A personalized classifier needs several hundred labeled examples before its predictions become reliable.

Added to korrents 20 Sept 2026 · How quotes work · Something wrong? Tell us

Shared subject first, then similar wording. They may agree or disagree.

• Learned approximations of slow simulators change what science is possible, by turning a six-month screening run into something you do over lunch. JDJeff Dean30 Jul 2026
• Full fine-tuning of large language models has become too costly, making parameter-efficient fine-tuning methods necessary. SRSebastian Ruder5 Dec 2023
• Using a neural network is likely to become easier than designing a custom-tuned prediction algorithm for many tasks. NENelson Elhage4 Jul 2025
• When pre-training data is limited, it is better to train a smaller model for multiple epochs than to train a larger model on unique data once. SRSebastian Ruder1 Dec 2023
• What sits in a model's context is far clearer to it than its training data, which is trillions of tokens stirred into a soup of parameters. JDJeff Dean30 Jul 2026

See this claim on the map