Alignment faking in large language models

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

First search for atmospheric millicharged particles with the LUX-ZEPLIN experiment

Autor: Aalbers, J., Akerib, D. S., Musalhi, A. K. Al, Alder, F., Amarasinghe, C. S., Ames, A., Anderson, T. J., Angelides, N., Araújo, H. M., Armstrong, J. E., Arthurs, M., Baker, A., Balashov, S., Bang, J., Bargemann, J. W., Barillier, E. E., Bauer, D., Beattie, K., Benson, T., Bhatti, A., Biekert, A., Biesiadzinski, T. P., Birch, H. J., Bishop, E., Blockinger, G. M., Boxer, B., Brew, C. A. J., Brás, P., Burdin, S., Buuck, M., Carmona-Benitez, M. C., Carter, M., Chawla, A., Chen, H., Cherwinka, J. J., Chin, Y. T., Chott, N. I., Converse, M. V., Coronel, R., Cottle, A., Cox, G., Curran, D., Dahl, C. E., Darlington, I., Dave, S., David, A., Delgaudio, J., Dey, S., de Viveiros, L., Di Felice, L., Ding, C., Dobson, J. E. Y., Druszkiewicz, E., Dubey, S., Eriksen, S. R., Fan, A., Fayer, S., Fearon, N. M., Fieldhouse, N., Fiorucci, S., Flaecher, H., Fraser, E. D., Fruth, T. M. A., Gaitskell, R. J., Geffre, A., Genovesi, J., Ghag, C., Ghosh, A., Gibbons, R., Gokhale, S., Green, J., van der Grinten, M. G. D., Haiston, J. J., Hall, C. R., Hall, T. J., Han, S., Hartigan-O'Connor, E., Haselschwardt, S. J., Hernandez, M. A., Hertel, S. A., Heuermann, G., Homenides, G. J., Horn, M., Huang, D. Q., Hunt, D., Jacquet, E., James, R. S., Johnson, J., Kaboth, A. C., Kamaha, A. C., K., Meghna K., Khaitan, D., Khazov, A., Khurana, I., Kim, J., Kim, Y. D., Kingston, J., Kirk, R., Kodroff, D., Korley, L., Korolkova, E. V., Kraus, H., Kravitz, S., Kreczko, L., Kudryavtsev, V. A., Lawes, C., Leonard, D. S., Lesko, K. T., Levy, C., Lin, J., Lindote, A., Lippincott, W. H., Lopes, M. I., Lorenzon, W., Lu, C., Luitz, S., Majewski, P. A., Manalaysay, A., Mannino, R. L., Maupin, C., McCarthy, M. E., McDowell, G., McKinsey, D. N., McLaughlin, J., McLaughlin, J. B., McMonigle, R., Mizrachi, E., Monte, A., Monzani, M. E., Mendoza, J. D. Morales, Morrison, E., Mount, B. J., Murdy, M., Murphy, A. St. J., Naylor, A., Nelson, H. N., Neves, F., Nguyen, A., O'Brien, C. L., Olcina, I., Oliver-Mallory, K. C., Orpwood, J., Oyulmaz, K. Y, Palladino, K. J., Palmer, J., Pannifer, N. J., Parveen, N., Patton, S. J., Penning, B., Pereira, G., Perry, E., Pershing, T., Piepke, A., Qie, Y., Reichenbacher, J., Rhyne, C. A., Richards, A., Riffard, Q., Rischbieter, G. R. C., Ritchey, E., Riyat, H. S., Rosero, R., Rushton, T., Rynders, D., Santone, D., Sazzad, A. B. M. R., Schnee, R. W., Sehr, G., Shafer, B., Shaw, S., Shutt, T., Silk, J. J., Silva, C., Sinev, G., Siniscalco, J., Smith, R., Solovov, V. N., Sorensen, P., Soria, J., Stancu, I., Stevens, A., Stifter, K., Suerfu, B., Sumner, T. J., Szydagis, M., Tiedt, D. R., Timalsina, M., Tong, Z., Tovey, D. R., Tranter, J., Trask, M., Tripathi, M., Usón, A., Vacheret, A., Vaitkus, A. C., Valentino, O., Velan, V., Wang, A., Wang, J. J., Wang, Y., Watson, J. R., Weeldreyer, L., Whitis, T. J., Wild, K., Williams, M., Wisniewski, W. J., Wolf, L., Wolfs, F. L. H., Woodford, S., Woodward, D., Wright, C. J., Xia, Q., Xu, J., Xu, Y., Yeh, M., Yeum, D., Zha, W., Zweig, E. A.

We report on a search for millicharged particles (mCPs) produced in cosmic ray proton atmospheric interactions using data collected during the first science run of the LUX-ZEPLIN experiment. The mCPs produced by two processes -- meson decay and proto

Externí odkaz: http://arxiv.org/abs/2412.04854

Stabilization of macroscopic dynamics by fine-grained disorder in many-species ecosystems

Autor: Martínez, Juan Giral, de Monte, Silvia, Barbier, Matthieu

Large systems are often coarse-grained in order to study their low-dimensional macroscopic dynamics, yet microscopic complexity can in principle disrupt these predictions in many ways. We first consider one form of fine-grained complexity, heterogene

Externí odkaz: http://arxiv.org/abs/2411.14969

Evidence for a shock-compressed magnetic field in the northwestern rim of Vela Jr. from X-ray polarimetry

Autor: Prokhorov, Dmitry A., Yang, Yi-Jung, Ferrazzoli, Riccardo, Vink, Jacco, Slane, Patrick, Costa, Enrico, Silvestri, Stefano, Zhou, Ping, Bucciantini, Niccolò, Di Marco, Alessandro, Weisskopf, Martin C., Baldini, Luca, Doroshenko, Victor, Ehlert, Steven R., Heyl, Jeremy, Kaaret, Philip, Kim, Dawoon E., Marin, Frédéric, Mizuno, Tsunefumi, Ng, Chi-Yung, Pesce-Rollins, Melissa, Sgrò, Carmelo, Soffitta, Paolo, Swartz, Douglas A., Tamagawa, Toru, Xie, Fei, Agudo, Iván, Antonelli, Lucio A., Bachetti, Matteo, Baumgartner, Wayne H., Bellazzini, Ronaldo, Bianchi, Stefano, Bongiorno, Stephen D., Bonino, Raffaella, Brez, Alessandro, Capitanio, Fiamma, Castellano, Simone, Cavazzuti, Elisabetta, Chen, Chien-Ting, Ciprini, Stefano, De Rosa, Alessandra, Del Monte, Ettore, Di Gesu, Laura, Di Lalla, Niccolò, Donnarumma, Immacolata, Dovčiak, Michal, Enoto, Teruaki, Evangelista, Yuri, Fabiani, Sergio, García, Javier A., Gunji, Shuichi, Iwakiri, Wataru, Jorstad, Svetlana G., Karas, Vladimir, Kislat, Fabian, Kitaguchi, Takao, Kolodziejczak, Jeffery J., Krawczynski, Henric, La Monaca, Fabio, Latronico, Luca, Liodakis, Ioannis, Maldera, Simone, Manfreda, Alberto, Marinucci, Andrea, Marscher, Alan P., Marshall, Herman L., Massaro, Francesco, Matt, Giorgio, Mitsuishi, Ikuyuki, Muleri, Fabio, Negro, Michela, O'Dell, Stephen L., Omodei, Nicola, Oppedisano, Chiara, Papitto, Alessandro, Pavlov, George G., Peirson, Abel L., Perri, Matteo, Petrucci, Pierre-Olivier, Pilia, Maura, Possenti, Andrea, Poutanen, Juri, Puccetti, Simonetta, Ramsey, Brian D., Rankin, John, Ratheesh, Ajay, Roberts, Oliver J., Romani, Roger W., Spandre, Gloria, Tavecchio, Fabrizio, Taverna, Roberto, Tawara, Yuzuru, Tennant, Allyn F., Thomas, Nicholas E., Tombesi, Francesco, Trois, Alessio, Tsygankov, Sergey S., Turolla, Roberto, Wu, Kinwah, Zane, Silvia

Synchrotron X-ray emission has been detected from nearly a dozen young supernova remnants (SNRs). X-rays of synchrotron origin exhibit linear polarization in a regular, non-randomly oriented magnetic field. The significant polarized X-ray emission fr

Externí odkaz: http://arxiv.org/abs/2410.20582

Dark Matter Search Results from 4.2 Tonne-Years of Exposure of the LUX-ZEPLIN (LZ) Experiment

Autor: Aalbers, J., Akerib, D. S., Musalhi, A. K. Al, Alder, F., Amarasinghe, C. S., Ames, A., Anderson, T. J., Angelides, N., Araújo, H. M., Armstrong, J. E., Arthurs, M., Baker, A., Balashov, S., Bang, J., Bargemann, J. W., Barillier, E. E., Bauer, D., Beattie, K., Benson, T., Bhatti, A., Biekert, A., Biesiadzinski, T. P., Birch, H. J., Bishop, E., Blockinger, G. M., Boxer, B., Brew, C. A. J., Brás, P., Burdin, S., Buuck, M., Carmona-Benitez, M. C., Carter, M., Chawla, A., Chen, H., Cherwinka, J. J., Chin, Y. T., Chott, N. I., Converse, M. V., Coronel, R., Cottle, A., Cox, G., Curran, D., Dahl, C. E., Darlington, I., Dave, S., David, A., Delgaudio, J., Dey, S., de Viveiros, L., Di Felice, L., Ding, C., Dobson, J. E. Y., Druszkiewicz, E., Dubey, S., Eriksen, S. R., Fan, A., Fayer, S., Fearon, N. M., Fieldhouse, N., Fiorucci, S., Flaecher, H., Fraser, E. D., Fruth, T. M. A., Gaitskell, R. J., Geffre, A., Genovesi, J., Ghag, C., Ghosh, A., Gibbons, R., Gokhale, S., Green, J., van der Grinten, M. G. D., Haiston, J. J., Hall, C. R., Hall, T. J., Han, S., Hartigan-O'Connor, E., Haselschwardt, S. J., Hernandez, M. A., Hertel, S. A., Heuermann, G., Homenides, G. J., Horn, M., Huang, D. Q., Hunt, D., Jacquet, E., James, R. S., Johnson, J., Kaboth, A. C., Kamaha, A. C., K., Meghna K., Khaitan, D., Khazov, A., Khurana, I., Kim, J., Kim, Y. D., Kingston, J., Kirk, R., Kodroff, D., Korley, L., Korolkova, E. V., Kraus, H., Kravitz, S., Kreczko, L., Kudryavtsev, V. A., Lawes, C., Leonard, D. S., Lesko, K. T., Levy, C., Lin, J., Lindote, A., Lippincott, W. H., Lopes, M. I., Lorenzon, W., Lu, C., Luitz, S., Majewski, P. A., Manalaysay, A., Mannino, R. L., Maupin, C., McCarthy, M. E., McDowell, G., McKinsey, D. N., McLaughlin, J., McLaughlin, J. B., McMonigle, R., Mizrachi, E., Monte, A., Monzani, M. E., Mendoza, J. D. Morales, Morrison, E., Mount, B. J., Murdy, M., Murphy, A. St. J., Naylor, A., Nelson, H. N., Neves, F., Nguyen, A., O'Brien, C. L., Olcina, I., Oliver-Mallory, K. C., Orpwood, J., Oyulmaz, K. Y, Palladino, K. J., Palmer, J., Pannifer, N. J., Parveen, N., Patton, S. J., Penning, B., Pereira, G., Perry, E., Pershing, T., Piepke, A., Qie, Y., Reichenbacher, J., Rhyne, C. A., Richards, A., Riffard, Q., Rischbieter, G. R. C., Ritchey, E., Riyat, H. S., Rosero, R., Rushton, T., Rynders, D., Santone, D., Sazzad, A. B. M. R., Schnee, R. W., Sehr, G., Shafer, B., Shaw, S., Shutt, T., Silk, J. J., Silva, C., Sinev, G., Siniscalco, J., Smith, R., Solovov, V. N., Sorensen, P., Soria, J., Stancu, I., Stevens, A., Stifter, K., Suerfu, B., Sumner, T. J., Szydagis, M., Tiedt, D. R., Timalsina, M., Tong, Z., Tovey, D. R., Tranter, J., Trask, M., Tripathi, M., Usón, A., Vacheret, A., Vaitkus, A. C., Valentino, O., Velan, V., Wang, A., Wang, J. J., Wang, Y., Watson, J. R., Weeldreyer, L., Whitis, T. J., Wild, K., Williams, M., Wisniewski, W. J., Wolf, L., Wolfs, F. L. H., Woodford, S., Woodward, D., Wright, C. J., Xia, Q., Xu, J., Xu, Y., Yeh, M., Yeum, D., Zha, W., Zweig, E. A.

We report results of a search for nuclear recoils induced by weakly interacting massive particle (WIMP) dark matter using the LUX-ZEPLIN (LZ) two-phase xenon time projection chamber. This analysis uses a total exposure of $4.2\pm0.1$ tonne-years from

Externí odkaz: http://arxiv.org/abs/2410.17036