The Grok bot scan for hallucinated papers turned up several medical related papers today.
The Hall of hallucinations is now up to 157 papers.
I have the pipeline to find articles with hallucinated references down to the point where I am typically adding 2 or 3 articles to the hall of hallucination per day.
Here is one of the most recent additions.
$1 to review a paper! (OA charges are over $3800 for this journal)
You would think having multiple authors would prevent AI hallucinations, but I suspect the opposite may be the case
Also includes multiple folks from legit institutions (Uni of Washington, Columbia, Scripps Ocean Institute)
I wrote a book on AI engineering with the LLM APIs. I am begging you to read and understand it, because I need to hire more people with these skills!
crimede-coder.com/store/
One of the recent AI hallucinations I have come across is DOIs that point to totally different papers. I honestly don't know if these are author or editor induced.
If editor, it just means the journals are publishing papers that *they know* have a pretty gross amount of errors.
Hall of Hallucinations is up to 142 papers. Sign up, contribute a few of your own.
veruscite.com/hallucinations
New VerusCite blog post, my false positive rate is under 1% in my benchmark and likely outside of it.
I go through my Grok Bot scan yesterday to show an out of sample example. Of the 200+ citations scanned, my tool flagged 10. Only one is potentially a false positive.
Damien Charlotin's AI hallucination tracker in court cases has flattened. Possibly via not collecting as many, but also just as likely the models are getting better. (I am skeptical individuals are using them more effectively!)













