Herb Sutter
Back in October, I wrote “Schneier on LLM vulnerabilities, agentic AI, and ‘trusting trust'” about fundamental architectural weaknesses in current LLMs and agents, and why I personally don’t yet trust AI agents with my credentials. At the end, I wrote: I love AI and LLMs. I use them every day....
Afnizar Nur Ghifari, Digital Product Designer
Beberapa hari ini saya sedang rajin mengkoleksi skills di Claude Code maupun Opencode — karena sangat membantu sekali dalam workflow pembuatan tools dan produk yang sedang saya kerjakan. Tapi di proses pengumpulan ini, makin lama makin berantakan. Tiap kali berpindah agents, saya perlu install...
Alan Johnson
I had a tough week, a week ago. My manager pointed out some of the negative side effects of my aggressive adoption of agentic coding, prompting me to rethink how I’m approaching my work. In particular, he pointed out that the fact that while I was able to take on some audacious tasks, the...