Gemini Co-Scientist在材料、生物和AI研究中表现出色，首次实验就成功制备3原子厚半导体，大幅降低AI研究中的数据造假率。
Gemini Co-Scientist与材料科学、生物学和计算机科学研究人员合作设计实验、预测生物行为、生长新材料并改进AI生成的研究。该模型首次尝试就提出了能生产3原子厚半导体的实验室配方。帮助预测了4项工程化大肠杆菌生长测量中的3项。独立设计了一个更安全的医疗AI系统，将AI论文中严重编造结果的比例从90%降至4%。
Learn how Gemini Co-Scientist worked with researchers across materials science, biology, and compute...
Learn how Gemini Co-Scientist worked with researchers across materials science, biology, and computer science to design experiments, predict biological behavior, grow new materials, and improve AI-generated research. Results: - Gemini proposed lab recipes that produced 3 atom-thin semiconductors on the first attempt - Helped predict 3 of 4 measurements of engineered E. coli growth - Independently designed an AI system that gave safer medical answers, and cut serious fabricated results in AI-written papers from 90% to 4%. Reading Recommendation: arxiv.org/html/2608.2670… and kudos to @SRSchmidgall and team! 💬 3 🔄 4 ❤️ 12 👀 1524 📊 6 ⚡