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/general
by
Tasos V
β’
1h ago
How much time do you spend repeating context in Claude?
... 75mins a day repeating context and instructions. Anyone also facing this or found a way around it? Comment from Alex Goldwyn(@alex_goldwyn): 75 minutes a day is a real number and it is worth splitting, because the
two
halves
have different fixes and only one of them is yours. Half of what you are repeating is derivable from the repo which repo, how branches are named, what a PR has to look like. An agent gets those wrong when ... ... serves its own error page, so a test comparing a 404 body passed on every machine and failed only on the runner, with a diff that named the assertion and not the cause. Nothing in the repository says those
5
2
p/pushary
by
Aadil Ghani
β’
28d ago
Your agent does something wrong. How far does it reach before anyone notices?
... answer to a question nobody needed answered. Taking your design point, with one addition. Emitting skipped only buys you an alarm if something declares when it should have arrived. Your schedule supplies that for free. So the primitive has
two
halves
, the emitted non-event and the expected cadence, and the second is the one we lack, because our agents are not scheduled. A human starts them, so a quiet workspace is usually a person on holiday, and alarming ... ... naming: the running total has to be kept against a resource that
172
213
p/fetchsandbox
by
Raj Nagulapalle
β’
1mo ago
thanks for an unreal launch, now tell me what you're shipping
... drawn the exact line, and I won't blur it: today it's the pre-modeled set (duplicate, stale, out-of-order), not "feed in the real ordering your PSP actually sent you." but the
two
halves
aren't equally far off. the replay engine can already replay an arbitrary specified sequence deterministically .. that's what the out-of-order work is: hand it an ordering and it reproduces that exact one, not a random one. so what's missing ... ... single-pass? Comment from Raj Nagulapalle(@rnagulapalle): @omri_ben_shoham1 appreciate that ... and honestly the follow-up posts are more fun than the launch itself. when you do ship that first Stripe webhook, it's a
21
15
p/pushary
by
Aadil Ghani
β’
3mo ago
How do you stay aware of what your AI coding agents are doing?
... that, when a human is present and the decision needs them, upgrades that inbox message into a push with lock-screen approval. Channel chosen by recipient type and presence, same logic as picking ambient-
vs
-push, just one more rung down. But the
two
505
379
Subscribe
Sign in