Researchers train 'world's most advanced humanoid robot' Ameca on GPT-4, finds her less responsive

Indonesia Berita Berita

Researchers train 'world's most advanced humanoid robot' Ameca on GPT-4, finds her less responsive
Indonesia Berita Terbaru,Indonesia Berita utama
  • 📰 IntEngineering
  • ⏱ Reading Time:
  • 31 sec. here
  • 2 min. at publisher
  • 📊 Quality Score:
  • News: 16%
  • Publisher: 63%

The makers noticed that the processing time with GPT-4 was much longer than GPT-3 and made Ameca appear less responsive with her facial expressions.

in August 2022. Now, the developers behind Ameca have released a new video in which the bot can be seen exhibiting its polyglot-like qualities - speaking several languages including Japanese, German, Chinese, French, British, and American English., a researcher asks Ameca, "I've heard you can speak a lot of languages, is that true?" To which, Ameca responds in the affirmative, and shows off her language skills.

This Ameca demonstration used GPT-3 for conversation and translation, DeepL for language detection, and Amazon Polly Neural voices, according to the YouTube description. The team is currently working on a demo using Eleven labs voice cloning which adds complexity, thanks to the additional "phoneme and Visme generation" for lip sync. They will be integrated into the company's Tritium software platform. And a beta public version will be released in the coming months.

The makers mentioned that they trained Ameca's facial expressions on GPT-3 and GPT-4. They noticed that the

Berita ini telah kami rangkum agar Anda dapat membacanya dengan cepat. Jika Anda tertarik dengan beritanya, Anda dapat membaca teks lengkapnya di sini. Baca lebih lajut:

IntEngineering /  🏆 287. in US

Indonesia Berita Terbaru, Indonesia Berita utama

Similar News:Anda juga dapat membaca berita serupa dengan ini yang kami kumpulkan dari sumber berita lain.

OpenAI's GPT-4: How is it different from its predecessor GPT-3.5?OpenAI's GPT-4: How is it different from its predecessor GPT-3.5?GPT-3.5 vs GPT-4: What are the most significant improvements done by OpenAI? What are its limitations? What are its potential applications?
Baca lebih lajut »

OpenAI GPT: How to Create a YouTube Summary | HackerNoonOpenAI GPT: How to Create a YouTube Summary | HackerNoonHow to create a YouTube summary using Python and the OpenAI GPT model. - artificialintelligence ai
Baca lebih lajut »

Alibaba unveils Tongyi Qianwen, an AI model similar to GPTAlibaba unveils Tongyi Qianwen, an AI model similar to GPTAlibaba Group Holding Ltd on Tuesday unveiled Tongyi Qianwen, an AI large language model similar to GPT that it plans to integrate into all of the company's business applications in the near future.
Baca lebih lajut »

It takes a body to understand the world – why ChatGPT and other language AIs don’t know what they’re saying | OpinionIt takes a body to understand the world – why ChatGPT and other language AIs don’t know what they’re saying | OpinionWhy does GPT-3 make those choices when most people choose the alternative? Because GPT-3 does not understand language the way humans do.
Baca lebih lajut »

Baidu files lawsuit against Apple, app makers for fake Ernie AI bot appsBaidu files lawsuit against Apple, app makers for fake Ernie AI bot appsChinese search engine giant Baidu has sued app developers and Apple for selling fake copies of its Ernie artificial intelligence (AI) chatbot bot app on the Apple App Store, according to a Reuters report on Saturday.
Baca lebih lajut »

Amid big drop in sales, PC makers may soon be paying more in Chromebook licensing feesAmid big drop in sales, PC makers may soon be paying more in Chromebook licensing feesWhile the big drop in Apple Inc.'s Mac sales got most of the attention Monday amid the news that PC makers had yet another terrible quarter, another element...
Baca lebih lajut »



Render Time: 2025-03-03 13:21:47