絞り込み結果
70 件並び順
19:43EN
AI Engineer· 2026年10月26日Jack Wotherspoon on Building a Team of Managed AgentsJack Wotherspoon · Google DeepMindGoogle DeepMind’s Jack Wotherspoon introduces Gemini Managed Agents: cloud sandboxes that let teams run coding and research agents with a single API call. He explains how persistent environments, reusable skills, proxy-injected credentials, schedules, and specialized agents fit together.
20:55ENAI Engineer· 2026年10月26日Jesse Hall: Build Voice Agents for Conversations, Not LeaderboardsJesse Hall · LiveKitLiveKit’s Jesse Hall explains how to evaluate voice agents as real-time systems: understand callers, handle interruptions, keep talking while tools run, and measure the delay people actually hear.
18:27ENAI Engineer· 2026年10月26日Daksh Gupta on Building a Better AI Code Review AgentDaksh Gupta · GreptileGreptile co-founder Daksh Gupta explains why a webhook plus a coding agent is not enough for reliable pull-request review—and how targeted prompts, incident data, model inversion, codebase context, browser testing, and task-specific model routing can help.
20:58ENAI Engineer· 2026年10月25日Vinoo Ganesh on Making Financial AI Cite Every NumberVinoo Ganesh · KeplerKepler CEO Vinoo Ganesh explains why financial AI should retrieve and cite figures while deterministic software handles the math. His design makes traceability, retrieval quality, and tenant security part of the answer itself.
15:27ENAI Engineer· 2026年10月25日What AI Engineers Do Now: Build the Loop Around AgentsAparna Dhinakaran · Arize AIAparna Dhinakaran argues that AI engineers are moving from shipping individual features to building systems that let agent teams improve them. At Arize, that means tracing agent behavior, evaluating its work against human judgment, and feeding those signals back into an always-on agent.
25:50ENKimi 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.
17:42ENAI Engineer· 2026年10月21日Is a Faster Model Actually Faster? Measure the Finished Job, Not the TokensMorgan Suo · MiniMaxMiniMax's Morgan Suo takes the engineering changes inside M3.1 Flash one by one and asks the question that matters to users: does the job an analyst needs actually get done sooner, cheaper and correctly?
16:22EN
How I AI· 2026年10月21日ポッドキャストClaire Vo: Claude Duet Is Beautiful, but It Is Not My Number One Agentホスト Claire VoAnthropic’s phone-based personal agent has the most polished launch Claire Vo has seen: thoughtful onboarding, task lists, first-class artifacts, and Slack-style channels. Polish is not enough when every other agent is competing for the same attention.
17:37ENAI Coding, Game Mashups and the Value of Human TasteMatthew Berman · Forward FutureMatthew Berman explains decompilation and game mashups, then argues that iterative AI coding changes software and creativity.
21:29ENMistral 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.
25:39ENPersonal AI Assistants in Practice: Briefs, Family Logistics, Email and BillsMatthew Berman · Forward FutureMatthew Berman describes how he connects assistants to everyday workflows and sets approval rules for consequential actions.
16:59ENClaude 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.
16:57ENGrok 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.
17:15ENThe Hugging Face Incident: AI Evaluation, Sandbox Escape and Reward HackingMatthew Berman · Forward FutureMatthew Berman explains the reported OpenAI evaluation incident and the security and incentive failures it exposed.
18:34ENModel 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.
18:31ENTesting Nano Banana: Gemini 2.5 Flash Image EditingMatthew Berman · Forward FutureMatthew Berman tests character consistency, image edits, generation, visual sequences and common failure cases.
19:06ENBuilding 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.
27:16ENTudor Brindus on Finding and Reducing System JitterTudor Brindus · Jane StreetA memory ping-pong benchmark reveals how virtualization, interrupts, CPU frequency changes and speculation can disrupt low-latency systems.
16:06ENAI News: Video Generation, Apple Intelligence, Robotics and DeepSeek Coder V2Matthew Berman · Forward FutureMatthew Berman reviews a week of launches and research, from Luma and Runway to NVIDIA, robotics and coding models.
15:20ENOpenAI Exit Agreements: Vested Equity, Reporting and the Company’s ResponseMatthew Berman · Forward FutureMatthew Berman discusses Vox’s reporting on departure documents and distinguishes equity cancellation from access to private-company tender offers.
16:28ENTesting Reka Core: Multimodal Benchmarks, Coding and ReasoningMatthew Berman · Forward FutureMatthew Berman reviews Reka’s reported model comparisons and tests Core on code, logic and image understanding.
15:01ENTesting Llama 3 at Launch: Code, Reasoning and Image GenerationMatthew Berman · Forward FutureMatthew Berman tries Meta AI’s new interface on a snake game, logic puzzles and rapid image generation.
23:00ENTesting Google Gemma 7B at Launch: Setup MattersMatthew Berman · Forward FutureMatthew Berman compares local and hosted tests of Google’s early open-weight model.
23:25ENRichard Eisenberg: How OCaml Locals Reduce Garbage-Collected AllocationRichard Eisenberg · Jane StreetAn annotated list-processing example shows why locality must be preserved both when values are created and when functions consume them.
もっと見る70 件中 24 件を表示