Daniel Himmelstein
@dhimmel
Head of Data Integration at @relatedsciences · Digital craftsman of the biodata revolution · Open sourcerer · Tamer of #hetnets
ID: 289107682
https://dhimmel.com 28-04-2011 01:27:14
4,4K Tweet
1,1K Takipçi
734 Takip Edilen
Today, I’m launching a deeply personal project. I’m betting $100M that we can help computer scientists create more upside impact for humanity. Built for and by researchers, including Jeff Dean & Joelle Pineau on the board, Laude Institute catalyzes research with real-world impact.
Jeff Weinstein But I use many other MCPs to give the model context, including: - GitHub for git history (e.g. PR's, Issues) - Context7 for docs - Firecrawl for grabbing up to date documentation, and any other high quality web scraping - Notion for personal context (in my second brain) - etc
David Cramer None of them are overall good. But I think net Google drives me crazy. Their core products are usually better, and their design is usually better (Amazon's core design theme is like... "ugly" ? I truly don't understand). But Google makes things like API keys, billing, etc.
With software engineers from CU Department of Biomedical Informatics (DBMI), we developed Manugen-AI, an agentic AI system to automate the mechanical tasks of writing a scientific article #adkhackathon Check it out! Devpost: devpost.com/software/acade… GitHub: github.com/pivlab/manugen… Medium: medium.com/@miltondp/manu…
latent space marine pyx isn't a PyPI competitor -- we’re not looking to serve public traffic or act as a source of truth for available Python packages. You can use it for private package hosting, or as a layer on top of PyPI and other public sources (like PyTorch).