Stop Paying Your GPUs to Wait: Handing a Shared Box Back to the LLM in Minutes, Not 40 watchmeship • about 1 hour ago • 2
Turkish Hate Map (TuHaMa): Decoding the Cultural Quirks of Local Hate Speech turkish-nlp-suite • about 6 hours ago • 1
Uncensored models in agent loops: they answer everything, then loop or crash OpenUncensored • about 18 hours ago • 1
AI Model Hacking Hackathon: Safe AI Is Built by Everyone Who Tries to Break It FINAL-Bench • about 19 hours ago • 9
TartanGround: Six Robot Trajectories Across Six Environments, Loaded in FiftyOne harpreetsahota • about 23 hours ago • 1
Long Workflows, Small Contexts: 1,140 Local Model Calls Across Two Android Phones Alechko375 • 1 day ago • 2
XL-Refusal-Bridge: closing Tiny Aya's cross-lingual safety gap with a 33 KB adapter and no retraining davidquicast • 1 day ago • 1
Efficient Healer: a Tiny Aya database agent that repairs itself, round after round Purusharth • 1 day ago