Résultats
48 articlesTrier
25:50EN
Matthew Berman· 24 oct. 2026Kimi K3.1 Pro Tested: Strong 3D Demos, Uneven Results and Competitive PricingMatthew Berman · Forward FutureMatthew Berman tests the open-weight model on coding, 3D rendering and visual explanations, then compares benchmark results and prices.
12:14ENMatthew Berman· 14 oct. 2026Gemini 4 Argon Tested: 3D Demos, a Spreadsheet Prototype and Benchmark ResultsMatthew Berman · Forward FutureMatthew Berman tests Google’s model on games and visual projects, then compares reported coding and agent benchmarks.
10:36ENMatthew Berman· 13 oct. 2026Meta Muse Wonder Tested: Strong Benchmarks, Mixed Demos and Quota FrictionMatthew Berman · Forward FutureMatthew Berman tests Meta’s models on browser demos and reviews their published benchmark scores, availability and cost.
21:29ENMatthew Berman· 7 oct. 2026Mistral Large 4 Preview: European Open Weights, Cyber Benchmarks and Setup FrictionMatthew Berman · Forward FutureMatthew Berman reviews the model’s reported specifications and benchmarks, then tests it in an agent coding workflow.
16:59ENMatthew Berman· 29 sept. 2026Claude Sonnet 5.5 Tested: Games, 3D Scenes and a Lower-Cost Opus AlternativeMatthew Berman · Forward FutureMatthew Berman demonstrates generated projects and compares Sonnet’s reported benchmark scores and API prices with Opus.
31:59ENMatthew Berman· 23 sept. 2026Claude Opus 5.5: Benchmarks, Cost and Anthropic’s Approach to PacingMatthew Berman, Thariq · Forward FutureMatthew Berman reviews the release and speaks with Anthropic’s Thariq about daily workflows, evaluation and agent harnesses.
16:57ENMatthew Berman· 22 sept. 2026Grok 4.7 Compared: Coding, Knowledge Work and Cost per TaskMatthew Berman · Forward FutureMatthew Berman examines reported benchmarks and prices while noting missing competitors and limited hands-on testing.
1:05:23ENMatthew Berman· 3 sept. 2026Matthew 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.
16:50ENMatthew Berman· 3 sept. 2026Gemini 3.8 Flash: Benchmarks, Cost and Hands-On Coding TestsMatthew Berman · Forward FutureMatthew Berman compares Google's September 2026 model announcement with several practical visual and web-building examples.
13:09ENMatthew Berman· 14 août 2026AI News: Ultrafast Inference, Claude Watermarks and New ModelsMatthew Berman · Forward FutureMatthew Berman reviews an ultrafast coding preview, text watermarking, Grok Bot, open-weight models and Computer History.
15:37ENMatthew Berman· 4 août 2026Matthew 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· 24 juil. 2026Claude 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.
17:03ENMatthew Berman· 27 mai 2026DeepSWE: Testing Coding Agents on Longer Software TasksMatthew Berman · Forward FutureMatthew Berman reviews Datacurve’s benchmark, its verifier audit and the tradeoffs of comparing models under a shared harness.
31:22ENMatthew Berman· 26 mai 2026Cursor Composer 2.5 and the Economics of Coding ModelsMatthew Berman, Sundar Pichai · Forward FutureMatthew Berman examines coding benchmarks, model costs and enterprise budgets, then considers Cursor’s partnership with SpaceX and Anthropic’s demand for compute.
9:47ENMatthew Berman· 3 avr. 2026Gemma 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· 20 févr. 2026Gemini 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· 17 févr. 2026Matthew 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· 18 nov. 2025Gemini 3's Launch: Benchmarks, Antigravity, and AgentsMatthew Berman · Forward FutureMatthew Berman summarizes Google's November 2025 model launch and its developer and assistant demos.
8:47ENMatthew Berman· 16 sept. 2025Why 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.
1:43:51ENMatthew Berman· 8 août 2025GPT-5, Cline and SWE-bench: How to Judge AI Coding AgentsMatthew Berman, Matt Wolfe, Ray Fernando, Saoud Razwan, Nick, Ofir, Carlos, John, Kilian · Forward FutureMatthew Berman and guests discuss early GPT-5 impressions, the economics of Cline, and why coding benchmark results depend on the evaluation setup.
1:01ENMatthew Berman· 5 août 2025OpenAI’s gpt-oss Release and a Coding BenchmarkMatthew Berman · Forward FutureMatthew Berman introduces two open-weight models and reviews a Codeforces comparison from the launch.
22:05ENMatthew Berman· 9 juin 2025Apple’s “Illusion of Thinking”: Puzzle Limits and a Code-Assisted TestMatthew Berman, Ilya Sutskever · Forward FutureMatthew Berman reviews Apple’s reasoning-model experiments and tests a different way to solve Tower of Hanoi using generated code.
15:13ENMatthew 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.
15:15ENMatthew Berman· 19 avr. 2025Early 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.Charger plus24 sur 48 affichés