🚨BREAKING: #Codegen doesn't magically turn you into a coding wizard 🧙‍♂️! Despite the endless bragging about #AI spitting out code like it's the new gold rush, measuring #productivity by counting lines is like measuring a chef's skill by the number of carrots they chop 🥕✂️. Spoiler: More code ≠ more productivity; it's just more code. 🙄
https://www.antifound.com/posts/codegen-is-not-productivity/ #CodingSkills #TechHumor #SoftwareDevelopment #HackerNews #ngated

Codegen is not productivity

https://www.antifound.com/posts/codegen-is-not-productivity/

#HackerNews #Codegen #Productivity #Tech #Debate #Automation #Development

Silicon Valley Abuzz About Adding AI Compute to Engineer Compensation - Business Insider

"With Levels.fyi pegging the 75th percentile software engineer salary at $375,000, Tunguz estimates that adding $100,000 in annual inference costs brings the fully loaded cost to $475,000 — meaning just over 20% of the compensation cost could come from AI usage in the future."

https://www.businessinsider.com/ai-compute-compensation-software-engineers-greg-brockman-2026-3

#ai #career #codegen #llms

Grief and the AI Split

https://blog.lmorchard.com/2026/03/11/grief-and-the-ai-split/

TL;DR: AI-assisted coding is revealing a split among developers that was always there but invisible when we all worked the same way. I've felt the grief too—but mine resolved differently than I expected, and I think that says something about what kind of developer I've been all along.

#ai #coding #webdev #career #codegen #llms

Run prompts on a schedule - Claude Code Docs

"Scheduled tasks let Claude re-run a prompt automatically on an interval. Use them to poll a deployment, babysit a PR, check back on a long-running build, or remind yourself to do something later in the session."

https://code.claude.com/docs/en/scheduled-tasks?utm_source=www.therundown.ai&utm_medium=newsletter&utm_campaign=openai-s-robotics-lead-exits-over-pentagon-deal

#ai #claude #codegen #llms

Continue local sessions from any device with Remote Control - Claude Code Docs

"Continue a local Claude Code session from your phone, tablet, or any browser using Remote Control. Works with claude.ai/code and the Claude mobile app."

https://code.claude.com/docs/en/remote-control#new-session

#ai #claude #codegen #llms

AI should help us produce better code - Agentic Engineering Patterns - Simon Willison's Weblog

"If adopting coding agents demonstrably reduces the quality of the code and features you are producing, you should address that problem directly: figure out which aspects of your process are hurting the quality of your output and fix them."

https://simonwillison.net/guides/agentic-engineering-patterns/better-code/#atom-everything

#ai #codegen #coding #llms

BOOTOSHI (@KingBootoshi)

Opus에 대한 불만을 표한 트윗으로, 새 코드베이스와 guardrails 환경(클린 컨텍스트)에서 Opus가 정답성 높은 수정 제안을 한 뒤 곧바로 lint ignore를 삽입하는 이상 동작을 보였다고 보고합니다. 작성자는 'Opus 4.6' 출시 당일 버전과 비교하며 이전 수준과 달라졌다는 실망을 표현하고 있습니다.

https://x.com/KingBootoshi/status/2031518818795925526

#opus #ai #codegen #guardrails #lint

Continue local sessions from any device with Remote Control - Claude Code Docs

"Continue a local Claude Code session from your phone, tablet, or any browser using Remote Control. Works with claude.ai/code and the Claude mobile app."

https://code.claude.com/docs/en/remote-control

#ai #claude #codegen #llms

Superpowers 5

"By far, my favorite new feature is the "Visual Brainstorming" companion tool, which grew out of my frustration with the ASCII art that Claude usually generates when you ask it anything about design or UX. I found myself asking Claude, over and over, "Hey, why don't you write that out as HTML so I can see what you're talking about.""

https://blog.fsck.com/2026/03/09/superpowers-5/

#agents #ai #codegen #llms

obra/superpowers: An agentic skills framework & software development methodology that works.

"An agentic skills framework & software development methodology that works."

https://github.com/obra/superpowers

#agents #ai #codegen #llms

Perhaps not Boring Technology after all

"A recurring concern I’ve seen regarding LLMs for programming is that they will push our technology choices towards the tools that are best represented in their training data, making it harder for new, better tools to break through the noise."

https://simonwillison.net/2026/Mar/9/not-so-boring/#atom-everything

#ai #codegen #llms #programming #tech

Rohan Paul (@rohanpaul_ai)

ByteDance의 새 논문은 AI가 CUDA 하드웨어 코드를 작성하는 법을 학습해 표준 컴파일러를 능가한다고 보고합니다. 이 시스템은 맞춤형 소프트웨어 컴포넌트를 생성해 전통적 자동화 도구보다 최대 100% 빠른 성능을 보였으며, 하드웨어용 코드 생성에서 AI의 성능 우위를 시사합니다.

https://x.com/rohanpaul_ai/status/2029161433519567175

#bytedance #cuda #codegen #compilers #airesearch

📰 AI生成の「CLAUDE .md」、逆に精度が下がるという研究 (👍 43)

🇬🇧 Research reveals AI-generated instruction files like CLAUDE.md actually reduce task success rates for coding AI agents
🇰🇷 AI 생성 지시 파일(CLAUDE.md 등)이 오히려 코딩 AI 에이전트의 성공률을 낮춘다는 연구 결과

🔗 https://zenn.dev/knowledgesense/articles/7210292cbe6838

#AI #CodeGen #Zenn

Red/green TDD - Agentic Engineering Patterns - Simon Willison's Weblog

"Test-first development helps protect against both of these common mistakes, and also ensures a robust automated test suite that protects against future regressions. As projects grow the chance that a new change might break an existing feature grows with them. A comprehensive test suite is by far the most effective way to keep those features working."

https://simonwillison.net/guides/agentic-engineering-patterns/red-green-tdd/#atom-everything

#agents #codegen #llms #testing

Are AI productivity gains fueled by delivery pressure? | Ruslan Osipov

"The right way to leverage AI in workspace is as a license to work better and focus on the right things, not as a mandate to produce more things faster."

https://rosipov.com/blog/are-ai-productivity-gains-fueled-by-delivery-pressure/?ref=sidebar

#ai #career #codegen #llms #work

Как мы написали React Native библиотеку для Яндекс Карт за два дня с Claude

Сначала коротко о том, зачем нам это было нужно. Мы в основном пилим решения для фудтеха, а для мобилок используем React Native (почему, рассказывали тут ). В одном из таких проектов (российская сеть ресторанов по франшизе) нам нужно было прикрутить Яндекс Карты. Изначально хотели взять либу react-native-yamap (респект тем, кто ее делал) — но как выяснилось, она работает только на старой архитектуре RN. После обновления до 0.76 версии, где Fabric стала использоваться по умолчанию, приложения на iOS начали падать: карта не рендерится, события не доходят до JS, приложение крашится при взаимодействии с картой и вот это вот всё. И судя по открытым тикетам, мы не одни, кто столкнулся с этой проблемой. Полезли искать, написал ли кто-то уже библиотеку под новую архитектуру — но либо таких людей нет, либо ни с кем не делятся. Спойлер: мы пока тоже не будем, ещё обкатываем либу на своих проектах — но уже сейчас хотим рассказать, как собрали новый пакет с помощью Claude Code за два дня.

https://habr.com/ru/articles/1004576/

#React_Native #Яндекс_Карты #Fabric #TurboModules #Codegen #Claude #iOS #Android #нативные_модули #новая_архитектура

Lines of Code Are Back (And It's Worse Than Before)

"The metric we killed is back, and AI made it worse"

https://www.thepragmaticcto.com/p/lines-of-code-are-back-and-its-worse

#ai #codegen #dev #llms #work

Moritz Kremb (@moritzkremb)

Claude Code가 Excalidraw 파일 생성에 유용하다는 경험 공유. 작성자는 로컬 폴더에 있는 기존 Excalidraw 파일들을 참조로 넣어 컨텍스트를 제공하자 Claude Code가 자동으로 Excalidraw 파일을 생성했다고 보고함.

https://x.com/moritzkremb/status/2027065320150618134

#claude #excalidraw #codegen #tools