That’s a good one. I have a much more basic litmus test on my LinkedIn - adding an emoji before my first name. If they haven’t removed the emoji I know it’s an automated message, and it’s surprising (although not really) how many messages are. I ignore anything with the emoji in, so I know the person messaging has at least minimally engaged in reading my profile.
I think my awareness that this may influence future responses has actually been detrimental to my response rate. The responses are often so similar that I can imagine preferring either in specific circumstances. While I’m sure that can be guided by the prompt, I’m often hesitant to click on a specific response as I can see the value of the other response in a different situation and I don’t want to bias the future responses. Maybe with more specific prompting this wouldn’t be such an issue, or maybe more of an understanding of how inter-chat personalisation is applied (maybe I’m missing some information on this too).
+1 for the importance of a good Saab mechanic (if you’re not working on it yourself). I think the deciding factor on if I buy another Saab in the future is my proximity to a decently rated Saab specialist.
This is very cool! What sort of values are you using for the denoising strength/guidance scale? Each frame is a nice level of similar/different to the last to create flowing video.