Large Language Models & Frameworks for Product Managers in 2023

Gain the basic know-how you need to understand what a large language model (LLM) is, how it works, and the best models in 2023.

Large Language Models & Frameworks for Product Managers in 2023

Few technological advancements have captured the imagination, curiosity, and application of experts and businesses quite like artificial intelligence (AI). From self-driving cars to personalized online shopping experiences, these solutions are just in their infancy—and the sky is the limit.

However, among all the modern-day AI innovations, one breakthrough has the potential to make the most impact: large language models (LLMs). These feats of computational linguistics have redefined our understanding of machine-human interactions and paved the way for brand-new digital solutions and communications.

Large language models can be an intimidating topic to explore, especially if you don't have the right foundational understanding. It's like trying to grasp Dogecoin's value without any knowledge about the world of cryptocurrency.

Below, we'll give you the basic know-how you need to understand LLMs, how they work, and the best models in 2023.

What Is a Large Language Model?

A large language model (often abbreviated as LLM) is a machine-learning model designed to understand, generate, and interact with human language. Engineers train these models on vast amounts of information. These models aren't just large in terms of size—they're also massive in their capacity to understand human prompts and generate vast amounts of original text.

Original natural language processing (NLP) models were limited in their understanding of language. They tended to rely on smaller datasets and more developer handholding, making them less intelligent and more like automation tools.

LLMs leverage deep learning architectures to process and understand the nuances and context of human language. They can be trained on vast amounts of data and benefit from the scaling of the transformer architecture.

LLMs generate text. From chatbots that provide human-like interactions to tools that can draft articles or assist in creative writing, LLMs have expanded the horizons of what's possible with AI-driven language tasks.

However, companies like AssemblyAI have pushed the boundaries in other directions, exploring the power of LLMs with voice data. While LLMs are powerful, they can’t do everything in isolation. LeMUR is a framework for applying LLMs to spoken language. It offers a simple API for applying LLMs to up to 100 hours of audio data, even exposing endpoints for common use tasks It's smart enough to auto-generate subtitles, identify speakers, and transcribe audio in real time.

Benefits of Using an LLM

LLMs might seem like a nice-to-have right now, but they'll eventually become integral to our day-to-day processes and systems. And here's why:

  • Speed: LLMs can process vast amounts of text data rapidly, allowing you to analyze huge volumes of information in minutes rather than dozens of manual man-hours.
  • Versatility: Businesses can leverage LLMs for everything from summarization to creative writing and code development.
  • Adaptability: Unlike static models, LLMs can be fine-tuned, allowing them to adapt to changing linguistic trends,new information, and a wide range of tasks.
  • Cost Efficiency: LLMs can automate tasks that previously required human intervention, leading to significant cost savings.
  • User Experience: LLMs can engage users in more natural, human-like conversations. They can even adapt to individual user preferences and styles, offering personalized responses and solutions.
  • Accessibility: Many LLMs have been trained on multiple languages, allowing them to bridge linguistic gaps.

LLMs also gain new abilities as they learn and grow—a process known as emergence. That means their use and application will continue to expand.

Challenges and Limitations of LLMs

While LLMs are becoming a game-changer for modern-day applications and solutions, they're not perfect. They do have a few challenges and limitations you'll want to keep in mind:

  • Data Biases: LLMs are trained on vast amounts of data from the internet, which means they can inherit biases they find. However, there is ongoing research to make LLMs safer, such as Reinforcement Learning from AI Feedback (RLAIF).
  • Reliability: LLMs can inadvertently generate false information or fake news.

While LLMs offer potential advantages in terms of scalability and cost-efficiency, they also present meaningful challenges, especially concerning data quality, biases, and ethical considerations.

How Do Large Language Models Work?

LLMs are built upon deep learning, a subset of machine learning. They use neural networks that are inspired by the structure and function of the human brain.

The breakthrough for LLMs came with the introduction of the Transformer architecture. This structure allows models to handle long-range dependencies in text—meaning they can consider the context from earlier in a sentence or paragraph when making predictions.

LLMs are typically trained using self-supervised learning on massive datasets. They learn to accurately predict the next word in a sequence, and through learning on millions of such predictions, they refine their internal parameters.

The LLMs that engineers train today have billions of parameters. These parameters are adjusted during training to minimize the difference between the model's predictions and the actual outcomes.

Before processing, text is broken down into chunks, often called tokens. Tokens can be as short as one character or as long as one word. The LLM converts these tokens into vectors, which are numerical representations of words. The model then processes these vectors to generate your desired outputs.

In a nutshell, that's how large language models work. Obviously, there's more going on under the hood than that, but this primer is a good starting point for understanding the basics. Want to dive deeper? Read Introduction to Large Language Models for Generative AI.

The Best Large Language Models and Frameworks in 2023

Startups and enterprises alike are pushing the boundaries of what's possible with large language models. They're rapidly turning out innovative products and features, and it's hard to keep up with the most revolutionary solutions.

While there's no one-size-fits-all LLM for every use case, a few models stand out from the crowd. Here are the top large language models and frameworks as of 2023.

1. LeMUR

LeMUR (Leveraging Large Language Models to Understand Recognized Speech) is a framework introduced by AssemblyAI. It is a framework for applying large language models to spoken data, allowing users to generate custom summaries, ask questions about the data, and obtain insights from nearly 100 hours of audio with just a single API call.

The framework is optimized for high accuracy on specific tasks, such as generating answers to questions and crafting custom summaries. It leverages advanced retrieval and compression techniques to ensure high-quality LLM responses.

LeMUR integrates with AssemblyAI's state-of-the-art speech recognition model, ensuring that the LLM outputs are based on quality transcriptions.

2. GPT-4

GPT-4 is OpenAI's latest (and largest) model. It's a Transformer-based model that’s larger than its 175B parameter predecessor,, and it's demonstrated human-level or near-human-level performance and accuracy on a range of benchmarks. As of now, it's available as a standalone product, and its API can be used for various applications. It currently powers Microsoft Bing Search and will soon be integrated into all Microsoft Office products.


BERT stands for Bidirectional Encoder Representations from Transformers, and it's a large language model by Google. BERT is an encoder-only Transformer model and is pre-trained on an extensive amount of unlabeled text from the internet. Its bidirectional approach sets BERT apart, enabling it to grasp context from both preceding and succeeding words in a sequence. For this reason, BERT is not used for text completion tasks but instead language understanding, in which it can be easily fine-tuned for different tasks like question answering.

4. Bloom

Bloom is an autoregressive large language model developed by BigScience with 176B parameters. Bloom excels in generating coherent and human-like text based on given prompts. The model's autoregressive nature allows it to seamlessly continue text from a provided prompt, and its standout feature is its ability to produce text across over 46 different languages.

5. Llama

Llama is a family of pre-trained and fine-tuned LLMs, ranging from 7B to 70B parameters. It was developed by the AI group at Meta (the parent company of Facebook). Llama 2 Chat LLMs are optimized for dialogue use cases and have been shown to outperform many open-source chat models in various benchmarks.

Meta claims that Llama chat is as safe or safer than other models. However, concerns regarding the training corpus have led to copyright issues.

How to Choose the Right Large Language Model

With so many options on the market, finding the right LLM for your use case can be tricky. The best large language model will depend on your required tasks, required training, accuracy, available APIs, and budget.

Here are a few things to consider when choosing the best LLM:

  • Primary Task: Determine the primary tasks you want the LLM to perform. This could range from text generation, summarization, and translation to question-answering.
  • Model Size: LLMs can range from millions to billions of parameters. Larger models generally perform better but come with increased computational costs.
  • Pre-Trained: While pre-trained models are good for general tasks, fine-tuned models are tailored for specific jobs or domains.
  • Accuracy: Choose a model that has high accuracy and performance.
  • Integrations: Find an LLM provider that offers easy-to-use APIs or SDKs for seamless integration into your systems.
  • Scalability: Ensure the model can handle the volume of data you'll be processing, especially if you need real-time responses at scale.
  • Cost: Understand the pricing model—it could be based on the number of tokens, API calls, or compute hours.

Start Building LLM Apps on Voice Data

Ready to take action on your spoken data? LeMUR can generate summaries, auto-transcribe, and answer questions about your phone calls, videos, podcasts, and meetings. Need a scalable solution? LeMUR processes over 100 hours of audio with a single API call, and it can handle over 1M tokens as input. Try it for yourself in our free-to-use playground.