최근 업데이트된 채널

선택하면 해당 채널만 표시모든 채널 보기 →

필터 결과

8개
정렬
슬라이드 8장27:05EN
Theo - t3․gg· 2026년 8월 30일OpenAI and Cursor’s Split: What Changes for DevelopersTheo Browne · Ping LabsTheo explains the proposed end of direct OpenAI model access in Cursor, the dispute over usage figures, and alternatives for developers.코딩 에이전트BenchmarksDeveloper productivity+1
슬라이드 14장43:14EN
Theo - t3․gg· 2026년 8월 27일Why Theo Uses GLM-5.3-Flash for Coding Agent WorkTheo Browne · Ping LabsThe anonymous Ox Alpha model became GLM-5.3-Flash. Theo tests its pull-request triage, cost, multimodal features and limitations.코딩 에이전트Open-weight modelsBenchmarks+2
슬라이드 5장36:35EN
Theo - t3․gg· 2026년 8월 22일Theo’s AI Model Tier List: Capability, Cost and Coding WorkflowsTheo Browne · Ping LabsTheo compares frontier and smaller models using his own development work, benchmark charts and the prices available in August 2026.코딩 에이전트Foundation ModelsBenchmarks+2
슬라이드 5장31:48EN
Theo - t3․gg· 2026년 8월 20일Why File Systems Slow Down Coding Agent WorkflowsTheo Browne · t3.ggTheo Browne compares worktree creation, package installs and storage use across Mac and Linux setups, and explains why he moved his agent workflow to XFS with VDO.개발 워크플로와 테스트Developer productivityBenchmarks+2
슬라이드 7장44:42EN
Theo - t3․gg· 2026년 8월 7일Theo Tests Meta’s Muse Code: Fast, Cheap and UnevenTheo Browne · Ping LabsMuse Spark 1.2 handles rapid analysis and pull-request triage at low cost, but Theo’s experiments expose integration failures, hallucinations and rate limits.코딩 에이전트AI cost & performanceSoftware engineering+2
슬라이드 10장44:29EN
Theo - t3․gg· 2026년 7월 25일Theo’s Opus 5 Review: Coding Style, Cost and Model TradeoffsTheo Browne · Ping LabsAfter a day of coding with Opus 5, Theo compares it with Fable and GPT-5.6 Sol across plans, benchmarks, costs and real work.코딩 에이전트AI cost & performanceBenchmarks+2
슬라이드 9장57:39EN
Theo - t3․gg· 2026년 7월 18일Fable 5 vs GPT-5.6 Sol: Theo on Cost, Coding and Model JudgmentTheo Browne · Ping LabsTheo compares two coding models through benchmarks, design work and long-running tasks, explaining why his favorite model is not always the one he uses first.코딩 에이전트AI cost & performance개발 워크플로와 테스트+2
슬라이드 11장41:35EN
Theo - t3․gg· 2026년 7월 17일Kimi K3 in Practice: Coding, Visual Work, Cost and LimitationsTheo Browne · Ping LabsTheo tests Moonshot’s planned open-weight model on long coding tasks, UI design and a 3D game, while examining benchmarks and security concerns.코딩 에이전트Open-weight modelsAI cost & performance+2