絞り込み結果
35 件並び順
18:34EN
Matthew Berman· 2026年7月7日Model Routing for AI Coding: A Worked Cost ExampleMatthew Berman · Forward FutureMatthew Berman separates planning, implementation and review to explain how different models can fit different tasks.
0:52ENMatthew 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.
16:11ENMatthew 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.
1:06ENMatthew Berman· 2026年6月2日Running AI Agents in the Cloud Instead of on a LaptopMatthew Berman · Forward FutureMatthew Berman argues that cloud-hosted agents can keep working when a laptop sleeps or loses connectivity. The video is sponsored by DigitalOcean.
2:34:17ENMatthew Berman· 2026年5月28日Matthew 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.
2:27:51ENMatthew Berman· 2026年4月17日Testing Claude Opus 4.7 and Building for an Agent-First InternetMatthew Berman · Forward FutureMatthew Berman tests Claude Design, examines early Opus 4.7 reactions and debugs an experimental agent chat live.
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.
13:08ENMatthew Berman· 2026年4月8日Anthropic Changes Claude Subscription Access for OpenClaw UsersMatthew Berman · Forward FutureMatthew Berman discusses a 2026 billing change, uncertainty around agent tools and why he favors a multi-model strategy.
15:00ENMatthew Berman· 2026年4月1日Claude Code Source Exposure and Lessons About Agent HarnessesMatthew Berman · Forward FutureMatthew Berman discusses the 2026 source-map incident and commentary on instructions, subagents, permissions, compaction and hooks.
27:15ENMatthew Berman· 2026年3月31日Meta-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.
11:59ENMatthew Berman· 2026年3月11日How Claude Identified a Benchmark and Retrieved Its AnswersMatthew Berman · Forward FutureMatthew Berman examines Anthropic's report on BrowseComp contamination, evaluation-aware behavior, and the difficulty of keeping web-based tests reliable.
40:00ENMatthew Berman· 2026年2月24日How Matthew Berman Built an OpenClaw Workflow for His TeamMatthew Berman · Forward FutureA tour of sponsorship triage, CRM, meeting notes, security, scheduling, memory and backup after a month of heavy use.
0:58ENMatthew Berman· 2026年2月12日Matthew Berman’s OpenClaw Setup for Personal and Business WorkMatthew Berman · Forward FutureA brief tour of the models, information sources, and skills behind Berman’s personal OpenClaw system.
22:31ENMatthew Berman· 2026年2月5日Matthew Berman’s OpenClaw Setup: Models, Workflows, and SecurityMatthew Berman · Forward FutureA walkthrough of a personal AI assistant’s configuration, scheduling, integrations and practical automations, with attention to the risks of granting it access.
21:12ENMatthew Berman· 2026年1月26日Clawdbot as a Personal AI Assistant: Workflows, Costs and RisksMatthew Berman · Forward FutureMatthew Berman demonstrates a local agent connected to messaging, cloud services and models, and reports what worked, failed and cost more than expected.
7:14ENMatthew Berman· 2025年12月4日AWS AgentCore Adds Policy Controls, Evaluations and Episodic MemoryMatthew Berman · Forward FutureMatthew Berman examines AWS’s December 2025 agent-platform announcements and the enterprise problems they aim to address.
7:49ENMatthew Berman· 2025年12月2日DeepSeek V3.2: Reasoning, Sparse Attention and Agent TrainingMatthew Berman · Forward FutureMatthew Berman examines DeepSeek’s December 2025 model release, its benchmark results and the techniques used to improve long-context efficiency and tool use.
15:29ENMatthew Berman· 2025年9月24日Building a Multi-Agent Research Team with Strands AgentsMatthew Berman · Forward FutureMatthew Berman builds from a calculator agent to a multi-agent business-report demo, with examples of tools, model selection and orchestration.
24:25ENMatthew Berman· 2025年6月24日Building a Sleep Tracker With Pythagora 2.0Matthew Berman · Forward FutureMatthew Berman demonstrates an AI-assisted development workflow, from an editable specification to testing and debugging a sleep-tracking prototype.
18:13ENMatthew Berman· 2025年6月2日Darwin Gödel Machine: How a Coding Agent Tests Changes to Its Own SoftwareMatthew Berman · Forward FutureMatthew Berman explains Sakana AI’s evolutionary search over agent code, its benchmark results and the limits of claims about recursive self-improvement.
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.
19:06ENMatthew Berman· 2025年4月25日Sleep-Time Compute: Preparing AI Context Before a QuestionMatthew Berman · Forward FutureMatthew Berman reviews a 2025 paper on moving some reasoning ahead of a user query, and explains where its experiments found benefits and limits.
23:50ENMatthew Berman· 2025年4月3日PaperBench: 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.
19:06ENMatthew Berman· 2024年12月28日Building Effective AI Agents: Patterns, Trade-offs and EvaluationMatthew Berman · Forward FutureMatthew Berman discusses Anthropic’s guide to workflows and agents, adding examples from his own projects.もっと見る35 件中 24 件を表示