Tidy up, Claude!
Nothing out of the ordinary there, but after years of procrastination at failing to update my publication webpage, following a wreckage by the default web composer on Ubuntu (and yours truly obviously!), I took advantage of the extra energy gained by my altitude night at the 5th station to ask Claude to update this page, with it replying it preferred to start from scratch (and from my LaTeX vita files). The only drawback is that many of the links introduced in the earlier version were not retrieved by the AI, despite my repeated request. On the plus side, trawling for missing entries and unpublished arXiv oldies but goldies, as well as adding mountain pictures (from the ‘Og!) proved much easier than the manual-by-keyboard approach. And I got an extra bonus in updating my LaTeX publication file and by creating the corresponding bibTeX file, all now available on my github page.
September 27, 2026 at 1:28 pm
Thanks to Claude (and GPT) I’ve now completed “my” proof of a CLT for the evidence in nested sampling under MCMC RW refreshment with fixed finite T MH steps (or attempted+successful steps, really). It required establishing preliminary results over two initial manuscript-sized pieces of exposition, with the final result in a third manuscript sized piece of exposition. I’m banking them on HAL now, but they are all apparently unpublishable as they cannot go beyond editorial rejection. It’s a strange new world.
September 27, 2026 at 2:04 pm
Sad. Rejected for being AI-based or as a general view that nested sampling is of limited appeal nowadays?
September 27, 2026 at 2:09 pm
It’s considered niche/lacked enough applied value [first rejection]; the result theorems were presented prior to all the definitions (a structural complaint that could be levied at almost any mathematical paper) and too burdensome for the reader to follow [second rejection]; too many papers being submitted for the journal to process (small specialist journal) [third rejection].