Viewing profile — mrprincerawat

yes, it feels like a dumbass

Opus since the last weekend feels worse then sonnet, it does not even recognise it's own skills until you explicitly scream at it tell it.

yoo, what's up gng, had breakfast?? (Can't think of any questions to ask)

Been noticing this pattern since Saturday, opus 4.6 on Claude Code thinks for 3-5 mins+ for even the most basic questions. Can this be related to the cache TTL drop they did??

Folks who have used both, what's your perspective??

haha yeah the weekend effect is real

Was thinking to create something similar, well done!

[dead]

Yea saw that a while ago, but honestly you can do all of that using Claude Code

AI agents treat remote servers like stateless APIs, a new SSH connection for every command, state lost every time, the full ssh -i key user@host repeated constantly. agentd gives a…

I built a Gmail CLI and made it a Claude Code plugin. Now I just say "check my inbox" or "reply to Alex's email" and it does just it. But it's also a full standalone CLI, interacti…

[dead]

Yeah that's fair, those teams probably produce better engineers in the long run too.

You're right, effort ≠ value. I've caught myself spending days "perfecting" things that had zero impact on the user just because the grind felt productive. The post wasn't about AI…

you're right, nothing stops me. i still can. but that's not really the point. when everyone around you is shipping in hours what used to take weeks, the pressure to keep up changes…

idk why the above link is not clickable: https://open.substack.com/pub/princerawat/p/software-in-the-...

I learned HTML at 10, spent an entire summer figuring out how to link webpages together. At 14 I built a CNN-based security camera system for a school science fair — took months, 1…

every agent framework is competing on how many abstractions they can stack. graphs, crews, nodes, edges, state machines. i just wanted to run an agent that calls my own python func…