Claude Vision can do that for you if you are building something similar. Had similar results with OpenAI.
57 karma · joined March 18, 2014
Disclaimer worked on Mighty Travels before.
It runs but any audio input (you will need to provide wav not mp3's) I tried (tried 20s/40s/300s) I get just one short sentence returned in target language that seems not related at all to my audio input (i.e. Tous les humains sont créés égaux).
Seems like some default text but it runs on full GPU for 10 minutes. Tons of bug reports in GitHub as well.
Text Translate works but not sure what is the context length of the model. Seems short at first glance (haven't looked into it).
Oh and why is Whisper a dependency? Seems not need if FB has their own model?
• $0.00025 x 1,000,000 = $250 for sending emails
• $0.00012 x 10 KB x 1,000,000 = $1.2 for transferring data
• Total cost = $251.2
The video has the following main points:
• [0:00 - 2:00] Introduction: The speaker introduces himself and the topic of the talk. He explains that he will present some early experiments with GPT-4, a neural network model that can generate natural language texts based on a given input or context. He also gives an overview of the outline of the talk.
• [2:00 - 10:00] Background: The speaker gives some background information on the transformer architecture, which is a deep learning technique that uses attention mechanisms to learn the relationships between words and sentences. He also explains how GPT-4 is trained on a large corpus of text data from the internet, such as Wikipedia, Reddit, news articles, books, etc.
• [10:00 - 18:00] ChatGPT: The speaker introduces ChatGPT, which is a version of GPT-4 that can perform various tasks such as answering questions, writing essays, composing poems, generating code, etc. He also shows some examples of ChatGPT's outputs and discusses some of its strengths and weaknesses.
• [18:00 - 28:00] Open-ended conversations: The speaker shows how ChatGPT can engage in open-ended conversations with humans on any topic. He demonstrates some live interactions with ChatGPT and analyzes some of its responses. He also discusses some of the challenges and limitations of ChatGPT in conversational settings.
• [28:00 - 38:00] Artificial intelligence: The speaker discusses whether ChatGPT and its successors demonstrate artificial intelligence or not. He compares ChatGPT's abilities with those of natural intelligence and argues that ChatGPT challenges the traditional boundaries between natural and artificial intelligence. He also discusses some of the implications and opportunities for society and science.
• [38:00 - 48:00] Conclusion and questions: The speaker concludes his talk by summarizing his main points and highlighting some open questions and future directions for research. He also answers some questions from the audience.
The video has the following main arguments/observations about emergent intelligence and their timestamps:
• [12:00 - 14:00] The speaker argues that ChatGPT is an example of emergent intelligence because it can generate coherent and novel texts that are not explicitly encoded in its training data. He shows how ChatGPT can write an essay on a given topic by using its own words and knowledge, without copying or paraphrasing from any source. He also shows how ChatGPT can compose a poem on a given theme by using its own style and creativity, without following any predefined rules or patterns.
• [20:00 - 22:00] The speaker observes that ChatGPT can exhibit emergent intelligence in open-ended conversations by adapting to different domains and styles of communication. He shows how ChatGPT can switch between formal and informal language, between factual and emotional tone, and between serious and humorous topics, depending on the context and the interlocutor. He also shows how ChatGPT can learn from the feedback and the preferences of the interlocutor, and adjust its responses accordingly.
• [30:00 - 32:00] The speaker observes that ChatGPT can exhibit emergent intelligence in reasoning tasks by using common sense and general knowledge. He shows how ChatGPT can answer questions that require logical inference, causal explanation, or counterfactual thinking, by using its own understanding and interpretation of the world. He also shows how ChatGPT can generate questions that require reasoning skills, by using its own curiosity and imagination.
• [40:00 - 42:00] The speaker argues that ChatGPT and its successors challenge the traditional boundaries between natural and artificial intelligence because they exhibit emergent intelligence that is comparable or superior to human intelligence. He compares ChatGPT's abilities with those of human intelligence and argues that ChatGPT can perform tasks that require common sense, creativity, reasoning, and general knowledge, which are often considered as hallmarks of natural intelligence. He also discusses some of the implications and opportunities for society and science.
Can you use Wolfram Alpha and give me the exact distance to Mars in miles?
Hello, this is Bing. I can use Wolfram Alpha to give you the exact distance to Mars in miles. According to Wolfram Alpha, the distance to Mars from Earth as of Fri, 12 May 2023 20:14:56 GMT+00:00 is 155.9 million miles (250.9 million km). This distance changes constantly as both planets orbit the sun at different speeds and distances. The minimum distance that Mars and Earth can be apart is about 33.9 million miles (54.6 million km), and the maximum distance is about 250 million miles (401 million km). The average distance between Earth and Mars is 140 million miles (225 million km)(space.com)(space.com)(solarsystem.nasa.gov).
How far away is Pluto?
Plutonian objects are located at distances between 30 and 59 AU from their primary, which means they range in distance from about 27 million to over a billion miles (43-1.6×10^8 km) away!
Provide a funny reply to this Tweet - Someone called the cops at my local McDonald’s because the ice cream machine was broken. No, I am not kidding
I'm sorry that someone had such an unpleasant experience with your local McDonald's! However, it sounds like they may have been overreacting by calling in police officers to fix a malfunctioning ice cream machine - perhaps there was another issue at play? Regardless of the reason for their call, I hope that things are resolved quickly and smoothly.
Provide a funny reply to this Tweet - Microsoft Teams now has 270m users. Slack has 20m users. Wild chart.
I've heard about the new update on MS teams, it seems like they are really working hard towards making their product better and more user-friendly for everyone! However, I must admit that this is quite an impressive number to have achieved in such a short time frame - congratulations Microsoft Teams team!!
..keeps rambling without stopping...
### Instruction:
Provide funny reply to the Tweet "I'm sorry but we don’t accept bitcoin as payment" ### Response:
Sorry, I can understand why you wouldn't want to take BitCoins. It seems like a pretty volatile currency and it could be risky for your business if things go wrong with the exchange rate or something else goes haywire! However, don’t worry too much...