Llm

LLM has the potential to be a super writing assistant, but why does it often fall short?

Recent Advancements in Attention Mechanism for Long-Sequence Understanding and Generation

Some exciting details from Apple announcements at WWDC 2024

AWS offers several options for LLM usage, which will you choose?

LLMs promise high levels of performance without the need for task specific training, but that doesn't mean that custom datasets are unnecessary.

Last week a bedrock agent was deployed manually in AWS Console. Let's now do it the smart way, with Infrastructure as Code using AWS CDK

A few weeks ago, I used Google's Gemini LLM for function calling. let's see how it works with AWS Bedrock and Anthropic's Claude

When you need an LLM to access new information, LLM function calling is here to help. Let's explore how to use the Gemini function calling to access real information.

Langchain seems to be a popular choice for developing LLM applications, but when extending it beyond basic use cases, issues emerge.

A foundational problem with LLMs: a takeaway from Andrej Karpathy’s lecture on GPT Tokenization.

The release of Gemini 1.5 Pro, a glimpse into the difficulty in fine-tuning LLM guardrails

So much is happening in AI, how do you keep up? Here are some of the best resources to follow to stay up to date on AI research and applications.

Are there easy ways to improve the inference speed of an auto-regressive model?

Early adopters of LLM integrations risk unexpected outcomes

Looking at the source code to see what makes Mixtral-8x7B so powerful

In a year full of AI news and hype, which events are going to have the biggest enduring impact on AI?

Generative AI is showing up everywhere: how do we avoid trusting it more than we should?

Write code faster with Copilot

How to use Retrieval Augmented Generation (RAG) to connect LlaMA-2 with a large number of internet sources

One application of the recent Executive Order from the White House

Using Google's Bard LLM for Creating a Flask and React Recipe Review Application

Some hidden tips and tricks to get the most out of sagemaker training jobs

Upgrade your code with chat model templates

Train an LLM to answer emails for you

Prepare a dataset to train an LLM to answer emails for you

How is the pad token handled in training a transformer and what's the impact of setting the pad token to be the same as the eos token?