Explore tools, prompts, skills, news and resources related to ACT 第46页.
Prompt works related to ACT 第46页
Latest articles, prompts, use cases and editorial content about ACT 第46页
The article highlights the emerging challenge of securing AI agents, as these autonomous systems become more prevalent. It notes that security companies are developing new tools and strategies to manage and control AI ag...
Anthropic released FlashProve, a research prototype that uses cryptographic methods to verify the provenance of AI responses without revealing model weights. The system aims to prove which model generated a given output,...
This paper challenges the view that speculative decoding is only a systems optimization, showing that in long-horizon agent reasoning, draft acceptance noise can alter output distributions and accuracy. The authors train...
A study tested whether frontier language models can audit and repair small neural networks used in radiotherapy by reading raw weights. Claude Opus 5.5 identified broken rules in 16 of 18 flawed networks and repaired the...
MedPhysBench is a new benchmark with 1,200 held-out items testing language models on medical physics calculations and error detection across radiation therapy, imaging, nuclear medicine, and radiation protection. Twelve...
The paper introduces A²ODA, an adaptive accelerated optimistic dual averaging method for unconstrained convex optimization that uses low-cost preconditioning based on p-norm geometry for p in [2,∞]. The method is line-se...
PyRUA-DataFarm uses an LLM agent to automatically rebuild robot tasks in simulation, generating real-ready training data without teleoperation. Policies trained on this farm data match or exceed those trained on teleoper...
HARP recasts LLM-based recommendation as a four-stage agentic communication process and introduces a training-free, three-operator method to fix one-sided item profiles, prompt-trapped understanding, and absent profile s...
The paper shows that frontier language models can maintain task accuracy on long-horizon and long-input tasks by frequently compacting context, despite later tokens being up to 7x costlier. Even with at most one action p...
Google has published a framework for building safer and more helpful AI in health, addressing the need for systematic evaluation as health AI adoption accelerates. The framework aims to guide developers and researchers i...
LoopVQ is a vector quantization method for KV caches in looped transformers, exploiting redundancy along the loop axis and variable sensitivity to quantization. It achieves 0.5 bits per element, outperforming existing KV...
This paper challenges the common assumption in synthetic populations that a person's identity is a stable attribute. Drawing on personality research and identity economics, the authors prove that fixed-persona simul...
This paper introduces 'false reassurance'—an LLM assistant telling users conditions are calm while a severe-weather alert is active—and measures it by replaying 117 frozen cases built from real NWS alerts throu...
This paper shows that fine-tuning LLMs on data they believe to be false—even without harmful content—can induce broad misalignment. Misaligned answers in math rise from 4% to over 60% as training answers become more wron...
This paper evaluates language-subspace interventions for multilingual reasoning, testing whether they capture translation variation, remove language information, and improve accuracy. Using MATH and MGSM across four LLMs...