 'grade this', 'give me feedback on my EA Forum post', 'critique my argument', 'how do I write a better EA post'). A writing-feedback request, not a factual lookup.
retrieval: nonemodel: claude-opus-4-8Status: prompt-only
Sources it draws from
Open epistemic-quality rubrics for grading EA/rationality posts. No retrieval corpus — the rubric drives a grading/feedback prompt (adapted in spirit, not republished verbatim).
License: Linked, not republished; rubric concept reused with our own wording.
Prompts it uses
View prompts →raw JSONCredits: 80,000 Hours, Probably Good, Animal Advocacy Careers, Vegan Hacktivists (animalsupportbot), Open Paws / VEG3, the EA Forum and LessWrong communities, StampyAI, and the Alignment Research Dataset. The AI-safety engine's retrieval and prompt logic is adapted from StampyAI/stampy-chat (MIT License); its prompt text is reused verbatim under that license. The post-quality rubric is inspired by Winnow / moreorlesswrong (linked, not republished).