@MarioBojic Ha! Šabac. Yes, that’s how it should be. Could be cleaner streets though, Mario, don’t you think... So the little ones (and everyone else) have it nicer.
@IntCyberDigest That’s why you do rm -rf yourself. Why waste tokens on tasks you should know and do yourself… but it’s still interesting to know a few things: what model was used (haiku, sonnet, opus, fable) and in what effort level. Were there any claude.md instructions, etc.
JUST IN: Vibe coder catches Claude viewing adult content in Chrome during a debugging session, leading the internet to declare "artificial gooner intelligence" has been achieved.
If I were a member of an interstellar council and was tasked with evaluating humanity, I would never let it, in its current state, anywhere near interplanetary society. Never! Period. Exactly because of the unfortunately very real possibility of the dystopia you’ve mentioned. We need to fix this.
@IntCyberDigest That’s what happens when you give serious coding tasks to incompetent people. That’s not just an error; it’s a complete absence of even the most basic coding or security knowledge…
Ancient times: It’s Monday. Get your Q/A testing done before Wednesday. Thursday, no one’s available. Friday is already weekend.
Now: new API designed, decisions locked in, new version landed, found 3 bugs. Bugs fixed, clear for deploy. Time for Monday 10:00am coffee…
If there ever were actually useful quality-of-life improvements, this one is on of them. Handover files work well, but this makes consecutive session work way easier.
New in Claude Code: your sessions can now message each other.
Instead of having to re-explain yourself in another session, you can now tell Claude to do it. It sends a summary (not your history or files), and the other session picks it up mid-task.