Towards AI

FEBRUARY 17, 2025

RAFT vs Fine-Tuning Image created by author As the use of large language models (LLMs) grows within businesses, to automate tasks, analyse data, and engage with customers; adapting these models to specific needs (e.g., Data Quality Problem: Biased or outdated training data affects the output. balance, outliers).

Data Drift 95

Data Drift LLM Automation Metadata 95

O'Reilly Media

MARCH 25, 2025

Lets be real: building LLM applications today feels like purgatory. The truth is, we’re in the earliest days of understanding how to build robust LLM applications. What makes LLM applications so different? Two big things: They bring the messiness of the real world into your system through unstructured data.

LLM 67

LLM Software Development Prompt Engineering Prompt Engineer 67

TheSequence

JULY 5, 2023

Created Using Midjourney In case you missed yesterday’s newsletter due to July the 4th holiday, we discussed the universe of in-context retrieval augmented LLMs or techniques that allow to expand the LLM knowledge without altering its core architecutre. Not surprisingly, data quality and drifting is incredibly important.

Data Drift 52

Data Drift Data Quality Metadata Data Platform 52

Unite.AI

JUNE 24, 2024

By establishing standardized workflows, automating repetitive tasks, and implementing robust monitoring and governance mechanisms, MLOps enables organizations to accelerate model development, improve deployment reliability, and maximize the value derived from ML initiatives.

Data Drift 120

Data Drift Machine Learning Data Scientist ML 120

The MLOps Blog

JUNE 27, 2023

This includes features for hyperparameter tuning, automated model selection, and visualization of model metrics. Automated pipelining and workflow orchestration: Platforms should provide tools for automated pipelining and workflow orchestration, enabling you to define and manage complex ML pipelines.

Machine Learning 134

Machine Learning Metadata Data Scientist Data Quality 134

ODSC - Open Data Science

FEBRUARY 5, 2025

This problem often stems from inadequate user value, underwhelming performance, and an absence of robust best practices for building and deploying LLM tools as part of the AI development lifecycle. Real-world applications often expose gaps that proper data preparation could have preempted. Engineering scalable and adaptable solutions.

AI Development 52

AI Development AI Developer LLM Data Drift 52

ODSC - Open Data Science

OCTOBER 11, 2023

Machine learning models are only as good as the data they are trained on. Even with the most advanced neural network architectures, if the training data is flawed, the model will suffer. Data issues like label errors, outliers, duplicates, data drift, and low-quality examples significantly hamper model performance.

Auto-classification 52

Auto-classification Auto-complete Data Drift Machine Learning 52