I am looking for people who want to be supervised by me to write a mech interp paper. Apply here now ! Due Aug 29| Neel Nanda
Again, most of my spare time was dedicated to AI learning and experimenting:| dx13.co.uk
Interpretability provides access to AI systems' internal mechanisms, offering a window into how models process information and make decisions.| www.alignmentforum.org
This class is substantially based on this paper, this paper, this post and this post.Interactive bit:Please complete the following sequences with the highest...| www.gleech.org
As a supporter, I would love not to feel this way| www.thealgorithmicbridge.com
We describe an approach to tracing the “step-by-step” computation involved when a model responds to a single prompt.| Transformer Circuits
A response to Apple's viral study| www.thealgorithmicbridge.com
Anthropic's latest interpretability research: a new microscope to understand Claude's internal mechanisms| www.anthropic.com
Scaling reinforcement learning, tracing circuits, and the path to fully autonomous agents| www.dwarkesh.com
.jpg)
In the decade that I have been working on AI, I’ve watched it grow from a tiny academic field to arguably the most important economic and geopolitical issue in the world. In all that time, perhaps the most important lesson I’ve learned is this: the progress of the underlying technology is inexorable, driven by forces too powerful to stop, but the way in which it happens—the order in which things are built, the applications we choose, and the details of how it is rolled out to society...| www.darioamodei.com
Thus concludes chapter 4 of| dx13.co.uk
LLMs are braindead, our failed quest for intelligence| www.mindprison.cc
This essay is about the nature and character of algorithms that would lead to artificial super intelligence (ASI) primarily through recursive self improvement. It is a window into my intuitions at the current time. current bottlenecks OpenAI just recently released a long form podcast talking about primarily pre-training gpt4.5 and the various lessons that it taught them. I never thought I would see such transparency from OpenAI and it serves as valuable insight into the current state of ML re...| Hugo ʕ•ᴥ•ʔ Bear
Interesting & joyful things from the previous week| registerspill.thorstenball.com
Hier ist der 24. Blog-Beitrag „Menschen, Daten, Sensationen – Rudis Bericht aus dem Datenzirkus, ergänzt um Franks Zugabe (KW 13&14/2025)“ – Die DVD-Edition.| Deutsche Vereinigung für Datenschutz e.V.