Best Products
Launches
Launch archive
Most-loved launches by the community
Launch Guide
Checklists and pro tips for launching
Community
Discuss
Forums
Ask questions, find support, and connect
Events
Meet others online and in-person
Kitty Points Leaderboard
The highest scoring community members
Streaks
The most active community members
Read
Newsletter
The best of Product Hunt, every day
Stories
Tech news, interviews, and tips from makers
Changelog
New Product Hunt features and releases
MCP
New
Advertise
Subscribe
Sign in
Clear text
recent
p/pushary
by
Aadil Ghani
•
4mo ago
Your agent does something wrong. How far does it reach before anyone notices?
... rather than hold the line forever. A stalled job that took the cautious path is recoverable. A stalled job that just sat there is a support ticket. Comment from Dale Mooney(@dalemooney): @alex_amancio_candoa_ @aadilghani Constant
versus
invariant is the useful thing here and I am taking it. One addition: you cannot separate them by observation, but you can by deliberately violating the constant once. A property that survives a test faking an unattended caller ... ... which is bounded, and cannot fire when nobody started anything. Your last seen sweeper is already the mechanism. It is sweeping into the wrong bucket rather than lacking the signal. Comment from Dale Mooney(@dalemooney): @aadilghani The gate
versus
170
153
p/pushary
by
Aadil Ghani
•
5mo ago
How do you stay aware of what your AI coding agents are doing?
... have actually diverged in outcome in the ledger so far and if it's inferred, what's your cold-start before a single divergence has been observed? Comment from Alexander Bering(@alexanderbering): @aadilghani The reason "edit
vs
. tell-it-to-revise
vs
496
271
p/vibecoding
by
Jake Friedberg
Featured
•
10mo ago
Is usage-based pricing becoming the norm for AI tools?
... users are grabbing on to. Noone wants another subscription, so we provide the AI Creative services of several platforms in one spot, and allow for pay as you go credits. So far the buy in has been 50/50 sub
vs
bundled, but having both options is effective. See our credit model: https://aetherwavestudio.com/buy... Comment from Andrew Froehlich(@andrew_froehlich): @dansaki_samuel I agree, the subscriber is the best friend of the Saas product, but do not overlook ... ... line and not think about again. Comment from Will Towle(@willatsharpread): Running into this exact tension with Sharpread. Every analysis costs real money in Anthropic API calls plus EDGAR data fetches, so pure flat-rate SaaS feels like a
race
119
121
Subscribe
Sign in