Re:Ask HN: What's your current AI agentic setup?
by laurasg on Thursday November 05, 2026 @02:43AM
(#50376309)
I don't think you are doing anything wrong; it is overwhelming. But I also don't think "trusting" the system more would help. IMO, now coding is a bit more like maintaining critical infrastructure; it may be built quickly, but you need to keep an eye out for random decisions agents are taking that will cost you (money, security...) in the future. I have seen Claude making many sneaky decisions and (maybe) coincidentally burning more tokens by doing so
Re:Ask HN: What's your current AI agentic setup?
by Kwpolska on Thursday November 05, 2026 @02:44AM
(#50376311)
You use Claude as a "thinking buddy", meanwhile those who spend $500+ on LLMs have shut their brains off, and have delegated all thinking to the LLM, producing tons of slop.
Re:Ask HN: What's your current AI agentic setup?
by luisgvv on Thursday November 05, 2026 @10:26AM
(#50380285)
This is what I've been thinking lately. I've watched people showing up their setups and it's "cool" to fully automate and watch everything get done while sipping tea, but I bet you if something breaks or a product manager asks them they'll still rely on being a meat proxy.
No idea if this is the future lol
I have a Claude Code pro subscription, and mostly have Opus as a thinking buddy, we have thoroughly designed a data model together, we have implemented it in Django. Then we designed the RBAC system and now we are making views per role.
It is so intense! Constant decisions, walls of text with pros and cons to decisions. I mean the speed is amazing, the code quality is also amazing, but the amount of information I get to process is just insane, and I enjoy it less than the flow-state writing of code. I think I'll get used to it, and the speed is motivating, but man. I can not picture keeping 10's of agents on tasks. What am I doing wrong? Should I trust the system more? Or am I just mostly working on decisions now and the 1000$ token burners are not bothered with that (because they have a full backlog, where I need to fill it myself)?
Btw, as a FOSS person I so hate that I am not owning my means of production anymore, I have a home battery for all my infra, very proud of what I build, but I can't run my agents :( I really hope that will change soon (for privacy and for control reasons.)
I also have HermesAgents on a nuc here in front of me, it makes small automations (scans for positions or projects for my company, parse RSS feeds for relevant cybersecurity news, research things when I ask.)