#agenticengineering

Andreas BeckerCaramba1
2026-02-12

Z.ai veröffentlicht GLM-5 und vollzieht den Wechsel von Vibe Coding zu Agentic Engineering. Im SWE-bench Verified erzielt das Modell 77,8 Prozent und schließt damit zur US-Spitze auf. Besonders bei autonomen Frontend-Fixes zeigt es Stärke, während es bei komplexem Reasoning noch knapp hinter Googles Gemini 3 Pro liegt. Die Dominanz westlicher Modelle bröckelt.
all-ai.de/news/news26top/glm5-

Mohan Iyer | Seekrates AImohan_iyer
2026-02-11

Osmani: "The better your specs, the better the AI's output."
Our evidence: 9,600 lines of specification BEFORE any code. 93-100% first-pass success. The spec IS the product.
The operating manual drops Saturday.
Preview: seekrates-ai.com/the-re-anchor-manager/

Latent.Space (@latentspacepod)

AINews: ElevenLabs가 시리즈 D로 5억 달러를 조달해 기업가치 약 110억 달러에 도달했고, Cerebras는 시리즈 H로 10억 달러를 확보해 기업가치 약 230억 달러가 됐다는 소식. 또한 'Vibe Coding'에서 'Agentic Engineering'으로의 트렌드 전환을 언급하며 업계 동향을 정리했습니다.

x.com/latentspacepod/status/20

#elevenlabs #cerebras #funding #ai #agenticengineering

Nine Internet Solutions AGninecloudnavigators
2026-01-22

The first TechTalkThursday of 2026 is approaching: it will take place on Tuesday, March 10. 📆 And we have already booked the speakers: Jonas Felix, Dan Acristinii and Thimo Koenig. 💻 They will talk about Agentic Engineering, Kubernetes and the Model Context Protocol (MCP). 👉 You'll find all the details about the event here: meetup.com/ninetechtalkthursda 👈

Nine Internet Solutions AGninecloudnavigators
2025-12-03

The last TechTalkThursday of 2025 is over, but the next one is just around the corner – on March 10, 2026. 📆 We are also pleased to announce our first speaker, Jonas Felix. 💻 He will talk to us about agentic engineering and how to use AI as a DevOps programmer with context, MCP, prompts, rules, and workflows. 💬 Find out more about the event here: meetup.com/ninetechtalkthursda 👈

Miguel Afonso Caetanoremixtures@tldr.nettime.org
2025-10-15

"So GPT-5-Codex is perfect?

Absolutely not. Sometimes it refactors for half an hour and then panics and reverts everything, and you need to re-run and soothen it like a child to tell it that it has enough time. Sometimes it forgets that it can do bash commands and it requires some encouragement. Sometimes it replies in russian or korean. Sometimes the monster slips and sends raw thinking to bash. But overall these are quite rare and it’s just so insanely good in almost everything else that I can look past these flaws. Humans aren’t perfect either.

My biggest annoyance with codex is that it “loses” lines, so scrolling up quickly makes parts of the text disappear. I really hope this is on top of OpenAI’s bug roster, as it’s the main reason I sometimes have to slow down, so messages don’t disappear.

Conclusion

Don’t waste your time on stuff like RAG, subagents, Agents 2.0 or other things that are mostly just charade. Just talk to it. Play with it. Develop intuition. The more you work with agents, the better your results will be.

Simon Willison’s article makes an excellent point - many of the skills needed to manage agents are similar to what you need when managing engineers - almost all of these are characteristics of senior software engineers.

And yes, writing good software is still hard. Just because I don’t write the code anymore doesn’t mean I don’t think hard about architecture, system design, dependencies, features or how to delight users. Using AI simply means that expectations what to ship went up."

steipete.me/posts/just-talk-to

#AI #GenerativeAI #Codex #LLMs #Chatbots #SoftwareDevelopment #Programming #AgenticEngineering

2025-10-15
Hacker Newsh4ckernews
2025-10-15

Client Info

Server: https://mastodon.social
Version: 2025.07
Repository: https://github.com/cyevgeniy/lmst