最近更新されたチャンネル

選ぶとそのチャンネルだけを表示すべてのチャンネル →

絞り込み結果

67 件
並び順
スライド 2 枚0:36EN
Matthew Berman· 2026年10月25日Kimi K3.1 and a Rubik’s Cube Solver DemonstrationMatthew Berman · Forward FutureMatthew Berman shows a scrambled virtual cube being solved and gives the Kimi K3.1 test a favorable assessment.評価(Evals)コーディングエージェントOpen-weight models
スライド0:58EN
Matthew Berman· 2026年10月17日A 20-Minute Spreadsheet Prototype Built with Gemini 4 ArgonMatthew Berman · Forward FutureMatthew Berman tests a browser spreadsheet prototype on simple formulas and reflects on how AI could change software costs.コーディングエージェントSoftware engineeringProduct Strategy
0:46EN
Matthew Berman· 2026年10月12日Matthew Berman's AI-Assisted Super Mario World RecreationMatthew Berman · Forward FutureA short progress update describes a multi-day attempt to rebuild the game for a ModRetro handheld.コーディングエージェントSoftware engineering
スライド0:56EN
Matthew Berman· 2026年10月10日AI, Reverse Engineering and the Possibility of Custom SoftwareMatthew Berman · Forward FutureMatthew Berman explores AI-assisted recreations of creative software and imagines applications tailored to individual needs. The legal and practical claims require more nuance.コーディングエージェントSoftware engineeringOpen-source ecosystems+1
スライド 2 枚0:33EN
Matthew Berman· 2026年10月8日Mistral Large 4’s Rubik’s Cube Simulation Fails a Functionality TestMatthew Berman · Forward FutureMatthew Berman tests a generated Rubik’s Cube simulation and finds that scrambling and color handling fail in different iterations.評価(Evals)コーディングエージェントSoftware engineering
スライド 2 枚1:14EN
Matthew Berman· 2026年9月29日What Matthew Berman’s Team Built With Sonnet 5.5Matthew Berman · Forward FutureA short showcase presents an ocean simulation, game prototypes, city rendering and a LEGO design tool.Generative mediaコーディングエージェント
スライド 5 枚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.OpenAIAI cost & performanceBenchmarks+2
スライド0:35EN
Matthew Berman· 2026年9月15日A Five-Day Astra Run Builds a City SimulationMatthew Berman · Forward FutureMatthew Berman shows a city-building game he says Astra produced over five days, and notes that the project remained unfinished.コーディングエージェントVibe CodingSoftware engineering
スライド0:31EN
Matthew Berman· 2026年9月14日After Hours: A 3D City Rendered in ASCIIMatthew Berman · Forward FutureMatthew Berman shows a generated city made of text characters and says it was built with Astra.コーディングエージェントGenerative mediaVibe Coding
スライド 7 枚16:39EN
Matthew Berman· 2026年9月11日DeepSeek V4.1 Flash: Low-Cost Inference Meets Mixed Results in Practical TestsMatthew Berman · Forward FutureMatthew Berman examines DeepSeek’s efficient new open-weight model, its reported benchmarks and API pricing, then tests its speed, coding and visual work. His small set of demos reveals both impressive speed and problems with simulation accuracy.モデルと学習Open-weight modelsAI cost & performance+2
スライド 2 枚0:35EN
Matthew Berman· 2026年9月3日Three GPT-6 Astra Use Cases: Games, Browsing and WritingMatthew Berman · Forward FutureMatthew Berman shares brief examples of a generated game, browser research and writing, alongside his personal assessment of the model.Generative mediaComputer useコーディングエージェント+1
スライド 3 枚0:37EN
Matthew Berman· 2026年9月3日Three GPT-6 Game and World DemosMatthew Berman · Forward FutureMatthew Berman briefly shows a navigable low-poly world, an ASCII scene and a city simulation.コーディングエージェントGenerative mediaVibe Coding
スライド 15 枚1:05:23EN
Matthew 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.OpenAIFoundation ModelsBenchmarks+2
スライド 3 枚20:47EN
Matthew Berman· 2026年9月1日Why OpenAI Plans to End Its Direct Model Agreement With CursorMatthew Berman · Forward FutureAfter SpaceX acquired Cursor, OpenAI proposed winding down its model-supply contract. Matthew Berman examines the dispute, competing providers and the risks of relying on another company’s models.コーディングエージェントAI securityAI Strategy+1
スライド 7 枚18:57EN
Matthew Berman· 2026年8月29日GLM-5.3-Flash: Ox Alpha Benchmarks, Costs and Coding TestsMatthew Berman · Forward FutureMatthew Berman reviews Z.ai’s open-weight model, compares benchmark costs and tries coding and presentation tasks against a competing model.Open-weight modelsBenchmarksAI cost & performance+2
スライド 2 枚0:40EN
Matthew Berman· 2026年8月2日Enabling Max Reasoning Effort in CodexMatthew Berman · Forward FutureMatthew Berman shows an August 2026 settings menu for exposing Max reasoning effort and explains his preference for Luna.コーディングエージェントAI cost & performanceプロダクトと UX
スライド 3 枚0:52EN
Matthew Berman· 2026年6月24日A 12-Day Codex Run to Build an Excel CloneMatthew Berman · Forward FutureMatthew Berman describes giving Codex a brief goal and manually stopping it after more than 12 days, then demonstrates the resulting spreadsheet.コーディングエージェントエージェント工学Software engineering
スライド 9 枚16:11EN
Matthew Berman· 2026年6月19日Seven AI Coding Agent Loops and When to Use ThemMatthew Berman · Forward FutureMatthew Berman explains how triggers, goals and repeatable checks can turn coding tasks into agent workflows, with examples for performance, documentation and product quality.コーディングエージェント開発ワークフローとテストエージェント工学+2
スライド 5 枚28:16EN
Matthew Berman· 2026年6月9日Claude Fable 5 and Mythos 5: Matthew Berman Reviews Long-Running Coding WorkMatthew Berman · Forward FutureAn early Fable 5 user examines Anthropic’s benchmarks, safety controls, pricing and coding workflows, then demonstrates a Rubik’s Cube and a fluid simulation.AnthropicコーディングエージェントAI cost & performance+2
0:16EN
Matthew Berman· 2026年6月9日A Skit About Trying to Keep Up With AI NewsMatthew Berman · Forward FutureMatthew Berman jokes about the feeling of catching up just as another coding-agent discussion appears.コーディングエージェントAgent orchestrationComedy
スライド 6 枚44:52EN
Matthew Berman· 2026年6月5日Anthropic’s Recursive Self-Improvement Report: Evidence, Limits and a Debate Over Slowing AIMatthew Berman · Forward FutureMatthew Berman examines Anthropic’s 2026 claims about AI-assisted development, research benchmarks and possible paths to autonomous self-improvement.AI researchAI SafetyAnthropic+2
スライド0:47EN
Matthew Berman· 2026年6月4日Cognition's AI Productivity Guarantee for DevinMatthew Berman · Forward FutureMatthew Berman discusses a 2026 enterprise offer that compares estimated engineering value with the cost of using Devin.Developer productivityコーディングエージェントPricing+1
0:51EN
Matthew Berman· 2026年5月7日Why Berman Prefers Cloud Agents to Keeping a Laptop OpenMatthew Berman · Forward FutureA short video contrasts locally running agents with remote environments that can continue after a laptop is closed.コーディングエージェントインフラとデプロイAgent orchestration
スライド 2 枚1:23EN
Matthew Berman· 2026年5月3日Matthew Berman Demonstrates Codex Creating a Population SpreadsheetMatthew Berman · Forward FutureA short demonstration shows an AI agent using a web search and a spreadsheet skill to produce a chart.エージェントプロダクトと UXコーディングエージェント
もっと見る67 件中 24 件を表示