Zobrazeno 1 - 10
of 16 365
pro vyhledávání: '"P A Buck"'
Autor:
Greenblatt, Ryan, Denison, Carson, Wright, Benjamin, Roger, Fabien, MacDiarmid, Monte, Marks, Sam, Treutlein, Johannes, Belonax, Tim, Chen, Jack, Duvenaud, David, Khan, Akbir, Michael, Julian, Mindermann, Sören, Perez, Ethan, Petrini, Linda, Uesato, Jonathan, Kaplan, Jared, Shlegeris, Buck, Bowman, Samuel R., Hubinger, Evan
We present a demonstration of a large language model engaging in alignment faking: selectively complying with its training objective in training to prevent modification of its behavior out of training. First, we give Claude 3 Opus a system prompt sta
Externí odkaz:
http://arxiv.org/abs/2412.14093
Autor:
CONUS Collaboration, Garcia, E. Sanchez, Ackermann, N., Armbruster, S., Bonet, H., Buck, C., Fulber, K., Hakenmuller, J., Hempfling, J., Heusser, G., Hohmann, E., Lindner, M., Maneschg, W., Ni, K., Rank, M., Rink, T., Stalder, I., Strecker, H., Wink, R., Woenckhaus, J.
CONUS+ is an experiment aiming at detecting coherent elastic neutrino-nucleus scattering (CE$\nu$NS) of reactor antineutrinos on germanium nuclei in the fully coherent regime, continuing the CONUS physics program conducted at the Brokdorf nuclear pow
Externí odkaz:
http://arxiv.org/abs/2412.13707
Subversion Strategy Eval: Evaluating AI's stateless strategic capabilities against control protocols
AI control protocols are plans for usefully deploying AI systems in a way that is safe, even if the AI intends to subvert the protocol. Previous work evaluated protocols by subverting them with a human-AI red team, where an AI follows the human-writt
Externí odkaz:
http://arxiv.org/abs/2412.12480
We present RUBIX, a fully tested, well-documented, and modular Open Source tool developed in JAX, designed to forward model IFU cubes of galaxies from cosmological hydrodynamical simulations. The code automatically parallelizes computations across mu
Externí odkaz:
http://arxiv.org/abs/2412.08265
Radial metallicity gradients are fundamental to understanding galaxy formation and evolution. In our high-resolution simulation of a NIHAO-UHD Milky Way analogue, we analyze the linearity, scatter, spatial coherence, and age-related variations of met
Externí odkaz:
http://arxiv.org/abs/2412.01157
Autor:
Wen, Jiaxin, Hebbar, Vivek, Larson, Caleb, Bhatt, Aryan, Radhakrishnan, Ansh, Sharma, Mrinank, Sleight, Henry, Feng, Shi, He, He, Perez, Ethan, Shlegeris, Buck, Khan, Akbir
As large language models (LLMs) become increasingly capable, it is prudent to assess whether safety measures remain effective even if LLMs intentionally try to bypass them. Previous work introduced control evaluations, an adversarial framework for te
Externí odkaz:
http://arxiv.org/abs/2411.17693
Autor:
Viterbo, Giuseppe, Buck, Tobias
Galaxies evolve hierarchically through merging with lower-mass systems and the remnants of destroyed galaxies are a key indicator of the past assembly history of our Galaxy. However, accurately measuring the properties of the accreted galaxies and he
Externí odkaz:
http://arxiv.org/abs/2411.17269
Autor:
Ahrens, Florian, Geatches, Dawn, McCarroll, Niall, Buck, Justin, Lorenzo-Lopez, Alvaro, Keshtkar, Hossein, Fayyad, Nadine, Hassanloo, Hamidreza, Manika, Danae
The UK Research and Innovation Digital Research Infrastructure (DRI) needs to operate sustainably in the future, encompassing its use of energy and resources, and embedded computer hardware carbon emissions. Transition concepts towards less unsustain
Externí odkaz:
http://arxiv.org/abs/2411.14301
We present $\texttt{LAMINAR}$, a novel unsupervised machine learning pipeline designed to enhance the representation of structure within data via producing a more-informative distance metric. Analysis methods in the physical sciences often rely on st
Externí odkaz:
http://arxiv.org/abs/2411.08557
Autor:
Oliver, William H., Buck, Tobias
We demonstrate how the composition of two unsupervised clustering algorithms, $\texttt{AstroLink}$ and $\texttt{FuzzyCat}$, makes for a powerful tool when studying galaxy formation and evolution. $\texttt{AstroLink}$ is a general-purpose astrophysica
Externí odkaz:
http://arxiv.org/abs/2411.03229