I tried out Kiro last week on quite a gnarly date time parsing problem. I had started with a two hundred-ish word prompt and a few bits of code examples for context to describe the problem. Similar to OP it forced me to stop and think more clearly about the problem I was trying to solve and in the end left my jaw on the floor as I saw it work through the task list.
I think only early bit of feedback I had was in that my tasks were also writing a lot of tests, and if the feedback loop to getting test results was neater this would be insanely powerful. Something like a sandboxed terminal, I am less keen on a YOLO mode and had to keep authorising the terminal to run.
This sort of comment always fascinates me. Having a machine do the last leaps for you is a time saver I guess, but I often wonder whether the real thing people are discovering again is that sitting down and really thinking about the problem you're trying to solve before writing some code results in better solutions when you get to it.
its not that i havent spent time thinking about it - i at least still my thinking first mostly on paper.
the LLM however asks me clarifying questions that i wouldnt have thought about myself. the thinking is a step or two deeper than it was before, if the LLM comes up with good questions
You can tell exactly where you live based on the castle reference. Happened to me once when a tourist in front asked about the castle and I couldn’t quite believe it was real.
I think if you’re planning on using this for personal use, and willing to accept the (slight) inconveniences associated with it, then this is likely very possible. Note that you’ll likely only be allowed to use the Bluetooth API in secure context, so HTTPS rather than file://[0]. I point this out as you’ve said a simple HTML page.
I recently built an application involving BLE (although not in a browser), and was quite surprised by how straightforward it can be. I’d recommend O’Riley’s Getting Started with Bluetooth Low Energy[1] as a quick skim to understand the core BLE concepts.
If you’re unsure how your device’s services and characteristics are set up, then using a decent inspector app is good if you’re trying to reverse engineer the values, I recommend BT Inspector[2] but unfortunately it’s iOS/MacOS only.
Hey sqrtc! Thanks for your response. I do intend on building something much larger than for my personal use, but having looked into it more it feels like the security risks are not worth the effort. I also understand the API is only available on Chrome (as other browsers such as Firefox have explicitly said they won't be supporting this). I'll play around with the react-native-ble-manager library and see what I can build. Thank you!
I am curious about how physical attractiveness was rated, and if there was particular criteria.
“..with the physical attractiveness of each participant rated by three members of the research team to produce an averaged single attractiveness score”
That seems very subjective to me, and subjectiveness may not even be the problem but having an average of just three scores.
I think only early bit of feedback I had was in that my tasks were also writing a lot of tests, and if the feedback loop to getting test results was neater this would be insanely powerful. Something like a sandboxed terminal, I am less keen on a YOLO mode and had to keep authorising the terminal to run.