agy(Antigravity) 기본 view_file tool 은 800 lines, 45KB 제약으로 한 턴에 여러번 같은 파일을 read-edit 반복하는 문제를 발견했어요
그래서 claude code 의 str_replace_editor 참고해서 rust 기반 fast-file-editor 를 mcp 로 만들어보았습니다
https://t.co/r0FK8FvKyL
리드스위치 달린 ESP32로 가스 사용여부/사용량을 모니터링 중이었음. 자가검침세대라서 카톡 오면 눈으로 확인또는 사진 찍어 검침을 직접 입력해오고 있었음. 부산도시가스 홈페이지에 aiohttp로 로그인하고 조회 및 검침값 입력 가능하게 구현함. 검침일 되면 폰에 알림뜨고 제출하기 누르면 끝
gemini 3.8 flash 하루 사용해 본 결과:
벤치마크대로 opus 나 sol 비슷한 퀄리티인지는 아직 판단하기 어렵지만 빠릅니다. 그리고 웹서비스 개발에는 이미 good enough 인것 같아요
내일까지 다 태워버려야할텐데...
https://t.co/CcjSj3T4pA
I’m excited to finally announce the newest edition my Stanford course 𝗧𝗵𝗲 𝗠𝗼𝗱𝗲𝗿𝗻 𝗦𝗼𝗳𝘁𝘄𝗮𝗿𝗲 𝗗𝗲𝘃𝗲𝗹𝗼𝗽𝗲𝗿. It has been 9 months in the making.
Last November, with the release of Claude Opus 4.5, coding agents experienced a step function improvement in capability. We all felt it. The LLMs were more powerful, could reason for longer, solve harder tasks.
This year’s iteration of my course reflects the 2026 metamorphosis of software engineering.
My core belief is simple: AI-native developers of the LLM era are going to become the most important members of any software organization. I have designed my course to train this next generation of engineers.
𝗪𝗵𝗮𝘁’𝘀 𝗱𝗶𝗳𝗳𝗲𝗿𝗲𝗻𝘁 𝘁𝗵𝗶𝘀 𝘁𝗶𝗺𝗲 𝗮𝗿𝗼𝘂𝗻𝗱
First, 85% of my Fall 2025 class material is being thrown out. The Fall 2026 syllabus reflects the core capabilities AI-native engineers must have: agent skills, advanced context engineering, MCP portals, agent-ready codebase principles, agentic code review, security, parallelizing background agents, software factories, and more.
Second, I am going to teach my students how to have software taste. Every student will be required to ship pull requests to production-grade, real-world codebases. The course is collaborating with the top open-source AI repos who will offer support and mentorship to students on how to meaningfully contribute to their projects.
This has never been done before in any university course so I am incredibly grateful to our OSS Partners: @browserbase, @HeyGen, @CopilotKit, @semgrep, @OpenHandsDev, @milvusio, @marimo_io, Pi, @crewAIInc, @warpdotdev, @vercel, @cmux, @arizeai, @UnslothAI, and @anyscalecompute.
𝗪𝗵𝗮𝘁’𝘀 𝘀𝘁𝗮𝘆𝗶𝗻𝗴 𝘁𝗵𝗲 𝘀𝗮𝗺𝗲
I’m fortunate to again have AI software engineering leaders and founders as guest speakers to share their learnings from building top coding agent products. Thank you to @leerob from @cursor_ai, @bcherny of @claudeai code, @EnoReyes of @FactoryAI, @silasalberti of @cognition, @0xine of @semgrep, Rajesh Bhatia of @Cloudflare , @amasad of @Replit, and @eladgil.
All resources will be available online. All classes will be available to the public.
9/22 on Stanford campus. See you in class.
https://t.co/wTokHyUMsz
"은행을 위한 서비스가 아니라 진짜 은행이 되어야 합니다."
AI 시대엔 단순 SW 판매보다 최종 결과(Outcome)를 책임지는 버티컬 기업이 살아남습니다
진짜 가치는 편리한 '도구'가 아니라 결과의 '소유권'에 있으니까요
=> 그럼 저 같은 쫌쫌따리 1인 개발자는 뭘해야하죠🤔
https://t.co/RH01qzBodS
오랜만에 (최근에 아무도 언급안하는) Antigravity 로 Gemini 3.7 flash 모델을 사용해서 작업해보고 있는데, 너무 응답이 빨라서 생각없이 대충한거 아닌가 의심했지만, 대단할거 없는 웹서비스 만드는데는 차고 넘친다는 느낌이에요. codex, claude code 로 만들어놓은 workflow 대로 잘 수행하네요