When the Claude Mythos system card was released, I initially felt like we had entered a late stage of AI safety, where the number of parties that can make a real impact shrinks down to the handful of labs at the frontier, a few companies too critical to exclude from...
Or, did a chief scientist of an AI assistant startup conclusively show that GPT-5.5 has 9.7T parameters?[1] Introduction Recently, a paper was circulated on Twitter claiming to have reverse engineered the parameter count of many frontier closed-source models including the newer GPT-5.5 (9.7T parameters) and Claude Opus 4.6 (5.3T parameters)...
I recently explored an interesting thought experiment about the Culture while talking with Max Harms. Specifically Max argued that the Culture is far from a perfect utopia, while I felt that it was way better than almost anything else I could think of. One of the key cruxes in the...
Code can be found here. Thanks to Paul Colognese and Narmeen Oozeer, and Mickey Beurskens for collaboration on this work, and with Jonathan Shock for so much support and feedback. TLDR: We investigated how a maze-solving RL agent (not a transformer model) internally represents and switches between multiple sequential goals....
The mandate had been given by God that morning, and Nathanael and Amon had arrived in the nascent realm to shape His will. The task was simple: creation, in all its perfection. As divine as this instruction was, it did demand a great deal of creativity on the part of...
Epistemic status: Fairly confident in the framework, uncertain about object-level claims. Keen to receive pushback on the thought experiments. TL;DR: I argue that Whole Brain Emulations (WBEs) would clearly have moral patienthood, and that the relevant features are computational, not biological. Recent Mechanistic Interpretability (MI) work shows Large Language Models...
TL:DR Join a global cohort of ambitious researchers in Cape Town for a fully-funded cooperative AI research fellowship! Spend 3 months from January to April 2026 researching with world-class mentors from Google DeepMind, Oxford, MIT, CMU, and Toronto, among others. Join us for an online information session on September 18th...