A walkthrough of TrimSFT, which replaces uniform SFT loss with logit gap weighting for mathematical reasoning. Why trimming both extremes helps, and what the results across six models show.
A walk through correctness weighted multi-teacher distillation, lost label behavior, and a grounding audit that could not close, with attention to what the numbers do and do not support.
When should a diagnosis agent commit to a diagnosis and when should it step back, with selective error and autonomous coverage controlled together through the Cros stopping layer.
A reading of PRAGMA on how to evaluate assistants that live in long conversations, from the gap between factual recall and personal guidance to evidence alignment and the next memory design.
From one-to-one comfort to multi-party dialogue among couples and families, an editorial walkthrough of RESCUE-BENCH and its test of relationship aware support.
How relative representations of hidden states turn fine-tuning bias shift into a three minute Delta B audit that complements output benchmarks.
Beyond chat evals, a taxonomy-driven framework that automatically finds multi-step risks in agentic AI from the outside
Why ranking tools by similarity to the request leaves the final action stranded, and how a menu built as a prior over execution paths lifted online success on ToolBench.
A scale-up reading of PNNL CICERO records through active learning. The gap between 16 wells and 48 wells on recycled NdFeB, the SmCo purity yield tradeoff, and choosing batches by Bayes risk.
Walking through a paper that models entangled collective behavior as probability waves and tests it on Chinese intraday trading data, and asking why AGI might need entangled game modules, and where the limits sit.
A walkthrough of a human in the loop, multi-agent GeoAI framework that treats Arctic routing as a multi-criteria choice across operational, physical, ecological, and community concerns.
A reading of when in-context skill execution frays and when subagent delegation holds, through contracts, procedure, and coordination cost.