<div dir="ltr"><div dir="ltr">On Wed, 2 Jul 2025 at 21:01, <<a href="mailto:spike@rainier66.com" target="_blank">spike@rainier66.com</a>> wrote:<br>><br>> Hey cool! I already have a huge body of text, nearly thirty years of posting to Extr… op…<br>><br>> Oh dear, I have problem on my hands, a big problem BillK. <br>> Fortunately it comes with a solution: I must outlive my bride.<br>><br>> spike<br><div>><span class="gmail_default" style="font-family:arial,sans-serif;font-size:small;color:rgb(0,0,0)"> ----------------------------------------</span> </div><div><br></div><div style="font-family:arial,sans-serif;font-size:small;color:rgb(0,0,0)" class="gmail_default">Problem? Just keep it under lock and key and show it only to heavily disguised persons in the privacy of your secret underground bunker. ;)</div><div style="font-family:arial,sans-serif;font-size:small;color:rgb(0,0,0)" class="gmail_default">BillK</div><div style="font-family:arial,sans-serif;font-size:small;color:rgb(0,0,0)" class="gmail_default"><br></div><div style="font-family:arial,sans-serif;font-size:small;color:rgb(0,0,0)" class="gmail_default">I asked Claude Sonnet 4 for a second, more thorough, opinion --</div><div style="font-family:arial,sans-serif;font-size:small;color:rgb(0,0,0)" class="gmail_default"><br></div><div style="font-family:arial,sans-serif;font-size:small;color:rgb(0,0,0)" class="gmail_default">Yes, people can now chat with visual avatars of deceased friends or relatives that speak in their own voice. This technology has evolved significantly and is becoming increasingly sophisticated and accessible.<br><br>## Technical Capabilities<br><br>**Voice Cloning Technology**<br>Modern AI can recreate remarkably realistic voices using relatively small amounts of audio data. Voice cloning with services like Speechify can work with just 30 seconds of recording, while more advanced systems can produce highly convincing results with several minutes of source audio. The technology uses deep learning models to analyze vocal patterns, pitch, tone, and speech characteristics to generate new speech that sounds authentic.<br><br>**Visual Avatar Creation**<br>AI can analyze and create a 3D avatar from the deceased person's face, reconstructing detailed facial features, and if no video exists, you can simply upload a photo of the deceased and get ready to make it into a Talking Photo. These avatars can lip-sync to the generated speech, creating the illusion of natural conversation.<br><br>**Conversational AI Integration**<br>The avatars are powered by large language models that can engage in meaningful dialogue. Some systems are trained on the person's writing, social media posts, text messages, or recorded interviews to approximate their communication style, personality, and knowledge base.<br><br>## Major Players and Services<br><br>**Established Companies**<br>HereAfter AI, founded in 2019, allows users to create avatars of deceased loved ones. The AI-powered app generates responses and answers to questions based on interviews conducted while the subject was alive. HereAfter.AI differentiates itself in the expanding deathbot genre by providing life story recordings and plans to be around for a long time, with provisions to let customers download their recordings if the company shuts down.<br><br>**Chinese Market Leadership**<br>China has become a significant hub for this technology. Silicon Intelligence is part of a number of startups that created AI chatbots using someone's voice and likeness, made possible by the rise of increasingly powerful chatbots and investments in computing power that allow companies to offer affordable digital "clones". Undertakers and tech-savvy people in China have already started using AI tools to create realistic avatars of people who have passed away, using a blend of tools such as the ChatGPT chatbot and the image generator Midjourney.<br><br>**Consumer Applications**<br>People like Robert Scott, who lives in Raleigh, North Carolina, uses AI companion apps Paradot and Chai AI to simulate conversations with characters he created to imitate three of his daughters. Ana Schultz, a 25-year-old from Rock Falls, Illinois, asks her deceased husband Kyle for cooking advice through AI conversations.<br><br>## Real-World Applications<br><br>**Grief Support**<br>AI-generated avatars that look and sound like deceased relatives are increasingly popular to console those in mourning, or to hide the deaths of loved ones from the elderly and young children. Many users report finding comfort in being able to continue conversations with lost loved ones.<br><br>**Memorial Services**<br>Some funeral homes and memorial services now offer digital resurrection as part of their packages, allowing families to create lasting interactive memorials.<br><br>**Cultural Preservation**<br>The technology is being used to preserve family histories and cultural knowledge by creating interactive archives of elders and community leaders.<br><br>## Ethical Considerations and Safeguards<br><br>**Consent and Authorization**<br>Due to the rise in AI-powered scams using deepfakes of a person's voice or likeness, both Super Brain and Silicon Intelligence require authorization from the person being digitally cloned, or authorization from family and proof of kin if the person is deceased. Chinese AI firms only allow people to digitally clone themselves or for family members to clone the deceased.<br><br>**Psychological Concerns**<br>Artificial intelligence that allows users to hold text and voice conversations with lost loved ones runs the risk of causing psychological harm, according to researchers at Cambridge University. Ethicists are already warning about the unforeseen emotional impacts this could have.<br><br>**Commercial Exploitation**<br>There are genuine ethical concerns about conversing with an AI replica of a deceased loved one. Many death tech startups are commercially driven and feed off your grief. Researchers wonder what it means when mourning is 'fully integrated into the capitalist market'.<br><br>## Current Limitations and Considerations<br><br>**Technical Constraints**<br>- Quality depends heavily on available source material (photos, videos, audio recordings)<br>- The technology requires significant computational resources for the most realistic results<br>- Real-time interaction may have latency issues depending on processing requirements<br><br>**Emotional Authenticity**<br>The essence of a person is more than just the sound of their voice; it's the context, the emotions, the shared experiences. While the technology can mimic speech patterns and conversational style, it cannot truly replicate the complex emotional intelligence and lived experiences of the deceased person.<br><br>**Regulatory Landscape**<br>The technology exists in a largely unregulated space, with different countries taking varying approaches to oversight and ethical guidelines.<br><br>## Future Developments<br><br>The technology continues to advance rapidly, with improvements in:<br>- Reduced data requirements for voice cloning<br>- More sophisticated personality modeling<br>- Better integration with virtual and augmented reality<br>- Enhanced emotional intelligence in responses<br><br>The market is expected to evolve with new concepts that differentiate services in an increasingly saturated market, though questions remain about the long-term psychological and social implications of widespread adoption.<br><br>This technology represents a significant shift in how we process grief and remember loved ones, offering both unprecedented opportunities for connection and concerning questions about the nature of death, memory, and human relationships in the digital age.</div><div style="font-family:arial,sans-serif;font-size:small;color:rgb(0,0,0)" class="gmail_default">---------------------------</div><div style="font-family:arial,sans-serif;font-size:small;color:rgb(0,0,0)" class="gmail_default"><p><br></p></div></div>
</div>