絞り込み結果
39 件並び順
7:26EN
Matthew Berman· 2026年9月23日GPT-6 Sol and Luna: Price and Benchmark Trade-offsMatthew Berman · Forward FutureMatthew Berman examines OpenAI’s September 2026 launch, comparing API prices and reported agent benchmarks with larger models.
1:05:23ENMatthew Berman· 2026年9月3日Matthew Berman Tests GPT-6 Astra: Benchmarks, Browser Agents and GamesMatthew Berman · Forward FutureAn early-access tour compares model benchmarks and pricing with practical browser workflows, presentations and a wide range of generated games.
15:37ENMatthew Berman· 2026年8月4日Matthew Berman on Qwen3.8-Max, AI Costs and Open-Weight CompetitionMatthew Berman · Forward FutureA 2026 review of reported benchmark results and research demonstrations leads to questions about deployment economics and geopolitical dependence.
52:29ENMatthew Berman· 2026年7月24日Claude Opus 5: Benchmarks, Cost per Task, and Early ImpressionsMatthew Berman · Forward FutureMatthew Berman reacts to the model launch, examines reported benchmark and pricing data, and explains why the cost of completing a task matters more than token price alone.
1:42:41ENMatthew Berman· 2026年5月1日Testing AI Reasoning, App Store Lookalikes and the Debate Over AnthropicMatthew Berman · Forward FutureIn a May 2026 livestream, Matthew Berman tests a car-wash prompt, discusses AI subscription limits and considers reported employee monitoring for model training.
18:07ENMatthew Berman· 2026年4月16日Claude Opus 4.7: Benchmarks, Cyber Safeguards and Open QuestionsMatthew Berman · Forward FutureMatthew Berman compares Anthropic’s April 2026 Opus release with the limited Mythos Preview and examines its system card.
9:47ENMatthew Berman· 2026年4月3日Gemma 4: Smaller Open-Weight Models for Local AIMatthew Berman · Forward FutureMatthew Berman reviews Google’s model sizes, multimodal features and reported benchmarks, with an eye toward local agents.
0:37ENMatthew Berman· 2026年2月20日Gemini 3.1 Pro: A Look at the Reported Benchmark ScoresMatthew Berman · Forward FutureMatthew Berman reacts to a Gemini 3.1 Pro comparison and highlights results on Humanity’s Last Exam.
11:49ENMatthew Berman· 2026年2月17日Matthew Berman Reviews Claude Sonnet 4.6: Benchmarks, Computer Use and SafetyMatthew Berman · Forward FutureA launch-day overview examines Anthropic’s reported knowledge-work and agent results, along with prompt-injection and capability evaluations.
1:11ENMatthew Berman· 2025年11月18日Gemini 3's Launch: Benchmarks, Antigravity, and AgentsMatthew Berman · Forward FutureMatthew Berman summarizes Google's November 2025 model launch and its developer and assistant demos.
13:53ENMatthew Berman· 2025年10月10日Tiny Recursive Models and the Limits of Puzzle Benchmark ComparisonsMatthew Berman · Forward FutureMatthew Berman examines a small recursive network that reports strong ARC and Sudoku results, and what its experimental setup means.
8:47ENMatthew Berman· 2025年9月16日Why Identical LLM Prompts Can Produce Different Answers at Temperature ZeroMatthew Berman · Forward FutureMatthew Berman explains Thinking Machines Lab’s work on batch-invariant inference and what its reproducibility experiment actually showed.
15:13ENMatthew Berman· 2025年5月10日Absolute 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.
0:34ENMatthew Berman· 2025年5月1日DeepSeek-Prover-V2 and Its Formal Math ResultsMatthew Berman · Forward FutureMatthew Berman highlights DeepSeek’s reported theorem-proving results on miniF2F, PutnamBench and formalized AIME problems.
14:04ENMatthew Berman· 2025年4月29日Qwen3: Open Weights, Adjustable Reasoning and Tool UseMatthew Berman · Forward FutureMatthew Berman reviews the April 2025 Qwen3 family, its benchmark claims, training pipeline and local demonstration.
15:15ENMatthew Berman· 2025年4月19日Early Reactions to OpenAI o3 and o4-mini: Tool Use, Math and MistakesMatthew Berman · Forward FutureMatthew Berman reviews 2025 demos and benchmark reports, from location guessing and coding to simple failures that challenge the hype.
7:33ENMatthew Berman· 2025年4月4日Ace Computer-Use Agent: Fast Desktop and Browser DemonstrationsMatthew Berman · Forward FutureMatthew Berman reviews General Agents’ examples and reported click accuracy and latency, while noting he has not yet tested Ace himself.
11:31ENMatthew Berman· 2025年3月29日AI News in March 2025: GPT-4o, Gemini, DeepSeek and MCPMatthew Berman · Forward FutureMatthew Berman reviews model updates, the ARC-AGI-2 benchmark, image generators and early adoption of Model Context Protocol.
8:52ENMatthew Berman· 2025年1月21日Industry Reactions to DeepSeek R1’s 2025 ReleaseMatthew Berman · Forward FutureMatthew Berman reviews early reactions to DeepSeek R1, from open-weight reasoning models and local hardware to benchmark results and API pricing.
21:02ENMatthew Berman· 2024年12月24日Reactions to OpenAI’s 2024 o3 Preview: Benchmarks, Cost and LimitsMatthew Berman · Forward FutureMatthew Berman surveys the responses to the o3 preview, from mathematical benchmarks to debates about AGI, compute and reliability.
9:00ENMatthew Berman· 2024年12月20日Best-of-N Jailbreaking: What Repeated Prompt Variations Revealed in 2024Matthew Berman · Forward FutureMatthew Berman reviews research on how repeated input variations can expose safety failures in text, vision and audio models.
26:43ENMatthew Berman· 2024年10月10日Testing OpenAI o1 on Planning, Rules and Spatial ReasoningMatthew Berman · Forward FutureMatthew Berman reviews a 2024 pilot study comparing o1-preview, o1-mini and GPT-4 on six planning domains.
18:09ENMatthew Berman· 2024年9月17日AI News in September 2024: Copilot, NotebookLM, o1 and World ModelsMatthew Berman · Forward FutureMatthew Berman reviews a week of AI announcements, from workplace assistants and audio overviews to benchmark results, generative video and spatial AI.
21:21ENMatthew Berman· 2024年9月12日OpenAI o1’s 2024 Launch: Reasoning Benchmarks and Early TestsMatthew Berman · Forward FutureMatthew Berman reviews o1-preview and o1-mini, OpenAI’s reported evaluations, and his own early coding experiments.もっと見る39 件中 24 件を表示