Explore tools, prompts, skills, news and resources related to AI 第58页.
Prompt works related to AI 第58页
Latest articles, prompts, use cases and editorial content about AI 第58页
Researchers identify a failure mode called CLADE, where retrieval-augmented language models answer from passages that mention only a broader category rather than the specific answer required. On biomedical questions from...
Researchers analyzed 1,260,967 blind votes cast on Chatbot Arena between May 2023 and August 2024, restricting the analysis to pairs of models whose versions were fixed. For the same unchanged pair, the share of votes sa...
This arXiv paper analyzes why higher-order discretization does not generally improve the convergence order of stochastic diffusion samplers, establishing matching upper and worst-case lower bounds. It introduces forward-...
The paper proposes Falsification-Gated Self-Evolution (FGSE), a verifier-grounded framework for deciding when lessons derived from an agent episode should become persistent memory. FGSE represents each candidate lesson a...
Google DeepMind researchers used agentic AI and a framework called AlphaProof Code to formally verify key cryptographic guarantees of the Signal protocol in a four-week proof-of-concept. The work provides further indepen...
Anthropic claims its in-house model, Mythos, ported Claude to AMD GPUs in three days with almost no human intervention. The company says Claude now runs on four chip families, aiming to cut costs and reduce vendor depend...
The paper identifies memory-induced degradation in LLM agents, where retrieved lessons cause failures on tasks the agent could otherwise solve. It introduces WikiTrace, an evidence-linked memory system that stores each l...
Researchers propose ReFrain (Regression-Free Abstention), which combines a linear probe on first-token logits, threshold calibration on held-out image clusters, and a deterministic veto that replaces rejected outputs wit...
LM-SimBench is a unified framework, profiling dataset, and benchmark for evaluating LLM training simulators. It decomposes simulation into functional stages from model compilation to schedule-level aggregation and connec...
A review of 54 recent evaluation studies of ambient AI scribes in healthcare identifies ten evaluation dimensions and 40 distinct metrics, operationalized in 96 different ways. Thirty-five of those operationalizations, 3...