> Connecticut’s Insurance Department recently reviewed EviCore and Carelon. It found no problems with Carelon. EviCore was fined $16,000 this year for more than 77 violations found in a review of 196 files.
$16k is such a low fine that it’d be funny if it wasn’t so sad. fines should be increased to actually represent a threat to the company - maybe as a % of yearly profit?
Look into openepaperlink. It’s an open source project that integrates with home assistant, and lets you control multiple tags over WiFi with just one device. you can create custom display setups in yaml to show anything you want.
my favorite that I have set up is a tag in my bathroom that shows me today’s weather and chance of rain when im brushing my teeth - I haven’t been caught by surprise in the rain since :)
if you read the thinking context while in plan mode (I had it shown to me, i think mistakenly, by switching modes while Claude was thinking a week or so ago) plan mode is just a pre-prompt saying “you are now in plan mode, don’t propose edits, read the code and understand how it works.”
really good piece, sums up almost exactly where I'm at with AI currently.
cognitive debt is a real problem in my domain (embedded software) because AI simply can’t debug the symptom when the reasons for the bug aren’t in code, and a stack trace may not exist. finding the REALLY hard bugs requires in depth systems understanding and the ability to connect things you’ve seen around the codebase together - and the fix usually isn’t adding code, which means the patchwork fixes Claude likes to do only makes things worse.
that said, it’s made writing harnesses and supporting tools WAY easier and faster, and my workflow is better for it. Searching the git history for the why of things is also made way easier; helping me to reason more effectively
For determining the number of balls, i had an idea but not sure of how well it’d fit in. Could you feed the listing title, unit count, and description into an LLM with a basic “figure out how many balls are in this listing and make sure that number makes sense with the price” prefix prompt and then store that number with the ASIN? One LLM call per product should be pretty low cost, and it could automate a bunch of repetitive manual work
As much as I love simple deterministic things, this is a classic example of where NLP is better than hardcoding a list of keywords. Trying to guess every set of quantity keywords with various spelling, punctuation and how they interact ("1dzn box, two pack" is actually 24 balls) seems more brittle than an LLM.
You're probably right. I can see how LLM is the better way to approach this. I haven't looked into AI usage fees or anything, but I would think the amount of queries I'd send wouldn't be that expensive. I'll look into it.
reply