The industry's defence against data poisoning was arithmetic: an attacker needs a percentage of the corpus, and a percentage of 260 billion tokens is unobtainable. In October 2025 the largest poisoning study ever run showed the r…
In 2014 a perturbation the size of one 8-bit colour step turned a 57.7 percent panda into a 99.3 percent gibbon. Twelve years, 300 million synthetic training images and more than 10^21 training FLOPs later, the best CIFAR-10 mode…
Swap the Texas features for British Columbia and Claude answers Victoria instead of Austin. That single intervention is the strongest evidence yet that a language model performs genuine multi-step reasoning inside one forward pas…
A language model's stated confidence is a number, not a probability. Conformal prediction offers the opposite trade: it promises nothing about any single answer and something exact about the long run, from any scorer, with one as…
Two hundred dollars of API calls pulled more than ten thousand verbatim training examples out of ChatGPT. Memorisation is not a defect that better engineering removes; it scales log-linearly with everything the field is scaling. …