Seen it used in some of the fraud models (I work in insurance). So that's both from the perspective of people trying to claim fraudulently and from suppliers over charging. I can't say how much of a lift we actually get vs existing ML models

How often does it correctly identify that the blog post was actually written by Claude or ChatGPT etc? :)

How many countries should be included before it should be published?

A mixture of haplogroups, not just one

I see, yes, you need to have two, otherwise science cannot happen

They don't even mention it in the article. So that's already poor science perspective

I read the title and felt personally attacked :(

Yep. We work with CMT and we’ve both done extensive testing on this. I think that often people don’t necessarily know what a hard braking event actually means, or how it’s quantified. Giving that realtime feedback helps close that gap in understanding

I’ve played guitar for 20 years, but I’ve decided to do something different and just got some drums. I need to spend some time away from work lest I suffer from burnout again…

That will be fun. I am actually going to come back to electric guitar in 2026 after 15 years away.

I tried learning piano but that was a total waste. Drums I think make a lot of sense as a compliment to guitar.

Piano just made me feel like I wasted my life practicing guitar.

If anything I’ve learnt more because I’m having to go and find bugs in areas that I’m not super clued up on… yet ;)

Yes, we are. South African company.

Haha no - then it wouldn't have got a gold medal ;)