Cobus Greyling
Writer at Freelance
Language Models, AI Agents, Agentic Applications, Development Frameworks & Data-Centric Productivity Tools | Chief Evangelist @ Kore AI
Articles
-
2 days ago |
cobusgreyling.medium.com | Cobus Greyling
The NVIDIA NeMo Framework and NeMo Microservices are two distinct components of NVIDIA’s AI ecosystem, serving different purposes in the development & deployment of generative AI applications. The NeMo Framework helps you create & train your AI models……while the NeMo Microservices provide the tools & infrastructure to deploy and manage those models in production, enabling AI Agents and other applications.
-
3 days ago |
cobusgreyling.medium.com | Cobus Greyling
NVIDIA has a framework which they refer to as a data flywheel, which is a process which focusses on continuous improvement of AI Agents. With this article, I want to kick off a series exploring NVIDIA’s data strategy. Through this journey, I aim to personally deeply understand their approach and share clear, insightful explanations from my own perspective.
-
5 days ago |
cobusgreyling.medium.com | Cobus Greyling
The length of tasks (measured by how long they take human professionals) that generalist autonomous frontier model agents can complete with 80% reliability has been doubling approximately every 213 days…With all the excitement around AI Agents there are two areas which are being neglected…safety and accuracy. In this article I want to take a look at the state of AI Agent accuracy. How accurate are AI Agents?
-
1 week ago |
cobusgreyling.substack.com | Cobus Greyling
This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts
-
1 week ago |
cobusgreyling.medium.com | Cobus Greyling
Use OpenAI’s Codex for coding tasks right from your terminal via the Codex CLI is your go-to tool. The OpenAI Codex CLI Getting Started guide provides a straightforward path to set it up and start coding efficiently. Here’s a quick breakdown to get up and running. What is the Codex CLI? The Codex CLI is a command-line interface that lets developers interact with OpenAI models to generate code, debug and automate tasks.
Try JournoFinder For Free
Search and contact over 1M+ journalist profiles, browse 100M+ articles, and unlock powerful PR tools.
Start Your 7-Day Free Trial →X (formerly Twitter)
- Followers
- 1K
- Tweets
- 5K
- DMs Open
- No
From hand-crafted code to machine learning intelligence From traditional software to AI-driven solutions From CPU processing to GPU-powered performance From isolated systems to interconnected networks From human intuition to data-driven insights
This article from Anthropic is one of the most grounded and sober pieces on AI Agent implementation you will find... Not only to they cover the basic definition of what AI Agents are, but also when (and when not) to use AI Agents. When and how to use frameworks...they suggest https://t.co/LbTVJIVtGJ
Even though a bit dated, this study from Stanford, makes for interesting reading and illustrates how far we have come over as short period of time. First of all, the study refers to what we now know as Large Language Models (LLMs), as Knowledge Intensive Natural Language https://t.co/HgBxcUJEZj