So I have opinions about the Google engineer who thinks that his chatbot is sentient, because of course I have. One of the things about people who work with computers is that we have opinions about AI which are not necessarily grounded in anything real about either intelligence or computers …

VQGAN+CLIP is a method for generating images from text phrases using a GAN image generator and the CLIP image recogition system: I tried feeding it the first few numbered paragraphs from Wittgenstein's Tractatus Logico-Philosophicus, which I was thinking about because I recently watched Derek Jarman's excellent film about the …

A fun quality of Mastodon - a social communication platform I hang out on a bit too much - is that individual instantiations can fork its basic form and add odd twists which suit just that community. Oulipo.social notoriously bans that fifth Latin glyph which is most common in many linguistic …

g CINA CONTENC MI CINE SI CENTENI SEE CONDENN DE CRE SU DE QUAENT ME CONNE CUNTUR DEACLETICE (FIUD SEE DED SEE SER SER SER SEENNN SER SER SEENN SER SER SEENDENNENCEN (_DER SER K of my own striking the more than the spirit of the morning of the Professor …

I trained a recurrent neural net with the same parameters as the most recent version of GLOSSATORY on the Gutenberg e-text of the 1811 edition of Francis Grose's Dictionary of the Vulgar Tongue.

The output was even better than I expected. The following excerpts were taken at increasing temperatures (the …

This is the output of the neuralgae algorithm, which visualises a neural net's idea of some image classes and then classifies the result and repeats, looped into a GIF, and it's exactly the sort of fluid morphing between surreal forms I've been trying to get for two years.

Here are all 1000 classes in the ImageNet challenge, rendered with the Visual Geometry Group's 19-layer neural net, using the same deepdraw technique I used for the thousand faces of CaffeNet. These ones are rendered on random grayscale noise, not my face.

This is the net which the neuralgae Twitter …

Glossatory is a recurrent neural net trained on all of the definitions in the lexical database WordNet. I recently retrained it on a GPU, increasing the number of hidden units to 512 and the layers from 2 to 3. The results are now a lot more grammatical, and there's a …

I was tinkering around trying to get Justin Johnson's neural-style implementation working on the HPC - this is an algorithm which uses a deep learning image recognition net to extract low-level style features from one image and use them to render the large-scale contours of another. This technique has been commercialised …

I've been playing around with the neural net behind @GLOSSATORY as part of this year's NaNoGenMo: here's a preview.

ABDOMINABLE: a small wall of muskeled for swinging in star or supported in the northwestern central England on the Russian Canamaaceae

ABILITY: the quality of being laws and property

ABNORAL: a …