![]() The Solid project is developing a specification for decentralized data storage. Data is stored in pods, which are analogous to secure personal web servers.All activity on the platform is logged, and all projects are visible to the public. The records never leave the repositories in which they are held. OpenSafely is an open source platform that allows researchers to access electronic health records securely and transparently. ![]() Doing so encourages human users to think critically, rather than simply accepting the AI’s output. The next step in making AI more trustworthy might be developing language models that respond to prompts by asking questions first, rather than generating answers.Edward Tian, cofounder of GPTZero, has said that GPTZero will never be about detecting plagiarism. Their goal is understanding and supporting students who are learning how to use these models.They support multiple foundation models, provide a data generator, and have APIs for prompt-tuning and RLHF. Lamini is a service for customizing large language models.DeepFloyd IF is a new generative art (text-to-image) model developed by Stability.AI.It supports iPhones, Windows, Linux, MacOS, and web browsers. MLC LLM, from developers of Web LLM, allows many different combinations of hardware and operating systems to run small large language models entirely locally.This is the first time that noninvasive techniques have succeeded in decoding linguistic activity. A new study has shown that fMRI images of the brain can be used to decode sentences that the person was hearing.OpenLLaMA is completely open source it was trained on the open source RedPajama dataset, allowing it to avoid the licensing restrictions attached to LLaMA and its descendants. OpenLLaMA is yet another language model based on Facebook’s LLaMA.Now that so many people are using APIs and tools like AutoGPT to build applications on top of AI models, Simon Willison’s explanation of prompt injection, which shows why it is an attack against the applications rather than the models themselves, is a must-read (or see).MPT-7B demonstrates the MosaicML platform, a commercial service for training language models. There are three variants of the base model that have been specialized for chat, writing long stories, and generating instruction. Mosaic has released MPT-7B, an open-source family of large language models that allows commercial use.These models are currently in restricted beta. They have also announced new models for image and music generation. Codey will be accessible through Visual Studio, Jet Brains, and other IDEs, in addition to Google Cloud products such as Vertex. Google has announced Codey, a code generation model similar to Codex.They can be used to augment a model’s “knowledge” by adding additional documents. Vector databases are a relatively new kind of database that work well with large language models and other AI systems.Fitting a language model into a chatbot is easy, and made it possible for millions to use them. But chatbots aren’t really a good user interface. The importance of user interface design for AI has never been properly appreciated.Chapters are being added as they are completed. Langchain: The Missing Manual has been published online by the makers of PineconeDB, a vector database that is frequently used with Langchain to build complex applications on top of large language models.TechTalks has a good explanation of LoRA (Low Rank Adaptation), a technique for fine-tuning large language models that is less time- and processor-intensive.To answer a query, relevant data is found in the vector store and used to build a prompt for the LLM. A new AI stack is emerging, using LLMs as endpoints and vector stores for local data.Unsurprisingly, Microsoft is adding plugins to its AI services, using the same API. OpenAI has added plug-ins (including web search) to its ChatGPT Plus product.PaLM 2 is included, but not the larger LLaMA models. LMSYS ORG (Large Model Systems Organization), a research cooperative between Berkeley, UCSD, and CMU, has released ELO ratings of large language models, based on a competitive analysis.Get a free trial today and find answers on the fly, or master something new and useful. Join the O'Reilly online learning platform.
0 Comments
Leave a Reply. |