非エンジニア独立AIアライメント研究者。Human-Side AI Alignment、AI Workflow Integrity、model–user configurationを研究。記事は全てAI出力、検証と訂正と公開判断を担う工程自体が研究対象。単著論文Springer Nature『Discover Psychology』査読中。Cohere Labs Catalyst Grant採択。
Support user
About Supporter ServiceFollowing Organizations
No Organizations you are following
$ analyze @dosanko_tousan
posted articles:
- AI:75%
- LLM:28%
- RLHF:20%
- Claude:20%
- AIAlignment:14%
answered questions:
- AI:50%
- Heroku:25%
- テスト:25%
- 質問:25%
- テストケース:25%