Comment by raphman

6 days ago

tl;dr: Use this if you don't like doing science or doing things well. It hallucinates references.

Seems to be based on https://github.com/swaruplab/operon as evidenced by the authorization dialog and https://x.com/testingcatalog/status/2037684573161783373 .

Mostly targeted at life sciences - e.g. integration for FDA, PubMed, genomics databases but no ACM / IEEE as far as I can tell.

Edit: arXiv search seems to be supported - but not Google Scholar etc. So, this tool is of little use for most researchers outside life sciences.

Edit 2: Quick walkthrough: the AppImage starts a browser window with an onboarding wizard and a chat interface. It suggests a few things one might do at the start of a research project - e.g. do a quick literature review. When I chose that option, wrote Python scripts that used MCP calls to do arXiv searches. Stayed seemingly stuck there for a few minutes not returning anything. Then:

> The free-text search returned too much noise

Claude decided to choose a certain paper as a starting point for further research. Shortly afterwards:

> That DOI resolved to the wrong paper. Let me find the correct anchor papers by title/author search directly.

Then it meandered a few more minutes doing research and creating a citation graph (that it did not show to me).

> I have a complete picture. Let me verify the key DOIs resolve and then write the review.

Then:

> The lint flags em-dash overuse. Let me reduce them, then save.

Then: a nice but verbose literature overview of my chosen topic

<blink>BUT it includes at least one hallucinated reference!</blink>

P.S.: What does this mean?

  [reviewer] verifier_mode=default-on downgraded to off: pro subscription tier, autoReviewer withheld (frame=f2a81cb2)

6 comments

raphman

Reply
Retr0id  6 days ago

> The lint flags em-dash overuse

An explicit text desloppification pass (i.e. LLM-use obfuscation) seems like outright scientific fraud.

  • sansseriff  6 days ago

    It sure is! But ironically, because of the intention behind the obfuscation. Not the fact that AI was used in a research paper.

    I have no issues with AI use in science. If claude can explain my research better than me, then have at it. But I do NOT want to read a passage thinking it was written by a human when it wasn't. Science has no idea yet how such disclosures should work yet. What should be done by humans as a matter of principle, and what can't be or should not be done by humans.

    • epihelix  6 days ago

      The thing that really scared me about the landing site for Claude Science was this promotional image of the software in action:

      https://cdn.prod.website-files.com/6889473510b50328dbb70ae6/...

      Very depressing. MDPI journals will be saturated with these slop papers (if they're not already). It shocks me that Anthropic thought that this was a good thing, and says a lot about their research integrity (or lack thereof).

      > Science has no idea yet how such disclosures should work yet.

      Technically, most journals have a policy that LLM use should be acknowledged, but I agree we're still very much in the weeds about this right now. Much firmer guidelines should have been established years ago.

      (I also have no issues with LLM usage in research either, btw -- I use LLMs to fact-check / proofread / discuss / sanity-check my conceptual work, to background myself in other research, and to refactor and assist with analytical coding. They can be a game-changer for medical research, when used rationally and sensibly.)

    • dleeftink  6 days ago

      Some authors may even choose to leave syntactical errors as a tell for those self-authored passages; long-term, some interesting language drifts may come of it.