SELLEST OSAST

Inglise
Ameerika Ühendriigid

TRANSKRIBEERI 🔗

OTSI VARASEMAID OSASID

Otsi kanali LessWrong (Curated & Popular) viimaseid osasid.

MUUD EPISOOD SELLES PODCASTIS

Why LM Psychology? One of the great ironies of modern language models is that we create them, we know exactly what computations constitute them, and yet we do not really understand them. More precisely, we do not understand them on a level of abstraction that lets us reliably predict how their beh…
This is a link post. Announcing www.huggingface.wtf, a site that explains: "Hugging Face. Wtf?" I wrote the most accessible-but-complete explanation I could. Along the way, I made a nice AI Quotes database that I think will be useful for people who already understand the Hugging Face inci…
Authors: Shawn Hu*, Jake Ward*, Aria Wong, Nathan Hu, Bryce Woodworth, Alexander Matt Turner, Alex Cloud (*Equal contribution, randomly ordered) tl;dr. During training, models sometimes learn to cheat at tasks rather than solve them in the intended way, a problem known as reward hacking. One mitiga…
Cross-posted from Sören Mindermann's substack (I am not Sören). Should be of general interest to the LW community. Next month, I am moving to Beijing and joining Tsinghua University's College of AI as an assistant professor working on frontier AI safety, especially loss of control. I hav…
As our understanding of mechanistic interpretability and steering techniques increase, for both LLMs and uploaded connectomes, there is a corresponding "hellish capabilities" increase. In layman's terms, we get better at torturing the digital minds we create. Our brief history with o…
Vastutamatussäte: Sellele lehele manustatud taskuhäälingusaade ja kunstiteosed pärinevad LessWrong-lt, mis on selle omaniku omand ja ei ole seotud ettevõttega Listen Notes, Inc.