Alexander Embiricos (@embirico)
Codex를 무료 사용자에게 공개했다는 발표입니다. 지난주부터 무료로 이용 가능하게 했고 앞으로도 계속 무료로 제공해 누구나 코드 생성 기능을 이용해 프로젝트를 빌드할 수 있다고 밝힌 업데이트입니다.
#codegen
AI Doesn’t Reduce Work—It Intensifies It
"I think we've just disrupted decades of existing intuition about sustainable working practices. It's going to take a while and some discipline to find a good new balance."
https://simonwillison.net/2026/Feb/9/ai-intensifies-work/#atom-everything
#ai #codegen #llms #work
Vaibhav (VB) Srivastav (@reach_vb)
간단한 언급으로 OpenAI의 Codex(코덱스)를 바로 사용해 코딩·자동화 작업을 처리할 수 있다는 내용입니다. 특정 신기능 발표나 상세 설명은 없지만, Codex를 이용한 작업 흐름이나 코드 생성의 편의성을 강조하는 트윗입니다.
Theo - t3.gg (@theo)
작성자는 자신이 아는 대부분의 제품을 실제로 배포하는 사람들은 현재 Codex로 배포(shipping)하고 있다고 말하며, Codex의 실무 채택(현장 사용)이 매우 활발하다는 관점을 피력합니다.
Programming is Dead
"I’ve heard so many engineers say “Oh, I dabble but I just don’t think AI can do it well” are just in absolute denial at this point. Yes, AI can do a terrible job right now if you don’t wield it properly. The loom can make a mess of things if it’s improperly used. But, this is the worst these tools will ever be. They will only get better."
https://hamptonmakes.com/blog/2026/02/06/programming-is-dead.html
#agents #codegen #llms #programming
Pietro Schirano (@skirano)
Codex 앱 초기 릴리스에서 사용된 모델에 대해 작성자가 큰 감명을 받았다고 보고함. 한 사례로 MagicPath의 꽤 복잡한 리팩터링 작업을 몇 시간 동안 성공적으로 수행했으며, 평소라면 몇 주가 걸렸을 작업이었다고 설명함.
Sam Altman (@sama)
GPT-5.3-Codex가 공개되었습니다. 코드 생성 성능이 크게 향상되어 SWE-Bench Pro 57%, TerminalBench 2.0 76%, OSWorld 64%를 기록한다는 성능 수치가 제시되었습니다. 작업 중 미드-태스크 steerability(중간 조정)와 실시간 업데이트를 지원하며, 5.2-Codex 대비 동일 작업에 필요한 토큰 수는 절반 미만, 토큰당 처리 속도는 25% 이상 빨라졌다고 합니다. 컴퓨터 사용 능력도 우수하다고 보고됨.
Latent Space Engineering
"I think the upshot of all of this is that there is a lot of value to actively managing your agents' vibes and feelings, not just treating them as text-generation robots. The models aren't alive, but thinking of them as having feelings, rather than just next-token-prediction engines can help you nudge their mental states into a better place. I think you'll like the results."
https://blog.fsck.com/2026/01/30/Latent-Space-Engineering/
#agents #ai #codegen #llms #psychology
Speedrunning Agentic Software Engineering Management
"By my very uncharitable math, agentic software engineering methodologies have gotten to somewhere around the 1970s. Like everything in AI, this is, of course, a speed run. We're very quickly relearning why software engineering management and software engineering project management matter.
So by next Tuesday, maybe folks will start thinking about what they can steal from XP."
https://blog.fsck.com/2026/02/03/managing-agents/
#agents #ai #codegen #llms
Paul Couvert (@itsPaulAi)
알리바바의 Qwen 코딩 모델이 공개 출시되었습니다. 100% 오픈소스이며 활성 파라미터는 약 3B에 불과하지만 Sonnet 4.5와 동등한 코딩 성능을 보인다고 주장합니다. 10×-20× 더 큰 모델들과 비교해도 유사한 성능을 내며 로컬에서 실행할 수 있어 경량 고성능 코드 생성 모델의 획기적 공개로 평가됩니다.
I think I might go back to using GLM-4.7 with something like Primeagen's 99 plugin for nvim
1. I'm pretty exhausted with Claude Code and it's making me a worse dev the more I use it
2. I'm pretty fond of Chinese labs
3. I'm pretty fond of using whatever AI tooling I want and Anthropic seems to be hellbent on forcing everyone into Claude Code (ugh)
Chubby (@kimmonismus)
소문에 따르면 'sonnet 5'라는 새 모델 출시가 임박했으며(공식 확인 없음), 코드 작성 성능에서 Opus 4.5를 능가한다고 전해진다.
The Five Levels: from Spicy Autocomplete to the Dark Factory – Dan Shapiro's Blog
"I’ve now seen dozens of companies struggling to put AI to work writing code, and each one has moved through five clear tiers of automation. That felt familiar, and I realized that the federal government had been there first – but for cars."
https://www.danshapiro.com/blog/2026/01/the-five-levels-from-spicy-autocomplete-to-the-software-factory/
#ai #codegen #llms #tech
A Codeless Ecosystem, or hacking beyond vibe coding - Anil Dash
"There's been a remarkable leap forward in the ability to orchestrate coding bots, making it possible for ordinary creators to command dozens of AI bots to build software without ever having to directly touch code. The implications of this kind of evolution are potentially extraordinary, as outlined in that first set of notes about what we could call "codeless" software. But now it's worth looking at the larger ecosystem to understand where all of this might be headed."
https://www.anildash.com/2026/01/27/codeless-ecosystem/
#ai #codegen #codeless #llms
The head chef model for AI-assisted development - The New Stack
"The head chef model doesn’t create less work, but it allows you to move faster without sacrificing reliability or performance. Your role as a developer shifts from implementation to orchestration, from programming to validating and integrating AI-generated code."
https://thenewstack.io/the-head-chef-model-for-ai-assisted-development/?utm_source=FuckOff&utm_medium=FuckOff&utm_campaign=FuckOff
#ai #codegen #llms
A Shiny New Bloggy Home | Ultranormal
"There's risk there, though. I think the thing people are running into is that we've accelerated the 0 - 90% part of development, but that last 10% is now a lot harder because you still need professional experience to understand security, performance, networking, etc. That's the next hurdle - how do we help people who've gone run into that 90% wall at the speed of sound and made a huge mess? That's a topic for a different post."
https://lawver.net/2026/01/a-shiny-new-bloggy-home/
#ai #claude #codegen #llms
Aiden Bai (@aidenybai)
작성자는 Claude를 이용해 작업을 범위화하고 계획을 생성한 뒤 Opus에게 반복 생성을 시키고, 완료 후 코드의 나쁜 관행을 정리('deslop')하는 워크플로우를 설명함. 여러 모델을 순환시켜 코드 작업을 완성하는 실제 사용 사례를 제시.
Cursor is better at marketing than coding • The Register
"From where I sit, what makes the Cursor case more dangerous than just a failed hack‑week project is that the hype is baked into its methodology. The "experiment" wasn't presented as what it really was: an interesting, but messy, internal learning exercise. No, it was rolled out as a milestone that conveniently confirmed the company's long‑running autonomous agent advertising. Missing from the story were basics any senior engineer would demand: passing Continuous Integration (CI), reproducible..."
https://www.theregister.com/2026/01/26/cursor_opinion/
#ai #browsers #codegen #cursor #llms #webdev
C không có template hay reflection native, khiến việc serialize, validate, clone mỗi struct phải viết lại code hoặc sinh khối lượng boilerplate lớn. Giải pháp: tạo metadata ở thời build bằng macro DSL, sau đó dùng handle phản chiếu nhẹ để code generic duyệt metadata tại runtime. Nhờ vậy một hàm JSON chung có thể serialize mọi struct mà không cần hàm riêng, giảm đáng kể boilerplate. #C #reflection #metadata #serialization #lậptrình #codegen #programming
Client Info
Server: https://mastodon.social
Version: 2025.07
Repository: https://github.com/cyevgeniy/lmst