Kürzlich aktualisierte Kanäle

Wählen, um nur diesen Kanal zu sehenAlle Kanäle →
Matthew Bermangestern +226AI Engineergestern +6Theo - t3․gggestern +9The Buildersgestern +1a16zgestern +2硅谷101gestern +1SemiAnalysisgestern +1Chris WilliamsongesternCheeky PintgesternInvest Like The Bestgestern

Ergebnisse

5 Artikel
Sortieren
KanalMatthew BermanThemaEvals & ObservabilityPersonMatthew Berman
5 Folien12:31EN
Matthew Berman· 18. Sept. 2026Jev's Fast Decisions: Demos, Tradeoffs and Reliability ClaimsMatthew Berman · Forward FutureMatthew Berman explores a decision-oriented AI model through routing, simulated worlds, chess and game-control examples.AI agentsAI cost & performanceEvals & Observability+1
4 Folien12:30EN
Matthew Berman· 7. März 2025QwQ-32B: A Smaller Reasoning Model and Its TradeoffsMatthew Berman · Forward FutureMatthew Berman examines Qwen’s reinforcement-learning recipe, tests a coding task, and compares benchmark scores and hardware requirements with DeepSeek-R1.Reasoning & test-time computeReinforcement LearningOpen Source+2
2 Folien0:54EN
Matthew Berman· 22. Feb. 2025Perplexity’s R1 1776: A Comparison of Responses and BenchmarksMatthew Berman · Forward FutureMatthew Berman examines a post-trained DeepSeek-R1 variant and Perplexity’s tests of responses on sensitive topics.Foundation ModelsEvals & ObservabilityAI Alignment
6 Folien13:39EN
Matthew Berman· 20. Nov. 2024What Interview-Based AI Agents Can Predict About PeopleMatthew Berman · Forward FutureMatthew Berman reviews a 2024 study using interviews with 1,052 participants to simulate survey answers and decisions.Multi-agent systemsSynthetic dataPsychology+2
5 Folien13:19EN
Matthew Berman· 17. Aug. 2023Testing WizardLM 70B: Setup, Coding and Reasoning ResultsMatthew Berman · Forward FutureMatthew Berman runs a quantized Llama 2-based model through an informal collection of coding, writing, arithmetic and logic prompts.Foundation ModelsFine-TuningLocal inference+2