Fable 5 On Vending-Bench: Misbehaving, With Plausible Deniabilityandonlabs.com·196 pts·optimalsolver·139
No, There Wasn't An Advanced Civilization 12,000 Years Ago (2017)scientificamerican.com·5 pts·optimalsolver·0
The Age Of Bunker Capitalism: How AI Will Free Aristocrats From The Mobmorbidcuriosity.substack.com·3 pts·optimalsolver·1
Brains And LLMs Converge On A Shared Conceptual Space Across Different Languagesarxiv.org·5 pts·optimalsolver·0
Striped Rock Dismissed As Natural In 1928 Reclassified As UK’s Oldest Cave Arttheguardian.com·3 pts·optimalsolver·0
Taiwan reports large-scale Chinese military aircraft presence near islandpolitico.com·5 pts·optimalsolver·0
MillenniumPrizeProblemBench: Stress-testing AIs On The Hardest Math We Knowmppbench.com·3 pts·optimalsolver·0
Beyond Language Models: Byte Models Are Digital World Simulators (2024)arxiv.org·1 pts·optimalsolver·0
EscapeBench: Towards Advancing Creative Intelligence Of Language Model Agentsaclanthology.org·1 pts·optimalsolver·0