I'm sorry that last sentence is nonsense. There are PIs who are only PIs because they couldn't get jobs as Nature editors, and there are some very editors there with less bias than academics. I won't defend the profits or many aspects of their process but it's just not true they're all failed PDs.

I have found it useful to have default specific instructions for each prompt to include the PMID for each citation and have it indicate the specific data in a paper that addressed a point, not just a summary of conclusions (etc). I always check the paper, but haven't found it to be quite accurate.

I view this like a new search tool - I still read these papers with my own judgment - but it is accelerating my literature discovery. For example, it helped me find a key paper that used an alternate name for a protein I had just missed (not in the databases and other people didn't use this name).

I spend a lot of time reading papers (PubMed searches, Google Scholar, searching bioRxiv, journal TOCs, citations in other papers). I compare the results in each case. My experience thus far is that the Claude PubMed MCP is finding things that I just wouldn't have come across otherwise.

4. A new publication in @natsmb.nature.com from ACS postdoctoral fellow Dr. Eric M. Smith and past ACS grantee Dr. @iaincheeseman.bsky.social at the #WhiteheadInstitute revealing two newly identified, unique subunits of the RNase MRP complex.

Read the paper here: lnkd.in/eTNkJhBW

This was not the first example of writing to my bosses or other leaders to express my candid views that they were making or were about to make a serious mistake (nor will it be the last).

As a leader, I have also appreciated it when others did the same to (for) me.

/fin