[btrettel]

> First I used Claude Code to generate all the BibTex files for the PDFs

I think this has an unnecessary risk of hallucinated bibliographic data. For anyone doing something similar in the future, it would be more reliable to make a LLM generate a list of DOIs and have Zotero import the DOIs.

[bayindirh]

Using a non-deterministic machine on something which needs to be pretty accurate and precise looks like playing Russian roulette with one's academic integrity.

It's not my cup of vodka, to be sure.

[freehorse]

And moreover, something already mostly solved algorithmically. Eg in zotero you can drag and drop files and it generates a reference based on the metadata as long as that is enough (somebody mentions it is not possible in newer versions, I use the latest version and it works fine).

Each one can choose their own tools of course, but we often see llms shown as solutions to something presented as unsolvable before, while it already was pretty amenable to normal tools.

[bayindirh]

> but we often see llms shown as solutions to something presented as unsolvable before, while it already was pretty amenable to normal tools.

I see that as a symptom of being intellectually lazy, or not knowing the value in mastering a tool via deliberate use over time.

Once one invests the required time to use a tool properly, they can reap way more benefits from said tool when compared to jumping tools at minute's notice.

[NL807]

> And moreover, something already mostly solved algorithmically. Eg in zotero you can drag and drop files and it generates a reference based on the metadata as long as that is enough

As mentoned somewhere else, zotero's metadata retrieval is like 50% hit/miss in my experience - as in for the papers i've imported it was able to ID about half of them. An the quality of that data is not that great either. Lots of OCR errors, sparse bibtext fields, author names wrong, etc.

[bayindirh]

You can always get the missing data with a DOI, which is always present on the paper if it's recent enough.

I have tried filling some missing fields in my books list with help of an LLM, and none of the books were rare. I allowed it to search the internet and it hallucinated so bad that I nuked that version of the list and reverted all the changes.

It's more accurate with all the holes in the data.

[NL807]

> I allowed it to search the internet and it hallucinated so bad that I nuked that version of the list and reverted all the changes.

Really? This does not reflect my experience at all. I've been using the Beaver plugin and also Claude Code, and they have been spot on.

[bayindirh]

Probably due to language barriers. The books were not written in English and not authored by authors living in English speaking countries. Mostly were non-fiction, too. Mostly history and neighboring genres.

[NL807]

None of these issues are relevant to me.

I'm a graphics programmer, i keep a lot of journals for research, and i needed the least painless method to get them sorted. Even if, say 1% is misclassified or has wrong metadata, it will not impact what I do the least bit. And those can be corrected with ease.