InfoQ Homepage Large language models Content on InfoQ
-
Defensible Moats: Unlocking Enterprise Value with Large Language Models at QCon San Francisco
In a recent presentation at QConSFrancisco, Nischal HP discussed the challenges enterprises face when building LLM-powered applications using APIs alone. These challenges include data fragmentation, the absence of a shared business vocabulary, privacy concerns regarding data, and diverse objectives among stakeholders.
-
The Challenges of Producing Quality Code When Using AI-Based Generalistic Models
Using AI with generalistic models to do very specific things like generating code can cause problems. Producing code with AI is like using code from someone else who you don’t know which may not match your standards and quality. Creating specialised or dedicated models can be a way out.
-
Practical Advice for Retrieval Augmented Generation (RAG), by Sam Partee at QCon San Francisco
At the recent QCon San Francisco conference, Sam Partee, principal engineer at Redis, gave a talk about Retrieval Augmented Generation (RAG). He discussed Generative Search, which combines large language models (LLMs) with vector databases to improve information retrieval. Partee discussed several innovative tricks such as Hypothetical Document Embeddings (HyDE), and semantic caching.
-
Generative AI Service AWS Bedrock Now Generally Available
After announcing Bedrock last April in preview, Amazon is now making its fully-managed service for generative AI apps generally available.
-
Multi-Modal LLM NExT-GPT Handles Text, Images, Videos, and Audio
The NExT Research Center at the National University of Singapore (NUS) recently open-sourced NExT-GPT, an "any-to-any" multi-modal large language model (LLM) that can handle text, images, videos, and audio as input or output. NExT-GPT is based on existing pre-trained models and only required updating 1% of its total parameters during training.
-
Hugging Face's Guide to Optimizing LLMs in Production
When it comes to deploying Large Language Models (LLMs) in production, the two major challenges originate from the huge amount of parameters they require and the necessity of handling very long input sequences to represent contextual information. Hugging Face has documented a list of techniques to tackle those hurdles based on their experience serving such models.
-
Abu Dhabi Releases Largest Openly-Available Language Model Falcon 180B
The Abu Dhabi government's Technology Innovation Institute (TII) released Falcon 180B, currently the largest openly-available large language model (LLM). Falcon 180B contains 180 billion parameters and outperforms GPT-3.5 on the MMLU benchmark.
-
AI, ML, Data Engineering News Roundup: Stable Chat, Vertex AI, ChatGPT and Code Llama
The most recent update, which covers developments through September 4, 2023, highlights significant pronouncements and accomplishments in the fields of artificial intelligence, machine learning, and data science. Developments from Stability AI, Google, OpenAI, and Meta were among this week's significant stories.
-
Weekly Update on Large Language Models: PointLLM, WALL-E, AskIt, and Jais
The most recent compilation of advanced research, inventive applications, and notable unveilings in the realm of Large Language Models (LLMs) during the week starting September 4th, 2023.
-
Google Cloud Unveils AlloyDB AI: Transforming PostgreSQL with Advanced Vector Embeddings and AI
During the recent Google Cloud Next, Google announced AlloyDB AI in preview as an integral part of AlloyDB for PostgreSQL, allowing developers to build generative (gen) Artificial Intelligence (AI) applications leveraging large language models (LLMs) with their real-time operational data through built-in, end-to-end support for vector embeddings.
-
Meta Open-Sources Code Generation LLM Code Llama
Meta recently open-sourced Code Llama, a code generation LLM which is based on the Llama 2 foundation model and carries the same community license. Code Llama was fine-tuned on 500B tokens of code and is available in three model sizes ranging up to 34B parameters. In evaluations on code-generation benchmarks, the model outperformed all other open-source models and is comparable to ChatGPT.
-
Google Expands Vertex AI Search and Conversation Capabilities
At its Google Cloud Next conference, Google officially introduced new capabilities for its enterprise AI platform, Vertex AI, which aim to enable more advanced user workflows, among other things.
-
How Spotify Improved its LLM Chatbot in Sidekick
While using a Large Language Model chatbot opens the door to innovative solutions, Spotify engineer Ates Goral argues that crafting the user experience so it is as natural as possible requires some specific efforts to order to reduce latency.
-
Stability AI Launches Open Source Chatbot Stable Chat
Stability AI, makers of the image generation AI Stable Diffusion, recently launched Stable Chat, a web-based chat interface for their open-access language model Stable Beluga. At the time of its release, Stable Beluga was the best-performing open large language model (LLM) on the HuggingFace leaderboard.
-
MetaGPT Leverages Human Collaboration Techniques for Multi-Agent-Based Software Engineering
Created by a team of researchers from Chinese and US universities, MetaGPT is a new LLM-based meta programming framework aiming to enable collaboration in multi-agent systems by leveraging human procedural knowledge to enhance robustness, reduce errors, and engineer software solutions for complex tasks.