Ergebnisse
6 ArtikelSortieren
15:13EN
Matthew Berman· 10. Mai 2025Absolute Zero: Training a Reasoner on Self-Generated Coding TasksMatthew Berman · Forward FutureMatthew Berman examines a 2025 paper in which a pretrained language model proposes and solves code tasks using verifiable feedback.
15:42ENMatthew Berman· 28. Aug. 2024Strawberry and Orion: What Was Reported About OpenAI’s Next Models in 2024Matthew Berman · Forward FutureMatthew Berman examines reports about a reasoning project, synthetic data and a future flagship model. Later releases clarify some of the story, while many original claims remain attributed to unnamed sources.
15:50ENMatthew Berman· 23. Juli 2024Llama 3.1: Meta’s 405B Model and the Open-Weight EcosystemMatthew Berman · Forward FutureMatthew Berman reviews Meta’s July 2024 release, the smaller models, reported benchmarks, synthetic data and the proposed Llama Stack.
19:37ENMatthew Berman· 13. Dez. 2023How Rephrased Test Data Inflated a 13B Model’s Benchmark ScoresMatthew Berman · Forward FutureMatthew Berman examines a 2023 experiment showing how reworded benchmark questions can evade simple contamination checks and inflate model scores.
18:29ENMatthew Berman· 1. Dez. 2023OpenAI's 2023 Leadership Crisis, Q* Speculation and Synthetic DataMatthew Berman, Andrew Ross Sorkin, Elon Musk · Forward FutureMatthew Berman connects Sam Altman's return, an Elon Musk interview and Nathan Lambert's discussion of synthetic training data, separating reported events from his own theories.
19:38ENMatthew Berman· 9. Juni 2023Orca: Teaching a Smaller Model with GPT-4 ExplanationsMatthew Berman · Forward FutureMatthew Berman reviews Microsoft Research’s 2023 Orca paper and its approach to training a 13-billion-parameter model on detailed teacher responses.