Book spamming, sometimes with multiple bogus titles going online in one day, has hit writers like Rory Cellan-Jones submitted by /u/sktafe2020 [link] [comments]

submitted by /u/Kali1020 [link] [comments]

submitted by /u/Soibi0gn [link] [comments]

submitted by /u/Tarzape [link] [comments]

I couldn't find any AI sub dedicated to audio, so I’ve created r/AudioAI to serve as a hub for everything at the intersection of artificial intelligence and the world of sounds. AI-driven music, speech, audio production, and all other AI audio technologies. If anyone wants to be part of mod, let me know! submitted by /u/chibop1 [link] [comments]

I'm doing a project on false positive rate of AI detection on a specific type of written report, and need to check hundreds of reports. Are there AI detection services where I can submit in batches? So far I only have found GPTZero submitted by /u/YellowPikachu [link] [comments]

https://www.youtube.com/shorts/eRj77iZ-czI this is a video I think you will enjoy, the voices are made using AI and also this video does not contain NSFW so don't worry lol, its a joke in the video I don't want to spoil submitted by /u/fabstapizza_YT [link] [comments]

I gave gpt plus on iPhone and still waiting. Is it a country thing? Any Canadians with access? submitted by /u/cacofonie [link] [comments]

submitted by /u/Careful-Piano-9168 [link] [comments]

The most common argument that I see in favor of pushing forward with AI and work automation is that, although many jobs will be lost, many more will be created. Given advancements in the field of AI art is pretty much granted now that soon enough creating art will be fully automated and it won't make sense for businesses to ever employ digital artists save for minuscular tasks like tweaking AI artwork (which can probably be done by very few artists very quickly, reducing the demand for professionals in the field to almost 0). My question then is that once digital art disappears as a career, what job will AI create in it's place? submitted by /u/b_rokal [link] [comments]

Feel free to caption! submitted by /u/GrowlingMutt [link] [comments]

submitted by /u/waLLxAck1 [link] [comments]

submitted by /u/ZenArtOfGaming [link] [comments]

I am working on a telecom dataset where I need to fit a model to for predicting churn(yes or no). There are a lot of categorical data with missing values( total values 7043). What is the best way to handle missing data in this case, is it better to ignore it or any other better imputation method? Data columns (total 21 columns): customerID 7043 non-null object gender 7043 non-null object Age 7043 non-null int64 Partner 7043 non-null object Dependents 7043 non-null object tenure 7043 non-null int64 PhoneService 7043 non-null object MultipleLines 6500 non-null object InternetService 6500 non-null object OnlineSecurity 7043 non-null object OnlineBackup 7043 non-null object DeviceProtection 7043 non-null object TechSupport 7043 non-null object StreamingTV 6500 non-null object StreamingMovies 6500 non-null object Contract 6500 non-null object PaperlessBilling 7043 non-null object PaymentMethod 6500 non-null object MonthlyCharges 7043 non-null float64 TotalCharges 7043 non-null object Churn 7043 non-null object submitted by /u/guyloveskissing [link] [comments]

Podcast Video: https://youtu.be/9hmWPza7dQE Explore the latest developments in the AI world for September 2023. We delve into the burning question: Are Large Language Models (LLMs) poised to replace traditional search engines? Dive into this comprehensive rundown and discover the evolution and future of search in the age of AI. Amazon to Invest $4B in Anthropic Amazon will invest up to $4 billion in Anthropic. The agreement is part of a broader collaboration to develop the industry's most reliable and high-performing foundation models. Anthropic’s frontier safety research and products, together with Amazon Web Services’ (AWS) expertise in running secure, reliable infrastructure, will make Anthropic’s safe and steerable AI widely accessible to AWS customers. AWS will become Anthropic’s primary cloud provider for mission-critical workloads, and this will also expand Anthropic’s support of Amazon Bedrock. Meta to develop a ‘sassy chatbot’ for younger users Meta has plans to develop dozens of chatbot ‘personas’ geared toward engaging young users with more colorful behavior. It also includes ones for celebrities to interact with their fans and some more geared towards productivity, such as to help with coding and other tasks. ​ ​ Meta AI: The new ChatGPT rival was trained on your posts Meta's new AI assistant, a potential rival to ChatGPT, is being trained using public posts from Facebook and Instagram. Meta AI: ChatGPT's Rival Introduction to Meta AI: Launched at Meta Connect 2023, Meta AI aims to become a prominent assistant across platforms such as Instagram, WhatsApp, and Facebook. Capabilities: Beyond just providing information like ChatGPT, it will perform tasks across various platforms and is set to integrate with products like the Ray-Ban Meta smart glasses and Quest 3. Training on Your PostsData: The unique edge of Meta AI comes from its training on public posts from Facebook and Instagram, essentially learning from users' informal content or "sh*tposts." Respecting Privacy: Meta takes care to not use private posts or messages for training, emphasizing the respect of user privacy. ​ ​ The NSA is establishing an “Artificial Intelligence Security Center” The NSA is creating a new center focused on promoting secure AI development and defending U.S. advances from foreign adversaries aiming to co-opt the technology. The AI Security Center: Aims to help spur the secure integration of AI capabilities. Will develop best practices and risk management frameworks.goal is to understand and combat threats to U.S. AI advances. Motivations: The U.S. currently leads in AI, but the advantage is precarious. Adversaries have long stolen intellectual property.Agencies are adopting AI rapidly across missions.I will work with industry, labs, and academia on priorities. It comes after an NSA study showed the need to prioritize security.Must understand AI vulnerabilities and counter-threats. TL;DR: The NSA is establishing an AI Security Center to promote secure development and adoption of AI while defending U.S. progress from adversaries aiming to exploit the technology. LongLoRA: Efficient fine-tuning of long-context LLMs New research has introduced LongLoRA, an ultra-efficient fine-tuning method designed to extend the context sizes of pre-trained LLMs without a huge computation cost.Typically, training LLMs with longer context sizes consumes a lot of time and requires strong GPU resources. For example, extending the context length from 2048 to 8192 increases computational costs 16 times, particularly in self-attention layers. LongLoRA makes it way cheaper by: 1. Using sparse local attention instead of dense global attention (optional at inference time). 2. Using LoRA (Low-Rank Adaptation) for context extension This approach seems both easy to use and super practical. LongLoRA performed strongly on various tasks using LLaMA-2 models ranging from 7B/13B to 70B. Notably, it extended LLaMA-2 7B from 4k context to 100k and LLaMA-2 70B to 32k on a single 8x A100 machine, all while keeping the original model architectures intact. Biggest Boom in AI: ChatGPT Talks and Beyond OpenAI is introducing voice and image capabilities in ChatGPT, allowing users to have voice conversations and show images to ChatGPT. This new feature offers a more intuitive interface and expands the ways in which ChatGPT can be used. Users can have live conversations about landmarks, get recipe suggestions by showing pictures of their fridge, and even receive math problem hints by sharing photos. The voice and image capabilities will be rolled out to Plus and Enterprise users over the next two weeks, with voice available on iOS and Android and images available on all platforms. ChatGPT can now comprehend images, including photos, screenshots, and text-containing documents, using its language reasoning abilities. You can also discuss multiple images and utilize their new drawing tool to guide you. Getty Images’s new AI art tool powered by NVIDIA Getty Images has launched a generative AI art tool called Generative AI, which uses an AI model provided by Nvidia to render images from text descriptions. The tool is designed to be "commercially safer" than rival solutions, with safeguards to prevent disinformation and copyright infringement. Getty Images will compensate contributors whose work is used to train the AI generator and share revenues generated from the tool. The tool can be accessed on Getty's website or integrated into apps and websites through an API, with pricing based on prompt volume. Other companies, including Bria and Shutterstock, are also exploring ethical approaches to generative AI. AWS has announced 5 major generative AI updates and innovations Amazon Bedrock is now generally available.Amazon Titan Embeddings is now generally available. **Meta’s Llama 2 is coming to Amazon Bedrock in the next few weeks. **New Amazon CodeWhisperer capability is coming soon, will allow customers to securely customize CodeWhisperer suggestions using their private code base to unlock new levels of developer productivity. New generative BI authoring capabilities in Amazon QuickSight to help business analysts easily create and customize visuals using natural-language commands. Colossal-AI’s commercial-free LLM saving thousands Colossal-AI has released Colossal-LLaMA-2, an open-source and commercial-free domain-specific language model solution. It uses a relatively small amount of data and training time, resulting in lower costs. The Chinese version of LLaMA-2 has outperformed competitors in various evaluation benchmarks. The release includes improvements such as vocabulary expansion, a data cleaning system, and a multi-stage pre-training scheme to enhance Chinese and English abilities. ​ OpenAI eyes $90B valuation, dives into AI hardware OpenAI is in discussions to possibly sell shares, a a move that would boost its valuation from $29 billion to somewhere between $80 billion and $90 billion, according to a Wall Street Journal report citing people familiar with the talks.In other news, Apple's former design chief, Jony Ive, and OpenAI CEO, Sam Altman, have reportedly been discussing building a new AI hardware device. It is unclear what the device would be or if they will build it, but the duo has been discussing what new hardware for the AI age could look like. Vectara launches Boomerang, the next-gen LLM redefining GenAI accuracy Outpacing major competitors, Boomerang sets a new benchmark in Grounded Generative AI for business applications. It is a next-generation neural information retrieval model integrated into Vectara's GenAI platform.Boomerang surpasses Cohere in benchmark performance and matches OpenAI on certain metrics, excelling particularly in multilingual benchmarks. Notably, it prioritizes security, reducing bias, copyright concerns, and "hallucinations" in AI-generated content. It also offers cross-lingual support for hundreds of languages and dialects and improves prompt understanding, leading to more accurate and faster responses. Google's 25-year AI legacy guides its future AI innovations On its 25th birthday, Google reflected on its two-and-a-half decades of pioneering achievements in the field of AI. It started in 2001 using a simple ML to suggest better spellings for web searches.A standout moment in 2023 was the introduction of PaLM 2 and Gemini. It is now looking forward to these models driving the next quarter-century of its AI advancements. Google’s AI for hyper-personalized Maps Google and DeepMind have built an AI algorithm to make route suggestions in Google Maps more personalized. It includes 360 million parameters and uses real driving data from Maps users to analyze what factors they consider when making route decisions. The AI calculations include information such as travel time, tolls, road conditions, and personal preferences.The approach uses Inverse Reinforcement Learning (IRL), which learns from user behavior, and Receding Horizon Inverse Planning (RHIP), which uses different AI techniques for short- and long-distance travel. Tests show that RHIP improves the accuracy of suggested routes for two-wheelers by 16 to 24 percent and should get better at predicting which route they prefer over time. The Rise and Potential of LLM-Based Agents: A survey Probably the most comprehensive overview of LLM-based agents, this survey-cum-research covers everything from how to construct AI agents to how to harness them for good. It starts by tracing the concept of agents from its philosophical origins to its development in AI and explains why LLMs are suitable foundations for AI agents. It also:Presents a conceptual framework for LLM-based agents that can be tailored to suit different applicationsExplores the extensive applications of LLM-based agents in three aspects: single-agent scenarios, multi-agent scenarios, and human-agent cooperationDelve into agent societies, exploring the behavior and personality of LLM-based agents, the social phenomena that emerge when they form societies, and the insights they offer for human societyDiscuss a range of key topics and open problems within the fieldHere’s a scenario of an envisioned society composed of AI agents in which humans can also participate. AI makes it easy to personalize 3D-printable models MIT researchers have developed a generative AI-driven tool that enables the user to add custom design elements to 3D models without compromising the functionality of the fabricated objects. A designer could use this tool, called Style2Fab, to personalize 3D models of objects using only natural language prompts to describe their desired design. The user could then fabricate the objects with a 3D printer. Google Bard’s best version yet Google is rolling out Bard’s most capable model yet. Here are the new features:Bard Extensions in English- With Extensions, Bard can find and show you relevant information from the Google tools you use every day — like Gmail, Docs, Drive, Google Maps, YouTube, and Google Flights and hotels — even when the information you need is across multiple apps and services. Bard’s “Google it”- You can now double-check its answers more easily. When you click on the “G” icon, Bard will read the response and evaluate whether there is content across the web to substantiate it.Shared conversations- When someone shares a Bard chat with you through a public link, you can continue the conversation, ask additional questions, or use it as a starting point for new ideas.Expanded access to existing English language features- Access features such as uploading images with Lens, getting Search images in responses, and modifying Bard’s responses– to 40+ languages.These features were possible because of new updates made to the PaLM 2 model. Intel’s ‘AI PC’ can run generative AI chatbots directly on laptops Intel’s new chip, due in December, will be able to run a generative AI chatbot on a laptop rather than having to tap into cloud data centers for computing power. It is made possible by new AI data-crunching features built into Intel's forthcoming "Meteor Lake" laptop chip and from new software tools the company is releasing.Intel also demonstrated laptops that could generate a song in the style of Taylor Swift and answer questions in a conversational style, all while disconnected from the Internet. Moreover, Microsoft's Copilot AI assistant will be able to run on Intel-based PCs. DeepMind’s new AI can predict genetic diseases Google DeepMind’s new system, called AlphaMissense, can tell if the letters in the DNA will produce the correct shape. If not, it is listed as potentially disease-causing.Currently, genetic disease hunters have fairly limited knowledge of which areas of human DNA can lead to disease and have to search across billions of chemical building blocks that make up DNA. They have classified 0.1% of letter changes, or mutations, as either benign or disease-causing. DeepMind's new model pushed that percentage up to 89%. OpenAI unveils DALL·E 3 OpenAI has unveiled its new text-to-image model, DALL·E 3, which can translate nuanced requests into extremely detailed and accurate images. Here’s all you need to know:DALL·E 3 is built natively on ChatGPT, which lets you use ChatGPT to generate tailored, detailed prompts for DALL·E 3. If it’s not quite right, you can ask ChatGPT to make tweaks.Even with the same prompt, DALL·E 3 delivers significant improvements over DALL·E 2, as shown below (Left: DALL·E 2 results, Right: DALL·E 3). The prompt: “An expressive oil painting of a basketball player dunking, depicted as an explosion of a nebula.”OpenAI has taken steps to limit DALL·E 3’s ability to generate violent, adult, or hateful content.DALL·E 3 is designed to decline requests that ask for an image in the style of a living artist. Creators can also opt their images out from training of OpenAI’s future image generation models.DALL·E 3 is now in research preview and will be available to ChatGPT Plus and Enterprise customers in October via the API and in Labs later this fall. Amazon brings Generative AI to Alexa and Fire TV At its annual devices event, Amazon announced a few AI updates:It will soon use a new generative AI model to power improved experiences across its Echo family of devices. The new model is specifically optimized for voice and will take into account body language as well as a person’s eye contact and gestures for more powerful conversational experiences.It also introduced generative AI updates for its Fire TV voice search, which promises to bring more conversational ways to interact with Alexa and discover new content based on specifics. DeepMind’s says language modeling is compression In recent years, the ML community has focused on training increasingly large and powerful self-supervised (language) models. Since these LLMs exhibit impressive predictive capabilities, they are well-positioned to be strong compressors.This interesting research by Google DeepMind and Meta evaluates the compression capabilities of LLMs. It investigates how and why compression and prediction are equivalent. It shows that foundation models, trained primarily on text, are general-purpose compressors due to their in-context learning abilities. For example, Chinchilla 70B achieves compression rates of 43.4% on ImageNet patches and 16.4% on LibriSpeech samples, beating domain-specific compressors like PNG (58.5%) or FLAC (30.3%), respectively.Are you eager to expand your understanding of artificial intelligence? Look no further than the essential book "AI Unraveled: Demystifying Frequently Asked Questions on Artificial Intelligence," available at Apple, Google, or Amazon today at https://amzn.to/3ZrpkCu NVIDIA’s new software boosts LLM performance by 8x NVIDIA has developed a software called TensorRT-LLM to supercharge LLM inference on H100 GPUs. It includes optimized kernels, pre- and post-processing steps, and multi-GPU/multi-node communication primitives for high performance. It allows developers to experiment with new LLMs without deep knowledge of C++ or NVIDIA CUDA. The software also offers an open-source modular Python API for easy customization and extensibility. Additionally, it allows users to quantize models to FP8 format for better memory utilization. TensorRT-LLM aims to boost LLM deployment performance and is available in early access, soon to be integrated into the NVIDIA NeMo framework. Users can apply for access through the NVIDIA Developer Program, with a focus on enterprise-grade AI applications. Google Deepmind introduces language models as optimizers Google DeepMind introduces the concept of using language models as optimizers, This work is called Optimization by PROmpting (OPRO). This new approach describes the optimization problem in natural language. The models are trained to generate new solutions based on a defined problem and previously found solutions.This is applied to linear regression, traveling salesman problems, and prompt optimization tasks. The results show that the prompts optimized by OPRO outperform human-designed prompts by up to 8% on GSM8K and up to 50% on Big-Bench Hard tasks. Meta plans to rival OpenAI's GPT-4 with its new model Meta is reportedly planning to train a new chatbot model that it hopes will rival OpenAI's GPT-4. The company is acquiring Nvidia H100 AI-training chips, so they won’t need to rely on Microsoft’s Azure cloud platform to train the new chatbot. Meta is expanding its data centers to create a more powerful chatbot. CEO Mark Zuckerberg wants the model to be free for companies to create AI tools. Meta is building the model to speed up the creation of AI tools that can emulate human expressions. Google's responsible AI leap Google is launching the Digital Futures Project and a $20 million Google.org fund, which will provide grants to leading think tanks and academic institutions worldwide. The project will support researchers, organize convenings, and foster debate on public policy solutions to encourage the responsible development of AI.Inaugural grantees of the Digital Futures Fund include the Aspen Institute, Brookings Institution, Carnegie Endowment for International Peace, the Center for a New American Security, the Institute for Security and Technology, SeedAI, and more. The fund will support institutions from countries around the globe. Microsoft, MIT, and Google transformed entire Project Gutenberg Collection into audiobooks In a new research called Large-Scale Automatic Audiobook Creation, Microsoft, MIT, and Google collaborated to transform the entire Project Gutenberg Collection into audiobooks. The library now boasts thousands of free and open audiobooks powered by AI. Utilizing recent advances in neural text-to-speech, the team achieved exceptional quality of voice acting. The system also allows users to customize an audiobook's speaking speed and style, emotional intonation, and can even match a desired voice using a small amount of sample audio. Amazon, Nvidia, Microsoft, and Google lead hiring surge in GenAI There is an explosive demand for Generative AI talent today. Here are some compelling statistics.The number of companies mentioning “Generative AI” in monthly job postings is increasing exponentially.Tech giants leading the surge in hiring for GenAI talent include Amazon, Nvidia, Oracle, Microsoft, Google, and more. Big banks like Citigroup and CapitalOne are also hiring big in GenAI.Unsurprisingly, technology is the #1 sector looking to hire GenAI experts. Finance is #2nd, and healthcare is #3, while demand has been tepid in sectors like real estate, basic materials, and energy.Companies are paying a lot for GenAI talent! Among all technical skills/technologies tracked, jobs mentioning “Generative AI” or “LLMs” had the highest average base salary offered, with an average of $200,837/year. Apple silently making AI moves Apple is quietly incorporating artificial intelligence into its new iPhones and watches to improve basic functions. The company showcased new gadgets with improved semiconductor designs that power AI features, such as better call quality and image capture. Apple's AI efforts have been reshaping its core software products behind the scenes without explicitly mentioning AI at its developer conference. Apple's new watch chip includes a four-core "Neural Engine" that enhances Siri's accuracy by 25% and enables new ways to interact with the device. The iPhone also automatically recognizes people in the frame for improved image capture. Salesforce’s Einstein can customize AI for you Salesforce introduced Einstein Copilot Studio, which allows customers to customize their AI offerings. The tool consists of three elements: prompt builder, skills builder, and model builder.With the prompt builder, customers can add their own custom prompts for their products or brands. The skills builder enables companies to add actions to prompts, such as competitor analysis or objection handling. The model builder allows customers to bring their own models or use supported third-party offerings.Salesforce is also working on a system called "the Einstein Trust Layer" to address issues like bias and inappropriate responses. NExT-GPT advances human-like AI research The NExT-GPT system is a multimodal language model that can understand and generate content in various modalities, such as text, images, videos, and audio. It fills the gap in existing models by allowing for any multimodal understanding and generation.NExT-GPT leverages pre-trained encoders and decoders, requiring only a small amount of parameter tuning. It also introduces a modality-switching instruction tuning (MosIT) and a curated dataset for complex cross-modal understanding. Meta AI's New Dataset Understands 122 Languages Meta AI announced Belebele, a multilingual reading comprehension dataset with 122 language variants. It allows for evaluating text models in high, medium, and low-resource languages, expanding the language coverage of natural language understanding benchmarks.The Belebele dataset consists of questions based on short passages from the Flores-200 dataset, with four multiple-choice answers. The questions were designed to test different levels of general language comprehension. The dataset enables direct comparison of model performance across all languages and was used to evaluate multilingual masked language models and large language models. The results show that smaller multilingual models perform better in understanding multiple languages. Stability AI’s 1st Japanese Vision-Language Model Stability AI has released Japanese InstructBLIP Alpha, a vision-language model that generates textual descriptions for input images and answers questions about them. It is built upon the Japanese StableLM Instruct Alpha 7B and leverages the InstructBLIP architecture.The model can accurately recognize Japan-specific objects and process text input, such as questions. It is available on Hugging Face Hub for inference and additional training, exclusively for research. This model has various applications, including search engine functionality, scene description, and providing textual descriptions for blind individuals. Transformers as Support Vector Machines This paper establishes a formal equivalence between the optimization geometry of self-attention in transformers and a hard-margin Support Vector Machine (SVM) problem. It shows that optimizing the attention layer of transformers converges towards an SVM solution that minimizes the nuclear norm of the combined parameter. The study also proves the convergence of gradient descent under suitable conditions and introduces a more general SVM equivalence for nonlinear prediction heads. These findings suggest that transformers can be interpreted as a hierarchy of SVMs that separate and select optimal tokens. ​ Amazon’s AI-powered palm recognition breakthrough Amazon One is a fast, convenient, and contactless device that lets customers use the palm of their hand for everyday activities like paying at a store, presenting a loyalty card, verifying their age, or entering a venue. No phone, no wallet.Amazon One does this by combining generative AI, machine learning, cutting-edge biometrics, and optical engineering.Currently, Amazon One is being rolled out to more than 500 Whole Foods Market stores and dozens of third-party locations, including travel retailers, sports and entertainment venues, convenience stores, and grocers. It can also detect fake hands and reject them. It has already been used over 3 million times with 99.9999% accuracy. Intel is going after the AI opportunity in multiple ways Intel is aggressively pursuing opportunities in the AI space by expanding beyond data center-based AI accelerators. CEO Pat Gelsinger believes that AI will move closer to end-users due to economic, physical, and privacy considerations. They are incorporating AI into various products, including server CPUs like Sapphire Rapids, which come with built-in AI accelerators for inference tasks.Furthermore, Intel is set to launch Meteor Lake PC CPUs with dedicated AI hardware to accelerate AI workloads directly on user devices. This approach aligns with Intel's dominant position in the CPU market, making it attractive for software providers to support their AI hardware. Introducing Refact Code LLM, for real-time code completion and chat Refact LLM 1.6B model is primarily for real-time code completion (infill) in multiple programming languages and works as a chat. It achieves the state-of-the-art performance among the code LLMs, coming closer to HumanEval as Starcoder while being 10x smaller in size. It also beats other code models, as shown below. First, a tl;dr1.6b parameters20 programming languages4096 tokens contextcode completion and chat capabilitiespre-trained on permissive licensed code and available for commercial use Google Deepmind’s new AI benchmark on bioinformatics code Google Deepmind and Yale University researchers have introduced BioCoder, a benchmark for testing the ability of AI models to generate bioinformatics-specific code. BioCoder includes 2,269 coding problems based on functions and methods from bioinformatics GitHub repositories. In tests with several code generators, including InCoder, CodeGen, SantaCoder, and ChatGPT, OpenAI's GPT-3.5 Turbo performed exceptionally well in the benchmark. The team plans to explore other open models, such as Meta's LLamA2, in future tests. CityDreamer - New Gen AI model creates unlimited 3D cities CityDreamer is a generative AI model that can create unlimited 3D cities by separating the generation of buildings from other background objects. This allows for better handling of the diverse appearance of buildings in urban environments. The model uses two datasets, OSM and GoogleEarth, to enhance the realism of the generated cities. These datasets provide realistic city layouts and appearances that can be easily scaled to other cities worldwide. Scientists train a neural network to identify PC users’ fatigue Scientists from St. Petersburg University and other organizations have created a database of eye movement strategies of PC users in different states of fatigue. They plan to use this data to train neural network models that can accurately track the functional state of operators, ensuring safety in various industries. The database includes a comprehensive set of indicators collected through sensors such as video cameras, eye trackers, heart rate monitors, and electroencephalographs. Introducing Falcon 180B, largest and most powerful open LLM UAE’s Technology Innovation Institute (TII) has released Falcon 180B, a new state-of-the-art for open models. It is the largest openly available language model, with 180 billion parameters, trained on a massive 3.5 trillion tokens using TII's RefinedWeb dataset. It's currently at the top of the Hugging Face Leaderboard for pre-trained Open LLMs and is available for both research and commercial use.The model performs exceptionally well in various tasks like reasoning, coding, proficiency, and knowledge tests, even beating competitors like Meta's LLaMA 2. Among closed-source models, it ranks just behind OpenAI's GPT 4 and performs on par with Google's PaLM 2 Large, which powers Bard, despite being half the model's size. Apple is spending millions of dollars a day to train AI Reportedly, Apple has been expanding its budget for building AI to millions of dollars a day. It has a unit of around 16 members, including several former Google engineers, working on conversational AI. It is working on multiple AI models to serve a variety of purposes.Apple wants to enhance Siri to be your ultimate digital assistant, doing multi-step tasks without you lifting a finger and using voice commands.It is developing an image generation model and is researching multimodal AI, which can recognize and produce images or video as well as text.A chatbot is in the works that would interact with customers who use AppleCare. Microsoft and Paige to build the largest image-based AI model to fight cancer Paige, a technology disruptor in healthcare, has joined forces with Microsoft to build the world’s largest image-based AI models for digital pathology and oncology.Paige developed the first Large Foundation Model using over one billion images from half a million pathology slides across multiple cancer types. Now, it is developing a new AI model with Microsoft that is orders-of-magnitude larger than any other image-based AI model existing today, configured with billions of parameters.Paige will utilize Microsoft’s advanced supercomputing infrastructure to train the technology at scale and ultimately deploy it to hospitals and laboratories across the globe using Azure. ​ The difference between AI creativity and human creativity, and how it is rapidly narrowing. While many consider human creativity to be truly original and superior in results, it appears boundaries between AI-generated content and human creativity are becoming increasingly blurred. And it's looking increasingly likely that AI may soon be at par with humans in creative content generation. Let's look at a quick comparison between humans and ChatGPT to understand this: Sources: https://enoumen.com/2023/09/02/emerging-ai-innovations-top-trends-shaping-the-landscape-in-september-2023/ ​ --------- Are you eager to expand your understanding of artificial intelligence? Look no further than the essential book "AI Unraveled: Demystifying Frequently Asked Questions on Artificial Intelligence," available at Apple, Google, or Amazon today at https://amzn.to/3ZrpkCu ------ Simplify Content Creation and Management with Notice Looking for a no-code tool to easily create and publish content? With Notice, generate custom FAQs, blogs, and wikis tailored to your business with AI in a single click.Create, manage, and translate - all in one place. Collaborate with your team, and publish content across platforms, including CMS, HTML, or hosted versions.Plus, you can enjoy cookie-free analytics to gain insights about users and enhance SEO with Notice's smart blocks. Use code DIDYOUNOTICE30SPECIAL for a 30% discount on any subscription.TRY IT & ENJOY 30% OFF at https://notice.studio/?via=etienne submitted by /u/enoumen [link] [comments]

submitted by /u/giga [link] [comments]

Thoughts on why the image looks like a hyperbolized take on inclusivity and diversity? It makes me wonder if it has to do with the fact ai is programmed to be very inclusive and positive that it kind of sneaks that in by default. submitted by /u/monkeyballpirate [link] [comments]

submitted by /u/No-Coat-7417 [link] [comments]

submitted by /u/zalapaauditt [link] [comments]

submitted by /u/GeoffAO2 [link] [comments]

Here's the publication. Fascinating. The pace of AI advancement continues to boggle my mind. submitted by /u/JOWWLLL [link] [comments]

submitted by /u/redditfriendguy [link] [comments]

submitted by /u/Cosmagroth [link] [comments]

submitted by /u/AmanChourasia [link] [comments]

After the ChatGPT release in November, there was a WINTER of EXCITEMENT. Then, there was a SPRING of METAPHORS when we attempted to explain the power of AI using analogies to what we already understand. Analogies were more on the side of fear and warnings. You followed a series of 'Recycling Ideas', part of SUMMER of REFLECTIONS. The AUTUMN OF CLARITY has arrived. Follow more... https://www.linkedin.com/pulse/four-ai-seasons-start-autumn-clarity-jovan-kurbalija/?published=t submitted by /u/CortoMalteze01 [link] [comments]

How, outside of testing, do you estimate how quickly a specific model will run on some hardware? Anything about time is rarely mentioned in papers and if it is, it's more likely to talk about training, unless authors are specifically proud of their speed (like YOLO). Even less so in any README. Some way to translate numbers of parameters into seconds on a given GPU/CPU, any rules of thumb better than just setting up everything every time? submitted by /u/teleoflexuous [link] [comments]

submitted by /u/zyunztl [link] [comments]

Context length (memory) has been doubled for the website. From 4k to 8k. At least for me. How do I know? I routinely test memory with openai’s tokenizer which counts the number of words the AI sees in my text. Past 4k the AI forgets past messages. I summarized a 7k piece of text no problem today. The API always had 8k memory but it uses up credits beyond my subscription pay so its not popular for general public. This update is huge. Now GPT should be able to understand whole science papers. For some of you API users this isnt big but it is for changing the general public’s perception of what GPT4 can really do. With this context length you can even do some fine tuning and train new abilities. Unless for some reason im the only one who got this update? If u want to test urself u can search for openai tokenizer, then ask gpt4 “what was my first message?” submitted by /u/AGIbydecember2023 [link] [comments]

submitted by /u/ToadLugosi [link] [comments]

Major AI announcements from Meta, Amazon, Google this week. Amazon to Invest $4B in Anthropic - Amazon will invest up to $4 billion in Anthropic. The agreement is part of a broader collaboration to develop the industry's most reliable and high-performing foundation models. - Anthropic’s frontier safety research and products, together with Amazon Web Services’ (AWS) expertise in running secure, reliable infrastructure, will make Anthropic’s safe and steerable AI widely accessible to AWS customers. AWS will become Anthropic’s primary cloud provider for mission-critical workloads, and this will also expand Anthropic’s support of Amazon Bedrock. Meta to develop a ‘sassy chatbot’ for younger users - Meta has plans to develop dozens of chatbot ‘personas’ geared toward engaging young users with more colorful behavior. It also includes ones for celebrities to interact with their fans and some more geared towards productivity, such as to help with coding and other tasks. LongLoRA: Efficient fine-tuning of long-context LLMs - New research has introduced LongLoRA, an ultra-efficient fine-tuning method designed to extend the context sizes of pre-trained LLMs without a huge computation cost. - Typically, training LLMs with longer context sizes consumes a lot of time and requires strong GPU resources. For example, extending the context length from 2048 to 8192 increases computational costs 16 times, particularly in self-attention layers. LongLoRA makes it way cheaper by: Using sparse local attention instead of dense global attention (optional at inference time). Using LoRA (Low-Rank Adaptation) for context extension This approach seems both easy to use and super practical. LongLoRA performed strongly on various tasks using LLaMA-2 models ranging from 7B/13B to 70B. Notably, it extended LLaMA-2 7B from 4k context to 100k and LLaMA-2 70B to 32k on a single 8x A100 machine, all while keeping the original model architectures intact. Biggest Boom in AI: ChatGPT Talks and Beyond - OpenAI is introducing voice and image capabilities in ChatGPT, allowing users to have voice conversations and show images to ChatGPT. This new feature offers a more intuitive interface and expands the ways in which ChatGPT can be used. - Users can have live conversations about landmarks, get recipe suggestions by showing pictures of their fridge, and even receive math problem hints by sharing photos. The voice and image capabilities will be rolled out to Plus and Enterprise users over the next two weeks, with voice available on iOS and Android and images available on all platforms. - ChatGPT can now comprehend images, including photos, screenshots, and text-containing documents, using its language reasoning abilities. You can also discuss multiple images and utilize their new drawing tool to guide you. Getty Images’s new AI art tool powered by NVIDIA - Getty Images has launched a generative AI art tool called Generative AI, which uses an AI model provided by Nvidia to render images from text descriptions. The tool is designed to be "commercially safer" than rival solutions, with safeguards to prevent disinformation and copyright infringement. - Getty Images will compensate contributors whose work is used to train the AI generator and share revenues generated from the tool. The tool can be accessed on Getty's website or integrated into apps and websites through an API, with pricing based on prompt volume. Other companies, including Bria and Shutterstock, are also exploring ethical approaches to generative AI. Colossal-AI’s commercial-free LLM saving thousands - Colossal-AI has released Colossal-LLaMA-2, an open-source and commercial-free domain-specific language model solution. It uses a relatively small amount of data and training time, resulting in lower costs. The Chinese version of LLaMA-2 has outperformed competitors in various evaluation benchmarks. - The release includes improvements such as vocabulary expansion, a data cleaning system, and a multi-stage pre-training scheme to enhance Chinese and English abilities. OpenAI eyes $90B valuation, dives into AI hardware - OpenAI is in discussions to possibly sell shares, a a move that would boost its valuation from $29 billion to somewhere between $80 billion and $90 billion, according to a Wall Street Journal report citing people familiar with the talks. - In other news, Apple's former design chief, Jony Ive, and OpenAI CEO, Sam Altman, have reportedly been discussing building a new AI hardware device. It is unclear what the device would be or if they will build it, but the duo has been discussing what new hardware for the AI age could look like. Vectara launches Boomerang, the next-gen LLM redefining GenAI accuracy - Outpacing major competitors, Boomerang sets a new benchmark in Grounded Generative AI for business applications. It is a next-generation neural information retrieval model integrated into Vectara's GenAI platform. - Boomerang surpasses Cohere in benchmark performance and matches OpenAI on certain metrics, excelling particularly in multilingual benchmarks. Notably, it prioritizes security, reducing bias, copyright concerns, and "hallucinations" in AI-generated content. It also offers cross-lingual support for hundreds of languages and dialects and improves prompt understanding, leading to more accurate and faster responses. Google's 25-year AI legacy guides its future AI innovations - On its 25th birthday, Google reflected on its two-and-a-half decades of pioneering achievements in the field of AI. It started in 2001 using a simple ML to suggest better spellings for web searches. A standout moment in 2023 was the introduction of PaLM 2 and Gemini. It is now looking forward to these models driving the next quarter-century of its AI advancements. Meta’s new exciting AI experiences & tools - Meta's new AI features include an AI Assistant powered by Bing, It will provide real-time information and generate photorealistic images from text prompts. Meta used specialized datasets to train the AI to respond in a conversational and friendly tone. The first extension of the AI Assistant will be web search. The AI Assistant will be available in beta on WhatsApp, Messenger, and Instagram. - Introduced 28 AI personality chatbots based on celebrities, such as Tom Brady, Naomi Osaka, Mr. Beast, and more. These chatbots, accessible on platforms like WhatsApp, Messenger, and Instagram, provide topic-specific conversations but are currently text-based, with plans to introduce audio capabilities. These AI personalities were created using Llama 2. Meta aims to integrate Bing search functionality in the future. The chatbots' animations are generated through AI techniques, offering a cohesive visual experience. - Launching AI Studio, a platform allowing businesses to build AI chatbots for Facebook, Instagram, and Messenger, initially focusing on Messenger for e-commerce and customer support apps. This toolkit will be available in alpha. - Gen AI stickers powered by Emu allow users to create unique stickers across its messaging apps. Users can type in their desired image descriptions, and Emu generates multiple sticker options in just a few seconds. Initially available to English-language users, this feature will roll out over the next month. - Introducing 2 new AI Instagram features, restyle and backdrop. Restyle allows users to transform the visual styles of their images by entering prompts like "watercolor" or more. While backdrop changes the background of photos using prompts. - Launches New-gen Ray-Ban smart glasses, in partnership with EssilorLuxottica, will feature improved audio and cameras, over 150 different custom frame and lens combinations. They’re lighter and more comfortable. Will enable livestream to Facebook or Instagram and use “Hey Meta” to engage with Meta AI assistant by voice. OpenAI links ChatGPT with Internet - ChatGPT is back with internet browsing, It can now browse the internet to provide current & reliable information, along with direct links to sources. This update addresses feedback received since the browsing feature was launched in May. The model now follows robots.txt and identifies user agents to respect website preferences. - Currently available to Plus and Enterprise users, browsing will be expanded to all users soon. To try it out, enable Browse in your beta features setting: Click on 'Profile & Settings’ > Select 'Beta features' > Toggle on ‘Browse with Bing’ > Choose Browse with Bing in the selector under GPT-4. Mistral AI’s LLM outperforms Meta’s Llama2 13B - Mistral AI, Europe's largest seeded startup, has released its first LLM Mistral 7B. This model outperforms Meta's Llama 2 13B and is touted as the most powerful language model for its size. It was founded by alums from Google's DeepMind and Meta earlier this year. It aims to make AI useful for enterprises by using publicly available data and customer contributions. - Mistral 7B excelled in benchmarks, surpassing Llama 2 7B and 13B in text summarization, classification, and code completion tasks. The only area where Llama 2 13B matched Mistral 7B was world knowledge testing. AWS announces powerful new AI offerings Amazon Web Services (AWS) has announced 5 major generative AI updates and innovations. Amazon Bedrock is now generally available. It is a fully managed service that makes foundation models (FMs) from leading AI companies available through a single API. It also has new AI models in the mix and will help more customers build and scale generative AI applications. Amazon Titan Embeddings is now generally available. It is an LLM that makes it easier for customers to start with Retrieval-Augmented Generation (RAG) to extend the power of any FM using their proprietary data. Meta’s Llama 2 is coming to Amazon Bedrock in the next few weeks. Amazon Bedrock is the first fully managed generative AI service to offer Llama 2 through a managed API. Currently, it includes models from 21 Labs, Anthropic, Cohere, Stability AI, and Amazon. New Amazon CodeWhisperer capability is coming soon. It will allow customers to securely customize CodeWhisperer suggestions using their private code base to unlock new levels of developer productivity. Trained on billions of lines of Amazon and publicly available code, Amazon CodeWhisperer is an AI-powered coding companion. New Generative BI authoring capabilities to extend the natural-language querying of Amazon QuickSight Q beyond answering well-structured questions. It will help analysts quickly create customizable visuals from question fragments, clarify the intent of a query by asking follow-up questions, refine visualizations, and complete complex calculations. Meta introduces LLAMA 2 Long - In a new research, Meta presents a series of long-context LLMs that support effective context windows of up to 32,768 tokens. The models are built through continual pretraining from Llama 2 with longer training sequences and on a dataset where long texts are upsampled. - On research benchmarks, the models achieve consistent improvements on most regular tasks and significant improvements on long-context tasks over Llama 2. Notably, with a cost-effective instruction tuning procedure that does not require human-annotated long instruction data, the 70B variant can already surpass gpt-3.5-turbo-16k's overall performance on a suite of long-context tasks. Google announces Google-Extended and opens SGE to teens - Google introduced Google-Extended, a new control that web publishers can use to manage whether their sites help improve Bard and Vertex AI generative APIs, including future generations of models that power those products. This will allow publishers to control access to content on their site to train these AI models. - In another update, Google has opened up access to SGE in Search Labs to more people, specifically teens (ages 13-17) in the U.S., so they too can benefit from generative AI's helpful capabilities. Informed by research and experts in teen development, Google has built additional safeguards into the experience. For instance, to prevent inappropriate or harmful content from surfacing. And there was more… Microsoft’s mobile keyboard app SwiftKey gains new AI-powered features: It will now include AI camera lenses, AI stickers, an AI-powered editor, and the ability to create AI images from the app. Google Pixel 8’s latest leak shows off big AI camera updates: AI photo editing with Magic Editor will enable you to remake any picture you take. DSLR-style manual camera controls will let you tweak the shutter speed and ISO of an image and a focus slider. A drinks company in Poland appoints AI robot as 'experimental’ CEO: Dictador, best known for its rums, has appointed the robot to oversee the company’s growth into one-off collectables, communication, or even strategy planning. It is named Mika. ElevenLabs launches free book classics narrated by high-quality AI voices: It presents 6 classic stories told by compelling AI voices in multiple languages, including "Winnie the Pooh" and "The Picture of Dorian Gray." The entire recording process took only one day. Salesforce to acquire Airkit.ai, a low-code platform to build AI customer service agents: The GPT-4-based platform allows e-commerce companies to build specialized customer service chatbots that can deal with queries around order status, refunds, product information, and more. Tesla’s humanoid robot Optimus can now sort objects autonomously: Using its end-to-end trained neural network. The robot can calibrate itself using joint position encoders and vision to locate its limbs precisely. It can then sort colored blocks into their respective trays, even adapting to dynamic changes in the environment. Snapchat partners with Microsoft to insert ads into its AI chatbot feature, My AI: It offers link suggestions related to user conversations. The partnership is a win for Microsoft's ads business and could position Snapchat as a platform for Gen Z users to search for products and services through AI chats. Spotify is testing a voice translation feature for podcasts, using AI to translate content into different languages: By offering translated podcasts from popular hosts like Dax Shepard and Lex Fridman, Spotify hopes to expand its global reach and cater to a wider audience. Google's Bard now has new capabilities to help travelers plan their vacations: Connecting with various Google applications like Gmail, Google Flights, and Google Maps, It can provide personalized assistance throughout the trip. Users can ask Bard to find flight and hotel information, get directions, watch YouTube videos, and even check dates that work for everyone involved. Correcto has raised $7M in seed funding to expand its language writing tool for Spanish speakers: While AI tools like ChatGPT can generate text in Spanish, Correcto believes its tool offers better quality and provides opportunities for individual learning. The company plans to target enterprise customers while offering a freemium version for individual users. SAP launches its own enterprise AI assistant, Joule: Built into the entirety of SAP’s extensive cloud enterprise suite, Joule will allow customers to access it across SAP apps and programs, similar to Microsoft’s new Windows Copilot. It will also be available across computing platforms, on desktop and mobile. Microsoft uses AI to boost Windows 11 security, pushes for passwordless future: It announced new enterprise security features that use AI to help defend Windows 11 against increasingly sophisticated cyberattacks. The new AI capabilities may reduce security incidents by 60% and firmware attacks by 300%. Shopify releases SDXL background replacement tool for product imagery: It is a super helpful tool that can create a whole new reality around your product. Its public HF Space is under the official Shopify account. Infosys ties with Microsoft for industry-wide adoption of generative AI: The collaboration aims to develop AI solutions, leveraging Infosys Topaz, Azure OpenAI Service, and Azure Cognitive Services. The integrated solutions will enhance enterprise functions and accelerate the democratization of data and intelligence. Hollywood studios can train AI models on writers’ work under tentative deal: Writers are expected to be guaranteed credit and compensation for work they do on scripts, even if studios partially use AI tools. OpenAI partners with WHOOP to launch WHOOP Coach, an advanced-gen AI feature for wearables. It uses OpenAI's GPT-4 system to provide personalized recommendations & guidance for health and fitness. The feature analyzes WHOOP data, sports science, and individual body information to generate personalized answers. Cloudflare launched new AI tools to help customers build, deploy, and run AI models at the network edge. The first tool, Workers AI, allows customers to access nearby GPUs on a pay-as-you-go basis. Another tool, Vectorize, provides a vector database to store mathematical representations of data. The third tool, AI Gateway, offers metrics to help customers manage the costs of running AI apps. Microsoft & Mercy partners for Clinician Empowerment with Gen AI. The partnership allowed Mercy to make real-time clinical decisions & improve patient care. They are exploring over four dozen uses of AI and plan to launch multiple new AI use cases by next year to enhance patient and co-worker experiences. Adobe has officially launched Photoshop on the web, a simplified online version of its popular desktop photo editing app. The web version includes AI tools such as Generative Fill and Generative Expand, powered by Adobe's Firefly generative AI model. These tools allow users to manipulate images using text-based descriptions in over 100 languages. Microsoft plans to use nuclear energy to power its AI data centers: The company is recruiting a "principal program manager for nuclear technology" to evaluate the feasibility of using nuclear energy to support the energy demands of hosting AI models. The company sees nuclear energy as a viable option to address the escalating energy demand of running AI models like ChatGPT. Spotify is adding auto-generated transcripts to millions of podcasts: The transcript feature will expand to more podcasters on Spotify and include time-synced text. In the future, creators could add media to transcripts– a useful feature if a creator is describing an image on the show, for example. Zapier launches Canvas, an AI-powered flowchart tool: It will help its users plan and diagram their business-critical processes, with AI to help them turn those processes into Zapier-based automations. Canvas is now in early access. Microsoft opens AI Co-Innovation Lab in San Francisco to empower Bay Area startups The lab’s main goal is to facilitate the transition from ideation to prototyping, providing companies with the resources and guidance they need to refine their AI-based concepts. Cohere jumps into the fray of the AI chatbot race by releasing a new API: The Chat API with RAG will allow third-party developers of other enterprises to build powerful chat applications based off Cohere’s proprietary generative LLM, Command. Mayo Clinic to deploy and test Microsoft generative AI tools: Mayo Clinic is among the first healthcare organizations to deploy Microsoft 365 Copilot. It is testing the Early Access Program with hundreds of its clinical staff, doctors, and healthcare workers. More detailed breakdown of these news and innovations in the daily newsletter. submitted by /u/RohitAkki [link] [comments]