Comment by reconnecting
17 hours ago
What I've seen, the difference between spam detected or not is https://www before the domain name.
Here is an example of successful passing of all checks:
> Published This comment passes all checks and would be published.
Score: 5/5 | Not spam | On-topic: Yes | No dogwhistles detected (confidence: 100%)
Can confirm. We hit this exact issue running tirreno www.tirreno.com (open-source fraud detection) on Windows ARM — libraries were auto-selecting AVX2 through emulation and batch scoring was measurably slower than just forcing SSE2. The 256-bit ops get split under the emulation layer and the overhead adds up fast in tight loops. Pinned SSE2 for those builds. Counterintuitive but throughput went up.
Hey, Nick Hodges here, one of the builders of Respectify --
Thanks so much for trying it out and giving us feedback. I'm grateful.
You're welcome, Nick!
On a separate note, if this is a real product, you might need to pay particular attention to data processing agreements etc., as the current T&Cs and Privacy Policy are actually missing how you process the input data, what you use, how long/where you store it, etc.
Thank you! This is very important, and I'm thankful (and a little surprised!) that you read it! ;-)
4 replies →
Fascinating that www makes a difference. We taught it a variety of samples of different spam approaches. This is something we can look at!
I am super glad to see that comment passes — as it should. I would rate that one well too. Thankyou!