#ensembling

The latest AI and developer news about #ensembling, with the original source and a short summary.

New scaling law prescribes quadrillion-parameter models for data-constrained LLM training

Baron et al. propose a scaling law that recommends ~7,000x more parameters than Chinchilla at 10^29 FLOPs, using hyperparameter transfer and ensembling to maintain loss reduction on fixed datasets.

·2026.11.03 23:00

Combining Weak Agents to Build a State-of-the-Art Deep Researcher

Instead of developing a new agent, merging the outputs of existing agents achieved the #1 spot on the Deep Research benchmark.

·1·2026.06.24 22:00