|
|
| (27 intermediate revisions by the same user not shown) |
| Line 1: |
Line 1: |
| − | {{#seo:
| + | [[Gemini]] |
| − | |title=PRIMO.ai
| |
| − | |titlemode=append
| |
| − | |keywords=artificial, intelligence, machine, learning, models, algorithms, data, singularity, moonshot, TensorFlow, Meta, Facebook, Google, Nvidia, Microsoft, Azure, Amazon, AWS
| |
| − | |description=Helpful resources for your journey with artificial intelligence; Attention, GPT, chat, chatbot, videos, articles, techniques, courses, profiles, and tools
| |
| − | }}
| |
| − | [https://www.youtube.com/results?search_query=ai+Google+Bard+Gopher+Palm+LaMDA+chat YouTube]
| |
| − | [https://www.quora.com/search?q=ai%20Google%20Bard%20Gopher%20Palm%20LaMDA%20chat ... Quora]
| |
| − | [https://www.google.com/search?q=ai+Google+Bard+Gopher+Palm+LaMDA+chat ...Google search]
| |
| − | [https://news.google.com/search?q=ai+Google+Bard+Gopher+Palm+LaMDA+chat ...Google News]
| |
| − | [https://www.bing.com/news/search?q=ai+Google+Bard+Gopher+Palm+LaMDA+chat&qft=interval%3d%228%22 ...Bing News]
| |
| − | | |
| − | * [[Generative AI]] ... [[Conversational AI]] ... [[OpenAI]]'s [[ChatGPT]] ... [[Perplexity]] ... [[Microsoft]]'s [[Bing]] ... [[You]] ...[[Google]]'s [[Bard]] ... [[Baidu]]'s [[Ernie]]
| |
| − | * [https://bard.google.com Bard] | [[Google]]
| |
| − | ** ... Open the Google app on your smartphone and tap on the [[Assistants#Chatbot | Chatbot]] icon, enter your prompt and hit enter
| |
| − | ** ... help test Bard's latest version (experiment) in [https://labs.withgoogle.com/ Google Labs]
| |
| − | * [[Singularity]] ... [[Artificial Consciousness / Sentience|Sentience]] ... [[Artificial General Intelligence (AGI)| AGI]] ... [[Inside Out - Curious Optimistic Reasoning| Curious Reasoning]] ... [[Emergence]] ... [[Moonshots]] ... [[Explainable / Interpretable AI|Explainable AI]] ... [[Algorithm Administration#Automated Learning|Automated Learning]]
| |
| − | * [[In-Context Learning (ICL)]] ... [[Large Language Model (LLM)|LLM]]s understand to encode learning algorithms implicitly during their training processes ... [[Context]]
| |
| − | * [https://www.phind.com/ phind] ... The AI search engine for developers
| |
| − | * [[Assistants]] ... [[Personal Companions]] ... [[Agents]] ... [[Negotiation]] ... [[LangChain]]
| |
| − | * [[Large Language Model (LLM)]] ... [[Natural Language Processing (NLP)]] ...[[Natural Language Generation (NLG)|Generation]] ... [[Natural Language Classification (NLC)|Classification]] ... [[Natural Language Processing (NLP)#Natural Language Understanding (NLU)|Understanding]] ... [[Language Translation|Translation]] ... [[Natural Language Tools & Services|Tools & Services]]
| |
| − | * [[Attention]] Mechanism ...[[Transformer]] ...[[Generative Pre-trained Transformer (GPT)]] ... [[Generative Adversarial Network (GAN)|GAN]] ... [[Bidirectional Encoder Representations from Transformers (BERT)|BERT]]
| |
| − | * [[Prompt Engineering (PE)]] ...[[Prompt Engineering (PE)#PromptBase|PromptBase]] ... [[Prompt Injection Attack]]
| |
| − | ** [[Generative AI for Business Analysis]]
| |
| − | * [[Text Transfer Learning]]
| |
| − | * [[Cybersecurity]]
| |
| − | * [[Google]]/Deepmind:
| |
| − | ** [https://arxiv.org/abs/2209.14375 Sparrow - A. Glaese, N. McAleese, M. Trębacz, J. Aslanides, V. Firoiu, T. Ewalds, M. Rauh, L. Weidinger, M. Chadwick, P. Thacker, L. Campbell-Gillingham, J. Uesato, P. Huang, R. Comanescu, F. Yang, A. See, S. Dathathri, R. Greig, C. Chen, D. Fritz, J. Elias, R. Green, S. Mokrá, N. Fernando, B. Wu, R. Foley, S. Young, I. Gabriel, W. Isaac, J. Mellor, D. Hassabis, K. Kavukcuoglu, L. Hendricks, and G. Irving]
| |
| − | *** [https://the-decoder.com/google-may-use-deepminds-sparrow-as-chatgpt-competitor/ Google may use Deepmind’s Sparrow as ChatGPT competitor | Matthias Bastian - The Decoder]
| |
| − | *** [https://www.sportskeeda.com/gaming-tech/how-google-s-ai-tool-sparrow-looking-kill-chatgpt How Google's AI tool Sparrow is looking to kill ChatGPT | Mayank Kumar - Sports news] ...
| |
| − | ** [https://www.anthropic.com/Claude Claude |] [https://www.anthropic.com/ | Anthropic]
| |
| − | *** [https://techcrunch.com/2023/01/09/anthropics-claude-improves-on-chatgpt-but-still-suffers-from-limitations/ Anthropic’s Claude improves on ChatGPT but still suffers from limitations | Kyle Wiggers - TechCrunch]
| |
| − | *** [https://www.bloomberg.com/news/articles/2023-02-03/google-invests-almost-400-million-in-ai-startup-anthropic Invests Almost $400 Million in ChatGPT Rival Anthropic | Davey Alba & Dina Bass - Bloomberg]
| |
| − | ** [https://cohere.ai/classify Classify], [https://cohere.ai/generate Generate], and [https://cohere.ai/embed Embed] | [https://cohere.ai/ co:here] ...
| |
| − | ** [https://www.deepmind.com/publications/an-empirical-analysis-of-compute-optimal-large-language-model-training Chinchilla | DeepMind -]
| |
| − | ** [https://c3.ai/products/c3-ai-applications/ C3 AI Applications] | [https://c3.ai/ C3 AI]
| |
| − | * [https://interestingengineering.com/culture/google-built-chatgpt-like-ai-years-ago Google engineers had built ChatGPT-like AI years ago but executives blocked it | Ameya Paleja - Interesting Engineering]
| |
| − | * [https://arstechnica.com/gadgets/2023/03/google-shows-off-what-chatgpt-would-be-like-in-gmail-and-google-docs/ Google shows off what ChatGPT would be like in Gmail and Google Docs | Ron Amadeo - Ars Technica]
| |
| − | * [https://www.neowin.net/news/google-bard-will-soon-switch-language-models-from-lamda-to-palm-to-compete-with-bing-chat/ Google Bard will soon switch langauage models from LaMDA to PaLM to compete with Bing Chat | John Callaham - Neowin]
| |
| − | | |
| − | | |
| − | | |
| − | Bard is a [[Large Language Model (LLM)]] that is trained on a massive dataset of text and code. This dataset includes everything from books and articles to code and code comments. Bard is able to learn from this data and generate text that is similar to the text that it has been trained on. The data that Bard is trained on is processed using a technique called tokenization.
| |
| − | | |
| − | * Tokenization is the process of breaking down text into smaller units, called tokens. In the case of Bard, tokens are typically words or phrases. The model learns to associate these tokens with the meaning of the text that they are found in. The tokens that Bard is trained on are typically words or phrases. These tokens are learned from the massive dataset of text and code that Bard is trained on. The model learns to associate these tokens with the meaning of the text that they are found in. For example, the token "the" is typically associated with the beginning of a sentence, while the token "a" is typically associated with the beginning of an indefinite noun phrase. The model learns to associate these tokens with their meaning in the context of the text that they are found in.This allows Bard to generate text that is grammatically correct and that makes sense in the context of the user's query. The specific tokens that Bard is trained on are a trade secret. However, it is likely that the tokens include common words and phrases, as well as more specialized tokens that are related to specific domains of knowledge.
| |
| − | | |
| − | * The tokens that Bard is trained on are important because they allow the model to generate text that is relevant to the user's query. If the model is not trained on a specific token, it will not be able to generate text that is relevant to a query that uses that token. For example, if the model is not trained on the token "if", it will not be able to generate text that is relevant to a query that asks for a code snippet that uses the "if" statement. This allows Bard to generate text that is grammatically correct and that makes sense in the context of the user's query. The specific tokens that Bard is trained on are a trade secret. However, it is likely that the tokens include common words and phrases, as well as more specialized tokens that are related to specific domains of knowledge.
| |
| − | | |
| − | When a user prompts Bard with a question or request, the model uses the tokens that it has learned to generate text that is relevant to the user's query. The model also uses the tokens to generate text that is grammatically correct and that makes sense in the context of the user's query. The user interface for Bard is simple and easy to use. The user can type in a question or request, and the model will generate text that is relevant to the user's query. The model will generate text that is relevant to the user's query by using the tokens that it has learned to associate with the meaning of the user's query. The user can also ask the model to generate text in a specific style, such as a poem or a code snippet.
| |
| − | | |
| − | <youtube>n9s0_bwKiFY</youtube>
| |
| − | | |
| − | | |
| − | | |
| − | = <span id="PaLM"></span>PaLM =
| |
| − | [https://www.youtube.com/results?search_query=ai+Google+Bard+Palm+chat YouTube]
| |
| − | [https://www.quora.com/search?q=ai%20Google%20Bard%20Palm%20chat ... Quora]
| |
| − | [https://www.google.com/search?q=ai+Google+Bard+Palm+chat ...Google search]
| |
| − | [https://news.google.com/search?q=ai+Google+Bard+Palm+chat ...Google News]
| |
| − | [https://www.bing.com/news/search?q=ai+Google+Bard+Palm+chat&qft=interval%3d%228%22 ...Bing News]
| |
| − | | |
| − | * [[PaLM-E]]
| |
| − | * [https://ai.googleblog.com/2022/04/pathways-language-model-palm-scaling-to.html Pathways Language Model (PaLM)] | [[Google]]
| |
| − | * [https://arxiv.org/abs/2204.02311 PaLM: Scaling Language Modeling with Pathways] | A. Chowdhery, S. Narang, J. Devlin, M. Bosma, G. Mishra, A. Roberts, P. Barham, H. Chung, C. Sutton, S. Gehrmann, P. Schuh, K. Shi, S. Tsvyashchenko, J. Maynez, A. Rao, P. Barnes, Y. Tay, N. Shazeer, V. Prabhakaran, E. Reif, N. Du, B. Hutchinson, R. Pope, J. Bradbury, J. Austin, M. Isard, G. Gur-Ari, P. Yin, T. Duke, A. Levskaya, S. Ghemawat, S. Dev, H. Michalewski, X. Garcia, V. Misra, K. Robinson, L. Fedus, D. Zhou, D. Ippolito, D. Luan, H. Lim, B. Zoph, A. Spiridonov, R. Sepassi, D. Dohan, S. Agrawal, M. Omernick, A. Dai, T. Pillai, M. Pellat, A. Lewkowycz, E. Moreira, R. Child, O. Polozov, K. Lee, Z. Zhou, X. Wang, B. Saeta, M. Diaz, O. Firat, M. Catasta, J. Wei, K. Meier-Hellstern, D. Eck, J. Dean, S. Petrov, & N. Fiedel]
| |
| − | * [https://www.seroundtable.com/google-bard-better-palm-35163.html Google Bard Now Better At Math & Logic By Using PaLM, Google Says | Barry Schwartz - Search Engine Roundtable]
| |
| − | | |
| − | | |
| − | Achieving state-of-the-art few-shot learning results on hundreds of language understanding and generation benchmarks. On a number of these tasks, PaLM 540B achieves breakthrough performance, outperforming the finetuned state-of-the-art on a suite of multi-step reasoning tasks, and outperforming average human performance on the recently released BIG-bench benchmark. A significant number of BIG-bench tasks showed discontinuous improvements from model scale, meaning that performance steeply increased as we scaled to our largest model. PaLM also has strong capabilities in multilingual tasks and source code generation, which we demonstrate on a wide array of benchmarks.
| |
| − | | |
| − | | |
| − | <youtube>2BYC4_MMs8I</youtube>
| |
| − | <youtube>spc-UGr0aq8</youtube>
| |
| − | <youtube>dUk8h4-6Kf8</youtube>
| |
| − | <youtube>yi-A0kWXEO4</youtube>
| |
| − | | |
| − | = <span id="LaMDA"></span>LaMDA =
| |
| − | [https://www.youtube.com/results?search_query=ai+Google+Bard+LaMDA+chat YouTube]
| |
| − | [https://www.quora.com/search?q=ai%20Google%20Bard%20LaMDA%20chat ... Quora]
| |
| − | [https://www.google.com/search?q=ai+Google+Bard+LaMDA+chat ...Google search]
| |
| − | [https://news.google.com/search?q=ai+Google+Bard+LaMDA+chat ...Google News]
| |
| − | [https://www.bing.com/news/search?q=ai+Google+Bard+LaMDA+chat&qft=interval%3d%228%22 ...Bing News]
| |
| − | | |
| − | * [https://www.blog.google/technology/ai/lamda/ LaMDA |] [[Google]]
| |
| − | * [https://www.cnet.com/google-amp/news/google-unveils-its-chatgpt-rival/ Google Unveils Its ChatGPT Rival for AI-Powered Conversation | Stephen Shankland & Oscar Gonzalez - CNET] ... Meet Bard, Google's AI [[Assistants#Chatbot | Chatbot]] powered by LaMDA.
| |
| − | * [https://blog.google/technology/ai/lamda/ LaMDA (Language Model for Dialogue Applications): our breakthrough conversation technology | ] [[Google]]
| |
| − | | |
| − | | |
| − | LaMDA is “the language model” that people are afraid of. After a Google employee believed LaMDA was conscious, the AI became a topic of discussion due to the impression it gave off in its answers. In addition, the engineer hypothesized that LaMDA, like humans, expresses its anxieties through communication. First and foremost, it is a statistical method for predicting the following words in a series based on the previous ones. LaMDA’s innovativeness lies in the fact that it may stimulate dialogue in a looser fashion than is allowed by task-based responses. So that the conversation can flow freely from one topic to another, a conversational language model needs to be familiar with concepts such as Multimodal user intent, reinforcement learning, and suggestions. [https://dataconomy.com/2023/02/how-to-use-google-bard-ai-chatbot-examples/#:~:text=How%20to%20use%20the%20Google,your%20prompt%20and%20hit%20enter! | Sundar Pichal - Dataconomy].
| |
| − | | |
| − | | |
| − | <youtube>ayhJii34D38</youtube>
| |
| − | <youtube>O-TGY105kbQ</youtube>
| |
| − | <youtube>BXaPyaVymkk</youtube>
| |
| − | <youtube>TsIqW38kEnI</youtube>
| |
| − | <youtube>HwUt9ZRziBE</youtube>
| |
| − | <youtube>2M2pSADmSDs</youtube>
| |
| − | <youtube>q5nyE3RTc9M</youtube>
| |
| − | <youtube>pZ5Y3xEkCA8</youtube>
| |
| − | <youtube>xhZ-rueqllg</youtube>
| |
| − | <youtube>Srx1IZXoiJU</youtube>
| |
| − | | |
| − | = <span id="Gopher"></span>Gopher =
| |
| − | [https://www.youtube.com/results?search_query=ai+Gopher+Bard+DeepMind YouTube]
| |
| − | [https://www.quora.com/search?q=ai%20Gopher%20Gopher%20DeepMind ... Quora]
| |
| − | [https://www.google.com/search?q=ai+Gopher+Gopher+DeepMind ...Google search]
| |
| − | [https://news.google.com/search?q=ai+Gopher+Bard+DeepMind ...Google News]
| |
| − | [https://www.bing.com/news/search?q=ai+Gopher+Bard+DeepMind&qft=interval%3d%228%22 ...Bing News]
| |
| − | | |
| − | * [https://www.deepmind.com/blog/language-modelling-at-scale-gopher-ethical-considerations-and-retrieval Gopher Blog Post]
| |
| − | * [https://storage.googleapis.com/deepmind-media/research/language-research/Training%20Gopher.pdf Gopher Paper]
| |
| − | | |
| − | | |
| − | Prompt: I heard you were going to get a new LLM
| |
| − | | |
| − | Bard: Yes, that's correct. Google is working on a new LLM called Gopher, which is expected to be much larger and more powerful than the current LLMs. Gopher is being trained on a massive dataset of text and code, and it is expected to be able to perform a wide range of tasks, including generating text, translating languages, writing different kinds of creative content, and answering your questions in an informative way. Google has not yet announced a release date for Gopher, but it is expected to be available in the near future. I am excited to see what Gopher can do, and I am confident that it will be a valuable tool for me and for others.
| |
| − | | |
| − | Prompt: Can you tell me more about Gopher?
| |
| − | | |
| − | Bard: Gopher is a large language model (LLM) from Google AI, trained on a massive dataset of text and code. It was announced in January 2023 and is expected to be released in the near future. Gopher is designed to be a more powerful and versatile LLM than the current LLMs, and it is expected to be able to perform a wide range of tasks, including generating text, translating languages, writing different kinds of creative content, and answering your questions in an informative way. Gopher is being trained on a dataset of text and code that is much larger than the datasets used to train the current LLMs. This larger dataset will allow Gopher to learn more about the world and to be more accurate in its responses. Gopher is also being trained using a new technique called "deep learning," which allows it to learn more complex patterns and relationships in the data. Gopher is expected to be a valuable tool for a variety of applications, including search, translation, and education. It is also expected to be a powerful tool for creative writing and for generating new ideas. Here are some of the things that Gopher can do:
| |
| − | | |
| − | * Generate text: Gopher can generate text in a variety of styles, including news articles, blog posts, and creative writing.
| |
| − | * Translate languages: Gopher can translate text from one language to another.
| |
| − | * Write different kinds of creative content: Gopher can write different kinds of creative content, such as poems, code, scripts, musical pieces, email, letters, etc.
| |
| − | * Answer your questions in an informative way: Gopher can answer your questions in an informative way, even if they are open ended, challenging, or strange.
| |
| − | | |
| − | Gopher is still under development, but it has already learned to perform many kinds of tasks. It is expected to be a valuable tool for a variety of applications, including search, translation, and education.
| |
| − | | |
| − | | |
| − | <youtube>nO653U-Pb5c</youtube>
| |
| − | <youtube>IaltsI1BCro</youtube>
| |
| − | | |
| − | | |
| − | = An example of how Bard can be used to generate text =
| |
| − | | |
| − | User: What is the meaning of life?
| |
| − | | |
| − | Bard: The meaning of life is a question that has been pondered by philosophers and theologians for centuries. There is no one answer that will satisfy everyone, but some possible answers include:
| |
| − | | |
| − | To find happiness and fulfillment.
| |
| − | To make a difference in the world.
| |
| − | To learn and grow as a person.
| |
| − | To connect with others and build relationships.
| |
| − | Ultimately, the meaning of life is up to each individual to decide.
| |
| − | | |
| − | User: Write me a poem about love.
| |
| − | | |
| − | Bard: Love is a many splendored thing.
| |
| − | | |
| − | It's the April rose that only grows in the early spring.
| |
| − | | |
| − | Love is nature's way of giving a reason to the rhyme.
| |
| − | | |
| − | Without love, we're just hollow reeds blowing in time.
| |
| − | | |
| − | | |
| − | Love is the dew on the morning grass.
| |
| − | | |
| − | It's the first warm rays of sunshine that shine through the glass.
| |
| − | | |
| − | Love is the song of the bird in the tree.
| |
| − | | |
| − | It's the gentle breeze that blows through me.
| |
| − | | |
| − | | |
| − | Love is the smile on your face.
| |
| − | | |
| − | It's the touch of your hand that makes me feel safe.
| |
| − | | |
| − | Love is the light in your eyes.
| |
| − | | |
| − | It's the reason I'll always rise.
| |
| − | | |
| − | | |
| − | User: Write me a code snippet that prints "Hello, world!"
| |
| − | | |
| − | print("Hello, world!")
| |
| − | | |
| − | As you can see, Bard is a powerful tool that can be used to generate text in a variety of formats.
| |
| − | | |
| − | = Programming =
| |
| − | * [https://blog.google/technology/ai/code-with-bard/ Bard now helps you code | ][[Google]]
| |
| − | * [[Python]] ... [[Generative AI with Python]] ... [[Javascript]] ... [[Generative AI with Javascript]]
| |
| − | * [[Development]] ...[[Development#AI Pair Programming Tools|AI Pair Programming Tools]] ... [[Analytics]] ... [[Visualization]] ... [[Diagrams for Business Analysis]]
| |
| − | * [[Gaming]] ... [[Game-Based Learning (GBL)]] ... [[Games - Security|Security]] ... [[Game Development with Generative AI|Generative AI]] ... [[Metaverse#Games - Metaverse|Metaverse]] ... [[Games - Quantum Theme|Quantum]] ... [[Game Theory]]
| |
| − | * [https://techcrunch.com/2023/04/21/googles-bard-ai-chatbot-can-now-generate-and-debug-code/ Google’s Bard AI chatbot can now generate and debug code | Kirsten Korosec - TechCrunch] ... more than 20 programming languages including C++, Go, Java, [[Javascript|JavaScript]], [[Python]] and TypeScript. Users can export [[Python]] code to [[Google]] [[Colaboratory |Colab]].
| |
| − | * [https://searchengineland.com/you-can-now-use-google-bard-to-help-you-code-395880 You can now use Google Bard to help you code | Barry Schwartz - Search Engine Land]
| |
| − | | |
| − | | |
| − | <youtube>2PsTedmEg-A</youtube>
| |
