PolygrAI
Automate, analyze & authenticate every interview with AI
Start new thread
Asen

LiarLiar.ai - Combining psychology with computer vision

by
PolygrAI
•
Introducing LiarLiar.ai, a groundbreaking leap in AI lie detection technology. Designed to discern truthfulness and identify potential deception, LiarLiar operates in real-time, combining proven psychological methods with advanced computer vision.

Add a comment

Replies

Best
Asen
PolygrAI
Maker
📌
Dear future early adopters of this captivating technology, I’d like to thank you in advance for supporting our efforts into disrupting the way we communicate online. In these uncertain times where remote work has been put on pedestal, it had become evident to us we need to take full advantage of the complex computer vision systems and neural networks that have become widely popular. We have been working to create this software for the past 3 months, and we still have a long way to go, but we’re very excited to start sharing our progress with our on a regular basis now, so that we can together shape the vision for this product. By the time we’re done with it, our goal is to have a software that can absolutely reliably and unbiased give you a gentle warning any time somebody has a high chance of being dishonest or deceitful to you. We have already conducted about a dozen experiment sessions, in which we have estimated that your tool has close to 70% success rate in correctly identifying natural deceitful activities, and has close to 100% accuracy in identifying the entailing cues and tells. While the interpretation of those activities and our truthfulness score is relatively subjective, it is absolutely evident that any time the truthfulness score of a person falls below 50%, you should take caution in their answers, and perhaps ask your question again. If this has happened, then the person you’re talking to has shown great sensitivity to the question or the discussion you have started. Our tool does not serve as a judge, but only as a precaution and emotional intelligence enhancer, so you can understand people and their true intentions better. I hope you have a great time using this software, and hopefully don’t encounter way too many bugs this early on that you get impatient. Looking forward to hearing your feedback and understanding how we can make this better.
Abdulla
Garen D Orchyan
Emma: AI Food Scanner
@asenlevov congratulations on the launch, best of luck 🦄♥️
Nastassia
Scade.pro
@asenlevov just wow! And do you use Paul Ekman technique with micro expressions?
Asen
PolygrAI
Maker
@nastassia_k Hello Nastassia, thank you! We are not using the Paul Ekman technique, yet. However, we use a neural network that's trained on millions of images for different emotions, while for the other type of micro-expressions, we are actively tracking more than 400 facial landmarks, and we have basically hard-coded the cues we're looking for such as change in eye gaze, blinking, lip compression, etc.
saurabh parmar
@asenlevov intersting. Do you have a monthly plan ? If not can I try it out with a video eg ww.youtube.com/watch?v=qO161zSEHho
André J
DiffSense
💡 Bright idea
Can I try it by uploading a video of a politician? Is it possible to try it before committing by paying? I want to see if it works first. Thanks
Asen
PolygrAI
Maker
@sentry_co Hi Andre, you can send the video to support@liarliar.ai, and I will process it for you gladly :)
André J
DiffSense
@asenlevov Awesome! thanks so much. I think this is so exciting! Imagine this as an Apple TV app analysing live tv, or as a mobile app to verify if people are telling the truth 😅 Black mirror vibes! So this is a famous left wing politician from Norway who has admitted that he lied in this interview: (full disclosure I have nothing against him or his party, I'm in the middle politically, This is truly to test if this service works, as his body language is all over the place 😅) https://www.nrk.no/video/moxnes-...
Asen
PolygrAI
Maker
@sentry_co My pleasure, Andre! I hope I don't come off as the villain in this Black Mirror episode, haha. Here is the analyzed video: https://youtu.be/AVM5FXIgtTc
André J
DiffSense
@asenlevov Thanks! That's really impressive stuff! I had no clue about all these signs that tell if your lying or not! Only problem is that the very same politicians can now practice lying with the same tool that will catch them. 😂
Asen
PolygrAI
Maker
@sentry_co It would take too much practice - they have more lucrative things to do surely Haha
💡 Bright idea
André J made a point with the video of a politician. 😄 Great tool; I can see how we will need this more and more often. Congrats on the launch! 💪
Asen
PolygrAI
Maker
@laurentiu_stefan Thanks, Laurentiu! Your words capture the essence of what we're striving for. André's video is just a glimpse into the vast possibilities if this type of technology was commercially adopted. Excited for what's to come.
Jacob Choi
Congrats on your launch. I love the concept behind this and I have a few questions! What criteria do you use to define falsehood, and thus the extent to which this technology can be applied? I wonder how the analyzed person's mental landscape and relationship to their words affect the ability to detect deceit. Thank you for your time considering my questions. I look forward to better understanding your product.
Asen
PolygrAI
Maker
@jacob_boston Hello Jacob, thank you for the great question. As we have outlined on our website, we use a combination of heart rate, eye gaze, micro-expressions, voice tone and pitch, and also emotions to create a standardized profile of a person. Then, when these parameters start fluctuating, we alert the user (you) for disturbance and irregularity, and thus we reduce the trustfulness score of the person. Essentially, the more tells/cues the person shows, the lower their trustfulness score is. Things like increased heart rate, decreased blinking, eye gaze change, and rapid emotional shift all contribute to lowering this score.
Jacob Choi
@asenlevov Thank you for your reply. So may I understand this technology then to be limited to persons who are aware of their own falsehood and are worried about being caught? By action-- an actor & a liar, though both are aware that everything they are conveying is figurative and thus false, only one carries the mental/emotional landscape (such as guilt or fear) necessary to trigger tells. So though both persons are doing the same thing, only the person with aspects such as guilt and fear present will be detected and given a lower truthfulness/trustworthiness score, correct?
Asen
PolygrAI
Maker
@jacob_boston Yes, that's right, Jacob. This detector, or any polygraph for that matter wouldn't be able to detect any difference for a person who truly believes what they are saying, including well-trained operatives or psychopaths for that matter. But for the average person, like 99% of the population, this tool would be very much functional.
Shivangi Awasthi
This is unbelievably the best use of AI. Kudos to you for coming up with this idea! Rooting for you today. Grab the #1 spot!!
Asen
PolygrAI
Maker
@shivangiawasthi Haha, thanks for the kind words!
Shane Yan
Amabay.ai
🔌 Plugged in
Hey Asen! Big congrats on this launch! The idea of a technology that can potentially predict deceit is not just fascinating but also pretty revolutionary – I've yet to come across anything quite like it. But it does make me wonder, who is the intended audience this? Would it be companies for interviews and business meetings, or any regular Joe looking to avoid dishonest interactions? I have some queries too - can this software detect deceit across different languages and cultures, considering body language and expressions vary worldwide? And, how does it differentiate between actual deceit and mere nervousness or discomfort? I genuinely can't wait for your vision to come to fruition! This could revolutionize digital communications as we know it.
Asen
PolygrAI
Maker
@shaneyan Hi Shane, thanks for the wonderful comment and food for thought. I certainly believe the way we communicate will be heavily disrupted by tools like LiarLiar and other computer vision algorithms. So far, the main audience is very interested in this has been salespeople, HR people, and companies looking to further strengthen their ID verification processes. I've also read about similar technologies being deployed at border security checkpoints for streamlined questioning. Regarding the varying international factors, the things we have outlined as cues and tells in our software are pretty much universal anywhere you go. For example, changes in the frequency of blinking or heartbeats are basically the universal tell that somebody is sensitive or nervous about a given topic. The same goes for eye gaze changes. Differentiating between actual deceit and discomfort is something no tool will ever be able to tell with certainty, however sensitiveness and nervousness around a topic can indicate that you should inquire further into that topic, and there's a high likelihood that the person is hiding something from you or being deceitful. Even CIA agents would never use the polygraph to determine whether a statement is a lie or not, but they would just delve deeper into the more sensitive topics, so they can get the most out of the conversation.
Artem Konovalov 💎
Shorty
Oh wow! You've finally launched, watched over your "Coming soon" for a while guys 😁 As I wrote before, just took the service for a spin, and it feels like a peek into the future of truth detection. Back in a while, I worked hard on face emotion recognition and many more (in stickerface.io and in Capture https://www.producthunt.com/products/capture-6, look at your project and see that technologies have stepped to the next level. Keep it up guys, good luck! 🔥 question: the header of PH says lifetime access, but I guess it does nothing. there are no promo codes or something?
Asen
PolygrAI
Maker
@mattisssa Haha thanks for following us, Artem! I'm glad you see some progress in tech - let's always see that and have the world become prettier, better and cleaner :) The lifetime deal is still site-wide and available for everyone to get. Planning to switch to subscription by the end of the year.
Eugene Lipski
Haha I love it! Good luck guys!
Asen
PolygrAI
Maker
@eugene_lipski Thanks, Eugene :)
Crustdata
Congratulations to the LiarLiar.ai team! This is such a revolutionary idea; the application of AI in lie detection is absolutely groundbreaking. I admire the novel concept behind real-time truth discernment and deception identification. My suggestion would be to consider introducing a credibility scale or spectrum in the output, offering a more nuanced understanding instead of a binary lie/truth scenario. Wishing you every success with LiarLiar.ai!
Asen
PolygrAI
Maker
@manmohit Hi Manmohit, we already have that, and it's called the Truthfulness Score (in the top right corner).
Success Hopeful
This is really an intriguing content.
Asen
PolygrAI
Maker
123
•••
Next
Last