34 points craigmart 1 hour ago 23 comments
dude250711 57 minutes ago | parent
I am more interested in the remaining 10%.
TobTobXX 53 minutes ago | parent
thevilish 16 minutes ago | parent
“Also Claude, but we're fixing up the attribution to be super confident before claiming it”
https://x.com/bcherny/status/2111207278653399460?a=CQxYPj8Va...
girvo 45 minutes ago | parent
Im already spending my $2k usd per month in tokens with just one or two agents. How do they expect me to do that?
thatsabadlook 30 minutes ago | parent
4lb3rn 22 minutes ago | parent
nandanadileep29 33 minutes ago | parent
mohsen1 26 minutes ago | parent
Starting with infra evidence and soon expanding to application verification loops. This is a very exciting place to build and we're seeing great results once the verification loop is closed for the teams
beatrice-costa 17 minutes ago | parent
dotdi 26 minutes ago | parent
this u?
laichzeit0 20 minutes ago | parent
ForHackernews 21 minutes ago | parent
"The resource at “https://claude.dev/_next/static/chunks/241gnzjfqbp9f.css” preloaded with link preload was not used within a few seconds. Make sure all attributes of the preload tag are set correctly."
mococa 12 minutes ago | parent
OtherShrezzing 11 minutes ago | parent
There’s a long section in the middle where the article describes per-change verification via skill files and “ask Claude to use the chrome-for-Claude tool” when checking if changes have introduced regressions.
But there’s already tools which do this without spending tokens tokens. Playwright will achieve equal quality but deterministic results across the same verification attempts. It is write-once-use-often, so has a marginal cost near zero.
cyanydeez 5 minutes ago | parent
inamorty 6 minutes ago | parent