@MaximeRivest: science made readable can now help you (and your agents) find experts in a field. For instance, in the below example I …
Summary
Science MadeReadable introduces an algorithmic expert-discovery feature that helps users and AI agents find leading researchers in a field, demonstrated by identifying Richard Sutton as a top Reinforcement Learning expert.
View Cached Full Text
Cached at: 10/17/26, 09:01 PM
science made readable can now help you (and your agents) find experts in a field.
For instance, in the below example I show how we algorithmically find that Richard Sutton is a leading expert in Reinforcement Learning https://t.co/u4XSFSRjkc
Similar Articles
@MaximeRivest: You can now have your agent search all of science, and read its abstracts, with this mcp: https://api.sciencemadereadab…
Science Made Readable released a free, no-auth MCP server that lets AI agents search ~200 million scientific papers by meaning or keywords, read abstracts, find similar papers, and traverse citations. It integrates with Claude Code, Codex, Claude, ChatGPT, Cursor, and VS Code, offering tools like search_papers and citation_walk at 30 calls per minute.
@MaximeRivest: I have embedded ALL of Science and made it available for free, so your agents can now do semantic search over the whole…
Maxime Rivest 发布了 ScienceMadeReadable：一个免费、开源的科学文献语义搜索 API，覆盖约 2 亿篇论文，可直接被 AI 代理调用，无需密钥或注册，嵌入由 LightOn 的 DenseOn 模型驱动。
@MaximeRivest: sciencemadereadable[.]com is almost science-fiction. 10 years ago, I could have never predicted that we could create su…
用户推荐 sciencemadereadable.com，称其为强大的科学文献探索与消化工具，认为它是为 AI 提供科学依据的最佳 RAG 后端，并介绍了新版 alpha 的 field maps 功能。
@MaximeRivest: ground your agents response in science. its: free, fast and open. this feels so obviously better that I am puzzled we d…
Maxime Rivest 推荐使用开放、免费且快速的科学检索方式来为 AI agent 的回答提供事实依据，认为这种做法明显更好且应更早普及。
@MaximeRivest: let's make science more accessible! its free and opensource! https://sciencemadereadable.com
Maxime Rivest launched Science, Made Readable, a free open-source site that rewrites open-access scientific papers into plain language for general audiences, using small fine-tuned Qwen 3.5 models (9B, 4B, 0.8B) that run on a home RTX 3090 and a rented H100. A judge model scored the 9B model at 7.8/10, slightly above GPT-6 Luna (7.5) but below Claude Opus (8.5), at about half a cent per paper.