Today I have something to share with you all!
My dog Arya has had several health issues since she was a puppy. To stay on top of her meds, I built my own app.
Now it’s live on the App Store and Play Store: Arya: Pill Reminder 🐾 a pet medication reminder & tracker.
@SSShken I have that same stack ($20 plan for codex, claude and cursor) and this checks out with my experience using all 3
Opus 5.5 is goated
Sol outputs tend to be worse than Opus 5.5 and limits are brutal, but it's really good for reviews
Cursor when i run out of usage on the other 2
@iannuttall@DeepakNesss I do have an opencode go sub as well but barely use it, frontier models have a completely different feeling from chinese ones at least time i tested them
@jackfriks imo vibe rating is fine for a prototype. once it touches client data or billing, "i dunno" stops being funny very fast.
the agent still needs a paper trail, even if a small one
"AI is just a toy that makes for cool demos"
"Ok it's not, but it cannot come up with novel ideas"
"Ok it can, but that fancy math problem has no real world implications"
Seems like this kind of people are running out of excuses 👀
Claude has discovered a previously unknown enzyme system hidden in the DNA of bacteriophages. Beside the enzyme’s gene sits a long array of repeating DNA—a structure that looks somewhat similar to CRISPR.
We don’t yet understand what this system does, but only a handful of known systems share its features, and all of them are able to cut, copy, and paste DNA. Historically, the discovery of such programmable systems has helped revolutionize medicine. CRISPR, for instance, is now the foundation of genetic medicines. But it will take much more work to learn what this system does, and whether it can be put to similar use.
Read more: https://t.co/RuEosScSMb
@iannuttall@brian_lovin Arya, a pill reminder app I built for myself and my dog, is pretty close to this. One painful problem, almost no surface area, technically not a SaaS i guess
https://t.co/MdqNBBoTFv
@levelsio Yep. Building is cheap now, but the moat is still knowing which problem is worth fixing. People only building AI products for tech users lack imagination imo
Were @theo and @maria_rcks responsible for OpenAI shutting you out when limits hit? No, they would have done it anyway.
But did it give OpenAI an excuse to do it without backlash? 👀 well I bet they found it very convenient.
And no this isn't yet another post throwing shade at them, in fact, I think what OpenAI did was pretty uncool.
Think about it, they pulled the plug on a feature that A LOT of devs appreciated, yet only these two are receiving the hate? And we didn't even receive a statement about it, OpenAI was completely content sitting back and watching the public lynching from afar.
Guys, it could have been anyone that made the same posts or even the same tool that exposed how easy that feature was to abuse, and we would be seeing some other guy being piled on instead.
I like OpenAI, but them letting some other person receive flak for what they decided and what they did, I don't think that's ok, why are we letting it slide?
Kind of wild that OpenAI is straight up in a compute crisis, going as far as shutting down signups for $200 accounts, yet somehow Maria and I are blamed for everything