On this day: Sep 19

The authors admit they cannot rule out that the reduction was driven by evaluation awareness

An early case of merging reasoning and non-reasoning models into a single set of weights — a direction that later became the industry standard

Confirms that multiple lawsuits have been consolidated and are proceeding as MDL 3143

A local deployment tool expands into hybrid execution. The point at which the definition of running locally began to blur

Prepending 50–100 tokens of LLM-generated context to each chunk cut the retrieval failure rate by 35%; by 49% when combined with BM25, and by 67% with reranking added

All open models except the 3B and 72B were released under Apache 2.0, and the 14B and 32B sizes missing from the previous generation returned

The first voluntary lab framework that ties safety measures to capability thresholds