Can You Hide From a Natural Language Autoencoder?
TLDR: NLAs are a recent black box mech interp method for verbalizing model internals. I will be focusing on one of two components, the Activation Verbalizer…
Latest
Tree Transformers: A step towards generalizing the transformer architecture
After a billion architectures and a trillion variations, I finally found a transformer architecture that intrigued me. And this essay is step one towards the theory…
Agentic Frameworks: Or different ways to make LLM API calls
The agentic framework research has produced some very interesting results; from different topologies to different ways of using tool-calls, it has been one of the most…
Preventative Steering has advantages over Inoculation Prompting
This was work done by Aansh Samyani under the supervision of Ariana Azarbal, Arun Jose, Kei Nishimura-Gasparian and Daniel Tan as part of the SPAR Research…
How might outsiders make things go well?
I've been thinking about the role of outsiders over the next decade as we transition to ASI. By "outsiders", I mean the AI safety community outside…
Superintelligence vs. The Second Strike
Crosspost of my substack piece, covering quick thoughts on AI overcoming nuclear deterrence. TLDR: Nuclear deterrents likely only buy time to further invest in more resilient…