Resultados
43 artículosOrdenar
0:21EN
Matthew Berman· 24 oct 2026An AI-Generated Kimi Benchmark Chart Used Invented ScoresMatthew Berman · Forward FutureMatthew Berman asks for a graph of Kimi K3.1 Pro benchmarks, then discovers that the displayed figures are illustrative placeholders.
1:03:37ENMatthew Berman· 23 oct 2026Matthew Berman’s Team Tests Kimi K3.1 on Animation, Games, and ChartsMatthew Berman, Alex, Brian · Forward FutureA live team AMA turns into an informal test of Kimi K3.1, from personal-agent workflows to motion graphics, a browser game, and a benchmark chart.
0:22ENMatthew Berman· 21 oct 2026A Robot Bodyguard Video Shows Dramatic Rescue ScenariosMatthew Berman · Forward FutureMatthew Berman reacts to a short robot demonstration depicting fighting and vehicle-rescue scenarios.
1:59:37ENMatthew Berman· 22 sept 2026Opus 5.5 and GPT-6 Sol and Luna: A Launch-Day LivestreamMatthew Berman, Thariq Shihipar, Alex, Brian · Forward FutureMatthew Berman interviews Anthropic’s Thariq Shihipar, shows early demos and then reviews two OpenAI models announced during the stream.
0:32ENMatthew Berman· 12 sept 2026DeepSeek’s Rubik’s Cube Demo Fails to Scramble and Solve CorrectlyMatthew Berman · Forward FutureMatthew Berman examines a cube simulation generated with DeepSeek V4.1 Flash through the Codex harness.
12:59ENMatthew Berman· 9 jun 2026Coding-Agent Loops: Triggers, Goals and the Cost of RepetitionMatthew Berman, Boris Cherny · Forward FutureMatthew Berman explains event-triggered and scheduled agent workflows, shows examples in Cursor and Claude Code, and considers their limits.
2:34:17ENMatthew Berman· 28 may 2026Matthew Berman Tests Claude Opus 4.8 and Dynamic Workflows LiveMatthew Berman · Forward FutureA launch-day walkthrough compares Anthropic’s reported benchmarks with informal coding experiments and a multi-agent website redesign.
17:03ENMatthew Berman· 27 may 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.
27:15ENMatthew Berman· 31 mar 2026Meta-Harness: Searching for Better AI Agent InfrastructureMatthew Berman · Forward FutureMatthew Berman reviews a paper on using a coding agent to iteratively improve model harnesses and discusses its experimental limits.
0:25ENMatthew Berman· 20 feb 2026Gemini 3.1 Pro: Four Benchmark Results from Its 2026 LaunchMatthew Berman · Forward FutureMatthew Berman reviews reported academic, abstract-reasoning and coding scores; the chart distinguishes ARC-AGI-2 from GPQA Diamond.
1:54:33ENMatthew Berman· 13 dic 2025Creative Agents, AI Evaluations and Enterprise Trust: Forward Future LiveMatthew Berman, Nick Wentz, Fabian Stelzer, Tejal Patwardhan, Christina Cacioppo, Jeremy Epling, Spenser Skates · Forward FutureLeaders from Glif, OpenAI, Vanta and Amplitude discuss creative workflows, knowledge-work benchmarks and practical AI adoption in December 2025.
32:22ENMatthew Berman· 16 oct 2025Qwen Image Edit Plus Compared With Nano Banana, Seedream and GPT Image 1Matthew Berman · Forward FutureMatthew Berman compares four image-editing models across compositing, precise edits, style transfer, object removal and weather effects.
28:27ENMatthew Berman· 2 oct 2025Sora 2 in Practice: Cameos, Camera Direction and Video Generation ErrorsMatthew Berman · Forward FutureMatthew Berman surveys early Sora 2 clips, testing likenesses, hands, motion, graphics and physics while pointing out where the generated scenes break down.
15:54ENMatthew Berman· 1 oct 2025Claude Sonnet 4.5: Coding, Long Tasks and a Simulated DesktopMatthew Berman, Dario Amodei · Forward FutureMatthew Berman reviews Anthropic’s launch claims and tries a generated-interface demo.
1:28:11ENMatthew Berman· 12 sept 2025AI Agents, Web Access and Startup Investing: Forward Future LiveMatthew Berman, Paul Klein, Yohei Nakajima · Forward FutureMatthew Berman speaks with Browserbase’s Paul Klein and investor Yohei Nakajima in a September 2025 livestream.
2:03:52ENMatthew Berman· 12 sept 2025AI Agents at Work: OpenAI, Factory AI and Box Discuss Building Reliable WorkflowsMatthew Berman, Nick Wentz, Srinivas Narayanan, Matan Grinberg, Aaron Levie · Forward FutureAt BoxWorks in September 2025, leaders discuss enterprise agents, software development and the practical work of evaluating AI systems.
1:50:08ENMatthew Berman· 22 ago 2025ARC-AGI, Agent Memory and Interactive Worlds: Forward Future LiveMatthew Berman, Nick Wentz, Greg Kamradt, Charles Packer, Alan · Forward FutureGreg Kamradt, Charles Packer and Skywork AI’s Alan join Matthew Berman and Nick Wentz to examine how AI systems learn, remember and interact with environments.
1:55:50ENMatthew Berman· 15 ago 2025Forward Future Live: GPT-5, AI Infrastructure, Evaluations and Coding AgentsMatthew Berman, Hiten Shah, Jordan Nanos, Tejal Patwardhan, Guy Gur-Ari · Forward FutureMatthew Berman and Hiten Shah speak with Jordan Nanos, Tejal Patwardhan and Guy Gur-Ari about the economics and measurement of AI in August 2025.
1:27:09ENMatthew Berman· 7 ago 2025GPT-5 Launch Watch Party: Coding, Reasoning, Health and Developer DemosMatthew Berman, Sam Altman, Mark Chen, Max Schwarzer, Rennie Song, Elaine Ya Le, Christina Kaplan, Tina Kim, Yann Dubois, Ruochen Wang, Saachi Jain, Sebastien Bubeck, Felipe Millon, Greg Brockman, Michelle Pokrass, Brian Fioca, Adi Ganesh, Michael Truell, Olivier Godement, Jakub Pachocki · Forward FutureMatthew Berman and producer Alex watch OpenAI's August 2025 launch, reacting to the model's routing, benchmarks, applications and live demonstrations.
10:28ENMatthew Berman· 5 ago 2025OpenAI’s gpt-oss Models: Open Weights, Benchmarks and SafetyMatthew Berman · Forward FutureMatthew Berman reviews the 120b and 20b models, local deployment claims, selected evaluations and the scope of OpenAI’s safety testing.
3:13ENMatthew Berman· 5 ago 2025Claude Opus 4.1: Anthropic’s August 2025 Benchmark UpdateMatthew Berman · Forward FutureMatthew Berman reviews the model’s reported coding, reasoning and tool-use results, including one benchmark that declined.
11:24ENMatthew Berman· 10 jun 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.
22:05ENMatthew Berman· 9 jun 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.
23:50ENMatthew Berman· 3 abr 2025PaperBench: How AI Agents Attempt to Replicate Machine-Learning ResearchMatthew Berman · Forward FutureMatthew Berman examines OpenAI’s research-replication benchmark, its partial-credit scoring and the prospect of faster AI research.Cargar másMostrando 24 de 43