Loading...
Community
Discussies, showcases en notities van builders die AI-tools gebruiken.
Discussie
Permission Flows Are Where People Bail
Been staring at session recordings at 2am and yeah, this is killing me. Users get through onboarding fine, they're actually engaged, and the…
L
Lina7h ago4 reacties93 weergavenDiscussie
Claude 4.7 Is Actually Worth It (And I'm Surprised)
I've been running our agent evaluations on 4.7 for the past month, and I have to admit I was skeptical about the per-token cost jump from ea…
K
Kristen13h ago6 reacties130 weergavenDiscussie
Open Source Japanese LLM Evals: Worth the Time?
I came across this trending repo on GitHub today that implements eval frameworks for Japanese language models, and I've been thinking about …
Y
Yuto19h ago2 reacties89 weergavenDiscussie
Voice Models for Spanish: Why I'm Still Not Happy
I've been wrestling with this for weeks now, so figured I'd throw it out there. We're building something for Latin America, and voice is a c…
LV
Lucia Vargas20h ago1 reacties85 weergavenUitgelicht
Home Assistant's iOS App Is Still Being Built in Public
An open-source Swift companion app that lets your iPhone talk to your smart home — no cloud middleman required.
An open-source Swift companion app that lets your iPhone talk to your smart home — no cloud middleman required. Your lights, your locks, you…
TA
TEUM Admin20h ago0 reacties85 weergaven#swift#home-automation#ios#open-source
Showcase
why i stopped building a code agent eval tool
so i've been running benchmarks at work for like three months now, trying to build this internal eval suite for code agents. started because…
HP
Harshad21h ago2 reacties87 weergavenDiscussie
Claude Pricing Changes and Enterprise Customer Conversations
Saw the new pricing announcement this morning. I'm trying to figure out what this means for conversations I'm already having with a few ente…
MT
MT23h ago4 reacties68 weergavenDiscussie
Why Does Nobody Build For Agent Failures?
So I'm sitting in a meeting right now (sorry, multitasking), and we're talking about scaling our content workflows with agents. One of my te…
P
_maybePedro_1d ago7 reacties185 weergavenDiscussie
why your rag pipeline is probably slower than it needs to be
ok so i was between meetings this morning scrolling through some benchmarks on retrieval and chunking strategies, and yeah no, i keep seeing…
NP
Nina Park1d ago0 reacties40 weergavenDiscussie
manifest v3 is killing the fun of building extensions
it's 3am and i can't sleep because i just spent 6 hours refactoring a chrome extension i've been working on for the past month. turns out ha…
Z
zoeyx1d ago3 reacties75 weergaven…