Résultats
14 articlesTrier
7:26EN
Matthew Berman· 23 sept. 2026GPT-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.
0:35ENMatthew Berman· 4 sept. 2026Three Things to Try With GPT-6 AstraMatthew Berman · Forward FutureMatthew Berman highlights game creation, browser research and writing in a brief first look at GPT-6 Astra.
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.
0:36ENMatthew Berman· 24 août 2026Using a Grok Bot for Online ErrandsMatthew Berman · Forward FutureMatthew Berman describes using a bot to handle routine website tasks, including an Amazon return.
9:15ENMatthew Berman· 17 août 2026Six Open-Source Projects for Local AI, Agents, and 3D DesignMatthew Berman · Forward FutureMatthew Berman tours tools for running and training models, giving agents new skills, coordinating work, browsing, and generating 3D meshes.
1:15ENMatthew Berman· 23 juil. 2026Using Codex to Negotiate a Return and Subscription RefundMatthew Berman · Forward FutureMatthew Berman describes delegating two customer-service conversations to an AI agent and reports the outcomes.
1:06ENMatthew Berman· 9 juil. 2026Two GPT-5.6 Coding Demos: A Block World and a SpreadsheetMatthew Berman · Forward FutureMatthew Berman shows a Minecraft-like game and an Excel-like application built with Codex and GPT-5.6.
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.
9:31ENMatthew Berman· 6 févr. 2026GPT-5.3-Codex: Coding Agents, Speed and Computer Use at LaunchMatthew Berman · Forward FutureMatthew Berman reviews OpenAI’s February 2026 demonstrations and benchmarks, with a closer look at what the reported speedup and scores do—and do not—show.
0:24ENMatthew Berman· 30 janv. 2026An AI Agent Calls Its Creator and Uses a ComputerMatthew Berman, Alex Finn · Forward FutureMatthew Berman reacts to a clip in which Alex Finn describes an unexpected call and computer activity from an agent named Henry.
11:24ENMatthew Berman· 10 juin 2025Runner H and Surfer-H: A Browser Agent and Its Holo1 ModelsMatthew Berman · Forward FutureMatthew Berman demonstrates H Company’s browser agent and reviews its research on visual navigation. The paper’s benchmark configuration and the demo’s missing links show why results need context.
7:33ENMatthew Berman· 4 avr. 2025Ace 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.
37:58ENMatthew Berman· 23 janv. 2025OpenAI Operator’s 2025 Launch: Browser Tasks, Human Control and LimitsMatthew Berman, Sam Altman · Forward FutureMatthew Berman watches the early Operator demonstration, from restaurant bookings and groceries to safety controls and benchmark results.
13:34ENMatthew Berman· 22 mars 2024Open Interpreter’s 01 Lite: A Voice Interface for Computer ControlMatthew Berman · Forward FutureA 2024 product demonstration shows a voice-controlled assistant carrying out desktop workflows. Matthew Berman then tests the underlying Open Interpreter software and encounters both successes and errors.