The Evaluator
Your go-to blog for insights on AI observability and evaluation.
Showing 311–320 of 458 posts (page 32 of 46)
LIMA: Less Is More for Alignment – Paper Reading and Discussion
Introduction In this paper reading, we discuss “LIMA: Less Is More for Alignment.” This research delves into the efficiency and effectiveness of large language models, demonstrating the power of pre-training and how minimal fine-tuning can enable high-quality output. We will do a deep-dive into how LIMA outperforms its contemporaries, redefining the existing knowledge paradigms in…
Drag Your GAN: Interactive Point-Based Manipulation on the Generative Image Manifold
Introduction In this paper reading, we dive into “Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold.” Drag Your GAN introduces a novel approach for achieving precise control over the pose, shape, expression, and layout of objects generated by GANs. This approach allows users to “drag” any points of an image to specific…
Cross Validation: What You Need To Know, From the Basics To LLMs
From the basics to how to do cross validation on large language models What Is Cross Validation? Imagine the machine learning model you have created has accuracy as 98%. Do you think the model is actually going to provide correct results 98% of the time? Well no, we do not know how well the model…
Sign up for our newsletter, The Evaluator — and stay in the know with updates and new resources:
Evaluating Model Fairness
In many ways, bias and fairness in AI are two sides of the same coin; bias is a result, fairness is an action. Bias is inherently present in the world around us and is where prejudice is put into practice (consciously or unconsciously). Fairness is the absence of prejudice or preference for an individual or…
Getting To Know MLflow: a Comprehensive Guide to ML Workflow Optimization
What is the purpose of a model store in machine learning? A model store serves as a centralized repository for machine learning models, streamlining storage, organization, and management. During the initial stages of developing machine learning models, practitioners may create and store models in various environments such as Jupyter notebooks or local workspaces. This scattered…
Exploring the Future of AI Community with Cerebral Valley Founder Ivan Porollo
Ivan Porollo is a co-founder of Cerebral Valley, a new community at the center of the AI renaissance currently underway in the San Francisco Bay Area. A software engineer-turned-founder, Ivan is hyper-focused on building out Cerebral Valley under a banner of builders and founders sharing knowledge ultimately propelling new breakthroughs in AI and new startups….
OpenAI on Reinforcement Learning With Human Feedback (RLHF)
Recently, we interviewed Long Ouyang and Ryan Lowe, research scientists at OpenAI. As the creators of InstructGPT – one of the first major applications of reinforcement learning with human feedback (RLHF) to train large language models – the two played an important role in the evolution of RLHF models and paving the way for GPT-4….
Lessons From Building an Early ChatGPT Plugin In Under 24 Hours
Cerebral Valley’s ChatGPT Plugins Hackathon offered a sneak peek of a burgeoning new ecosystem and best practices learned the hard way from creating a new plugin from scratch (meet Observe!) This blog is a collaboration with Aparna Dhinakaran, Chief Product Officer and Co-Founder of Arize AI; Francisco (“Kiko”) Castillo Carrasco, a Data Scientist and Software…
Survey: Massive Retooling Around Large Language Models Underway
Over half (53.3%) of say they plan to deploy large language model (LLM) applications into production in the next 12 months or “as soon as possible” To paraphrase Shakespeare (the original bard), it is the best of times and the worst of times for AI. On the one hand, generative AI is fueling a technical…
Five Rules to Follow To Get Your First Role in Tech
The art of landing entry-level tech jobs Getting your first role in the tech industry can be a time-consuming and difficult challenge. Whether you are a new graduate or are switching into tech from another industry, the challenge is sure to be a rewarding one. Before diving into my five rules to help you navigate…
