AI Scripts updates and requests
Can I just say I love seeing this nerd shit being discussed, to me this is the beginning of an eventual personal SEX AI ...the fucking Lucy Liu Bot from Futurama and i'm here for it.
Rakly3 super happy biy meets girl in vancover is scripted but you guys need to please fix the script. The stroke lenght and timing is all messed up especially in the cowgirl position.
Qwertyqwerty1234 Thats not a good sign. I tried to watch a different AI script yesterday. The stokes are jerky. They are now longer but not smooth like a woman riding you would be.
I would think people are going to get mad if they pay money for these scripts.
Will65 I'm pretty sure I am going to cancel my script sub if this is what we are going to get. These scripts are worse than the Handy-generated ones, and I thought those were pretty bad. But if people keep subbing for it (and they keep silencing anyone who complains), they'll just keep pushing it.
AI scripts will only improve with time, and hand-crafted scripts are very much available as well.
Will65 @rerun119 @Qwertyqwerty1234 - its important to keep in mind that the AI scripts are fully automated (no human touch)
They will not be on the same level as purely human crafted scripts (like with anything purely automated) but they should be an added bonus to your scripts subscription (not a replacement)
It would be appreciated and I would encourage all of you with a scripts subscription, to still continue to enjoy the many current and ongoing handcrafted scripts we continually create and release - as long as you guys also keep and supporting those and enjoy those, we'll keep making those for you alongside these AI scripts
- Edited
There's this restaurant in town that has Ribs to die for! I go there every weekend. But lately they have been giving me a side dish of vegies with it at no extra cost. If they don't cut that shit, I'm never going there again.
Rakly3 So I watched https://www.sexlikereal.com/scenes/long-night-34588?tab=haptic for a bit and the intensity is much improved (pretty much what I'm used to in hand crafted scripts). The slow parts seem really nice (I'll have to watch a scene completely sometimes but at first glance I liked it).
The problem now are the fast movements. Anything red or purple in the heatmap is very jerky and not enjoyable. If you can just get the AI to catch up with these movements or smooth it out or whatever I think you will have a perfectly fine script and having everything scripted like that would be great, so keep up the progress!
RealcumberScripts my comment was not meant as negative critisism but more letting you know of an issue in the AI generated script so it can be addressed in further interations, and hopefully fixed in this particular scene. I realized AI scripts are not quite there yet but I hope this sort of comment can be used to help make them better. In fact, I'm excited we are getting more scripts period and would want all scenes scripted.
Hi everyone! It has been some time, but we took it to improve and today I would like o share with you 10 more AI scripts. Check them out and let us know what you think!
Kieshi So I watched back in your arms and my main feedback is that the intensity is too low again. Just watch the parts where the guy starts truly pounding her as fast as he can. I mean you pretty much can't fuck a girl faster than that and the funscript there isn't even purple. It almost felt like I set the handy to half the stroke length or something. Now it didn't even bother me so much for the blowjob parts but the fucking is really not up to par imo. The intensity is definitely not similar to something like a good Realcumber script.
Now I know that the previous batch (which had proper intensity imo) was pretty much unwatchable during the fast parts but toning down the intensity really isn't the solution here. It will just give unsatisfying scripts.
I do have some other more minor feedback as well (like that the AI only really captures up and down movements) but those are problems I can oversee in an AI script and aren't really deal breakers for me. I still think that you are on the right track and that if the intensity is solved the scripts would be enjoyable so I do hope you guys can fix it!
- Edited
fenderwq o I watched back in your arms and my main feedback is that the intensity is too low again. Just watch the parts where the guy starts truly pounding her as fast as he can. I mean you pretty much can't fuck a girl faster than that and the funscript there isn't even purple. It almost felt like I set the handy to half the stroke length or something. Now it didn't even bother me so much for the blowjob parts but the fucking is really not up to par imo. The intensity is definitely not similar to something like a good Realcumber script.
I'll take a closer look at it.
We set a new way for speed caps, that might be too restrictive.
Does surprise me as I used the Handy mechanical limits as cap. Though I have an idea of what might be wrong.
But a question still though. are there too few strokes in those fast parts (skipping strokes), or only the range+speed?
Rakly3 Skipped strokes is usually not the issue in the AI script (except for one part, I'll mention it later). It's the stroke range and I can say the cap is definitely too restrictive and as the handy can handle much more than that. Just compare some of the funscript heatmaps below of some good SLR scripts that feature similar intense parts as back in to your arms. They are way more intense and play perfectly fine. Also Notice how the range is often maxed to the bottom (which makes sense if a girl slaps into you).
For reference, back in your arms:
Screwing out of school (https://www.sexlikereal.com/scenes/screwing-out-of-school-project-32655) (especially notice the difference in the fast parts of the standing position)
Resting roommates (https://www.sexlikereal.com/scenes/resting-roommates-22501)
So I took another look and made some notes for you and added some semi rough timestamps. This is not everything but I think it brings the point across:
- 06:04 - The AI only seems to track up and down movements, blowjob segment was good overall though
- 18:12 - The guy is fucking her hard and the intensity (stroke range) is way too limited
- 24:24 - Maximum pounding but barely any stimulation in the script is (it's actually yellow)
- 25:16 - No visible up and down movement but griding so too little intensity (might also be a perspective thing)
- 25:35 - Visible movement here with low intensity so it's okay
- 32:37 - Doggy works well since it's a slow part and good visibility
- 38:46 - Skipped strokes, intensity way too low (perspective issue for the AI?)
- 39:32 - Even better example as the above. One of the worst parts.
- 42:56 - Jerk of finish, stroke range too low and at the bottom instead of top
So, to summarize some parts are good. Mostly the parts that are slow and clearly visible and in the right perspective. Fast parts and especially those that are less visible and in different perspective struggle to get a good result. Now I get that perspective and the obstruction of view can be difficult but the range should at least be limited way less.
Also, I don't know if you already do this and don't want to tell you how to do things but if I might make a suggestion: It might be a good idea to make a movie that has various common positions in different intensities (especially with the parts the AI struggles with) from movies that are scripted by someone like Realcumber. Than each time you iterate the AI you could just analyze this movie and compare the AI output with the manual script. Like with some test automation script that checks stroke range and intensity and visually using the heatmaps. The reason for me to mention this is that I think it is pretty obvious that there is something going on with the intensity by just by looking at the heatmap. For instance it's very rare for a funscript to only have 3 slightly orange parts and I think it has never been the case for a manual script made for an SLR Original.
Anyways, hope that this will help you crack the AI funscript thing!
fenderwq Also Notice how the range is often maxed to the bottom (which makes sense if a girl slaps into you).
This one is something we have been working on with varying results. The issue often is that, while trying to correct one thing, it 'breaks' another. The 'not reaching bottom' I think is a major problem point, partially causing the strokes being too shallow. - We will certainly take your detailed feedback in to our evaluation!
I do want to mention that we can not use the scripts hand made by scripters just like that, to train the AI. I don't think it's ethical and may be legally questionable.
The feedback is much appreciated and keep 'em coming! 
️
Rakly3 Glad to help and yeah I know how one thing can effect the other thing all to well as a tech lead of a dev team myself 
. The main reason I mentioned the bottom range maxing out is that it will effectively mean a larger average stroke range. In other words if you cannot max out the bottom You'll have to increase the range to get a similar sensation which might be difficult when the range is already large (I'm sure you are aware of this though).
As for the test movie: I get that you can't just use any script for training but you wouldn't train an AI model to generate Anime images without Anime in the training set either right? In other words scripters like Realcumber set a benchmark for what users want and come to expect. Now I think Realcumber is a level of quality we won't see in AI scripts for quite a long time but a script AI needs to at least understood some of the basics that make these scripts good and I think the stroke range (and thus overall intensity) is one of these essential things. Maybe Realcumber would be OK to provide a few parts of his scripts for a semi automated test that has a very varied amount of positions and intensities? This way you wouldn't even train your AI directly on the script, you would just have a tool to automate some of your quality control for the fundamentals of your script AI. This would also allow you to plot your progress for various versions on different key factors such as intensity for a varied amount of positions and intensities. I think this will take a lot of the guesswork out of the process. Just a thought though.
- Edited
fenderwq Hi, thank you for detailed feedback. I checked problems at timestamps you listed. It was helpfull. I prepared version of "Back in Your Arms" with better tuned larger range. Large range "Back in Your Arms"
We actually have automatic testing of our ai-scripting through comparing ai with Realcumber, we measure metrics of quality (like f-score, precission, recall, L2) as usual in Machine Learning projects The problem is umbiguity of video: there are several possible movements for single video interval, especially when penis is not visible. And detailed movements like at 06:04 you mentioned is hard problem due to lack of data of such kind.
