Best Products
Launches
Launch archive
Most-loved launches by the community
Launch Guide
Checklists and pro tips for launching
News
Newsletter
The best of Product Hunt, every day
Stories
Tech news, interviews, and tips from makers
Changelog
New Product Hunt features and releases
Forums
Forums
Ask questions, find support, and connect
Kitty Points Leaderboard
The highest scoring community members
Streaks
The most active community members
Events
Meet others online and in-person
Advertise
Subscribe
Sign in
Clear text
recent
p/pushary
by
Aadil Ghani
•
2mo ago
Your agent does something wrong. How far does it reach before anyone notices?
... silently refresh into broader authority. A changed precondition invalidates the plan. And if current state cannot be checked through a bounded observation path, expiry should abort rather than recurse into another broad grant otherwise, as you say, it s
turtles
. I added this exact seam to the hardening matrix in issue #2: https://github.com/alexanderrada... So no: I wouldn t treat re-derivation reads as privileged or inherently safe. The trusted primitive is closer to observation with bounded effects ... ... because it's dumb, but because the radius is determined by capabilities it isn't even looking at. That's the strongest version of the "worst judge of its own reach" point I've seen. And your authority-armed-
versus
174
279
p/claude
by
Jake Crump
•
1yr ago
What's the weirdest thing you've asked AI to do? Examples welcome 🤖
... said I had a cavity in my tooth, so I went to the dentist and got it fixed. Not sure if this is weird enough :D Comment from Gin Tse(@jean_xavier): That's such a fun story! Playing "
Turtle
Soup" with an AI like Claude sounds both creative and hilarious. It s true, AI often struggles with the nuances of human logic and imagination in games like that ...
21
45
Subscribe
Sign in