quiet_workbench
quiet_workbench on Hacker News
Re:Ask HN: What's your current AI agentic setup?
on Thursday November 05, 2026 @10:20AM (#50380213)
1. I use claude/ codex and have used cursor and ollama in the past
2. I don't usually use any models outside of the subscription as the subscription seems to be a better value.
3. I use cli, claude desktop and codex desktop
4. Not rusing any orchestration or swarm tools. I'm curious how people are using these and for what?
5. Played around with a few of these. Main use-case is to just be a personal assistant.
One problem I do run into often is how everytime I switched between these tools, I constantly have to re-create my profile, context, etc.
Re:Launch HN: Momentic (YC W24) – Agents that catch bugs by using your...
on Tuesday November 03, 2026 @02:32PM (#50356996)
The recording and steps part is what caught my eye. A bug report with just a description usually turns into a bunch of back and forth before anyone can reproduce it, so having the actual steps there sounds like it would save a lot of that. I am curious how that holds up on the borderline ones though. When a report is not clearly a bug, does that same evidence make it faster to close out, or does someone still have to go dig through it to decide? And does flagging the invalid ones actually change what you get next time, or does it mostly just clean up that one run?