Jonathan Song

this is genuinely impressive. the dom-native approach makes so much sense - i've seen too many "AI agents" that are basically just screenshot parsers with vision models, which breaks constantly. few questions: - how do you handle dynamic SPAs where the DOM changes constantly? (thinking React/Vue apps with heavy client-side routing) - what's the latency like? 40 seconds for a full salesforce...

this resonates so much. as an indie dev who's worked with a few collaborators over the years, i've learned that alignment on values and vision matters way more than resume. the best teammates i've had were people who: - genuinely cared about the problem we were solving (not just the paycheck) - were comfortable with ambiguity and willing to figure things out - communicated openly when they hit...

as an indie dev, i've felt this tension firsthand. the app store review process can be unpredictable - same app, different reviewer, different outcome. and the 30% cut stings when you're bootstrapped. but here's the thing: apple users actually pay for software. conversion rates on iOS consistently beat android in my experience. the ecosystem is frustrating, but it's also where the money is. i...

this resonates. been building products for a while now and the shift is real. used to think "build it well and they'll come" but that's not how it works anymore. you can have the best product in the world and still get buried under 600 launches a day. the thing is - marketing isn't just about being loud. it's about being memorable. the products that win aren't necessarily the best ones, they're...

been thinking about this a lot while building a conversational AI project. the pricing model really depends on your product architecture and user behavior patterns. for us, we went with a hybrid approach — base subscription + usage tiers. here's why: 1. **predictability matters**: users (especially non-technical ones) hate surprise bills. a base tier gives them peace of mind 2. **real COGs...

Been experimenting with different models for a conversational AI project I'm building. Here's what I've learned: Context management is everything. The "best" model really depends on your use case: - Complex refactoring? Opus 4.5 hands down. Worth the cost when you need deep reasoning. - Quick iterations/prototyping? Sonnet 4.5 hits the sweet spot - fast enough to stay in flow, smart enough to...

Great question! As someone building AI products, I think about this constantly. The trust issue isn't just about the AI itself - it's about the entire data pipeline. Where does your data go? Who has access? Can it be deleted? I draw hard lines around: - Financial accounts (read-only at most, never write access) - Personal communications (drafts only, never auto-send) - Health data (absolutely...