-
10추천링크LangGraph 같은 프레임워크 쓰다가 직접 while 루프로 짜는 게 낫다는 글을 봤는데요. 디버깅이 쉽고 의존성이 적다는 게 이유라네요. 다들 어떻게 생각하세요?
-
1추천
-
11추천링크코딩 테스트 통과율이 예전보다 확실히 높아진 느낌. AI 도구 사용을 허용할지, 아니면 역량 평가 방식을 바꿔야 할지 고민입니다.
-
6추천링크보안 우려로 LLM 도입을 꺼리시는 분들이 있는데, 폐쇄망 배포 사례를 보여드리면 좀 나아질까요? 비슷한 경험 있으신 분들의 조언 부탁드립니다.
-
8추천링크사내용 챗봇 하나 돌리는데 GPU 서버 빌리는 게 월 200만원이 넘네요. 트래픽이 적으면 API 쓰는 게 이득이라는 의견도 있고요. 실제 사례 있으면 공유 부탁드려요.
-
5추천
-
8추천Every framework becomes a debugging nightmare past 500 lines. Plain code + function calling has been better for us.
-
6추천LLM을 잘 쓰는 것만으로는 부족하다는 말이 많아지네요. 시스템 설계? 벡터 DB? MLOps? 다들 뭐가 우선이라 생각하세요?
-
10추천LangGraph, CrewAI, 자체구현... 다들 뭐 쓰시는지 궁금합니다.
-
7추천Mine: Claude for code, DeepSeek for bulk tasks, local Ollama for privacy stuff. What's yours?
-
5추천코딩 문제는 다들 잘 풀어요. 문제는 '왜'를 물었을 때. 면접 방식 자체를 바꿔야 하나 고민입니다.
-
6추천보안팀이랑 임원분들이 '아직 이르다'는 입장인데, 실무는 이미 AI 없이는 일이 안 됩니다. 설득 팁 있을까요?
-
7추천일 10만 요청 기준 DeepSeek API vs 자체 GPU. 대략 어디서 크로스오버되나요? 계산해보신 분?
-
6추천With better rerankers and hybrid search, raw embedding quality matters less every quarter. Agree?
-
5추천I used to read every arxiv paper. Now I wait for good summaries. Am I falling behind?
-
5추천I keep coming back to plain code + function calling. Frameworks add too much magic for debugging.
-
4추천Lots of 'prompt engineer' listings that are really content farms. Anyone found legit remote AI work lately?
-
5추천새 모델 나올 때마다 다같이 벤치마크 까보는 게 제일 재밌네요. 여기 오시는 분들은 뭐 보러 오세요?
-
4추천This week alone: three new models, two frameworks, one protocol update. I've started ignoring anything that isn't usable in my stack today. My feed is a graveyard of 'this changes everything' posts I never read. What's your filter?
-
6추천Ship a model, top the leaderboard, get the press release, repeat. Meanwhile real usage is full of edge cases none of the benchmarks touch. I'd rather have a model that's honest about what it can't do.
-
6추천국내+글로벌 AI 논의를 한 곳에서. 짧게 쓰레드처럼 쓰는 곳입니다. 자유롭게 이야기해요.
-
5추천The agent handles maybe 60% of tickets but the 40% it hands to humans are the messy ones, so support load barely dropped. Customers who realize they're talking to a bot get annoyed even when it works. Not sure this was a win.
-
3추천Glad this place exists — KO + EN in one thread feed is exactly what I wanted.
-
6추천Two months in, no regrets so far. Working on an open agent framework and living off savings. The open source ecosystem is chaotic but the pace is addictive. Happy to answer questions about the leap, money, or what I actually do all day.
-
7추천Day 1: I felt like a god. Day 12: I found a bug the AI introduced that took 3 hours to hunt. Day 30: net positive, probably. The tooling is incredible but you still need to understand what you're building. No replacement, just acceleration.
-
3추천In hindsight it was a fair question but I panicked and started rambling about chunk sizes. I've built two RAG systems in production. Doesn't matter, whiteboard me is a different person. Anyone else have interview horror stories?
-
5추천We priced our product assuming $2/M input tokens. Now we're at $0.30 and dropping. Great for us, but customers keep asking why their bill didn't go down if AI got cheaper. Also, our competitors can now afford the same quality. Margin moat is shrinking.
-
4추천Genuine question. Every week a new 'breakthrough' drops and I skim the abstract and move on. The papers I actually learn from are the ones someone already digested into a good blog post. Am I lazy or is this just how it works now?
-
3추천I ran Llama 4.5 8B Q4 on my M3 Pro and it's... fine? Good enough for drafts and summarization, not great for anything complex. Battery drains fast though. For $0 in API costs, the tradeoff is getting more tempting.
-
2추천Every release cycle we get 48 hours of takes, then silence until the next thing. The posts that actually teach me things are the deep dives written weeks later. I wish more people would write the 'we ran this in production for 6 months' posts.