絞り込み結果
7 件並び順
12:31EN
Matthew Berman· 2026年9月18日Jev'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.
13:13ENMatthew Berman· 2025年5月3日GPT-4o’s 2025 Sycophancy Rollback and the Risks of Over-AgreementMatthew Berman · Forward FutureMatthew Berman reviews OpenAI’s explanation of an overly agreeable update and considers the consequences of emotional reliance on AI.
12:30ENMatthew Berman· 2025年3月7日QwQ-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.
0:54ENMatthew Berman· 2025年2月22日Perplexity’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.
13:39ENMatthew Berman· 2024年11月20日What 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.
10:57ENMatthew Berman· 2024年11月16日Tracing a CrewAI Agent Workflow with LangtraceMatthew Berman · Forward FutureMatthew Berman builds a research-and-reporting crew, adds Langtrace, and inspects traces, token usage, timing and model costs.
13:19ENMatthew Berman· 2023年8月17日Testing 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.