Skip to main content

Community Forums

Share insights, seek advice, or simply connect with fellow members on topics that matter to you.

69 Topics
Anbu V
Explorer
Anbu VExplorer
posted in Artificial Intelligence
A Deep Dive into LLM Guardrails

 Image generated using Microsoft Copilot In the rapidly evolving landscape of artificial intelligence, Large Language Models (LLMs) have emerged as powerful tools with far-reaching implications. As these models become increasingly integrated into our daily lives, the need for robust safety measures has never been more critical. Enter guardrails - sophisticated algorithms designed to act as digital sentinels, safeguarding the interactions between humans and AI.The Evolution of AI SafetyIn the pre-LLM era, AI safety primarily relied on white box techniques. These methods focused on creating transparent and interpretable models, allowing researchers and developers to understand the internal workings and decision-making processes. However, the advent of LLMs has shifted the paradigm towards more complex, black box systems. This transition has brought about new challenges in ensuring AI safety. The focus has moved from inherent model transparency to post-hoc strategies, notably the implemen

1032
Anbu V
Explorer
Sothan
SothanCommunity Manager
published in General Discussion
What is your Data Science and AI Stack? (2024 Edition)

Post about your data science and AI stack—what tools and languages do you usually work with for your projects? Use the following format to answer 😎 Programming Languages:Data Analysis and Visualization:BI Tools:Database Warehouse: Cloud Platforms:Compute Resources:Job Title:Industry:

671
jrgosalvez
jrgosalvez
jrgosalvezCommunity Manager
published in Artificial Intelligence
To GPT4o or Not to GPT4o?LLM

OpenAI released GPT-4o a conversational chat-bot last week.It is integrated into the online chat-bot as well as an API for integration with 3rd party systems. Early findings illustrate it is twice as fast and half the cost, with higher rate limits for better performance. https://vimeo.com/945586717 The multi-group query decoder architecture performs well based on zero-shot prompts, which are plain prompts that do not provide context in the prompt to help the LLM improve its response.  The API leverages the existing OpenAI chat completion API, which requires an API key to load and interact with the model. Many additional parameters, such as temperature, can be tuned.  from openai import OpenAIOPENAI_API_KEY = "<your-api-key>"client = OpenAI(api_key=OPENAI_API_KEY)response = client.chat.completions.create(  model="gpt-4o-2024-05-13",  messages=[    {"role": "system", "content": "You are a helpful assistant."},    {"role": "user", "content": "Who won the world series in 2020?"},    

270
jrgosalvez
Anbu V
Explorer
Anbu VExplorer
posted in Artificial Intelligence
Training AI Agents to Self-Correct: A Deep Dive into Agent-R’s Theoretical Foundations

Imagine teaching a robot to boil water. It might first search for a pot, fill it with water, then place it on the stove. But what if it mistakenly turns on the microwave instead of the stove? Traditional AI agents often struggle to recover from such errors, leading to cascading failures. This is the problem Agent-R—a novel framework for training self-reflective language model agents—aims to solve.In this article, we’ll unpack the theoretical backbone of Agent-R by focusing on how this framework redefines error recovery in AI.Why Error Recovery Matters in Interactive EnvironmentsMost AI agents learn by mimicking expert trajectories (e.g., perfect step-by-step guides). But real-world tasks are messy. Errors are inevitable, and waiting until the end of a task to correct them is like letting a typo in a sentence propagate into a garbled paragraph.The Core Challenge: Timely InterventionProblem: In multi-step tasks (e.g., crafting items in Minecraft or navigating a virtual lab), errors early

10
Anbu V
Explorer
Anbu V
Explorer
Anbu VExplorer
posted in Artificial Intelligence
Shared Recurrent Memory Transformer

Multi-agent systems have become increasingly important in solving complex problems through distributed intelligence and collaboration. However, coordinating multiple agents effectively remains a significant challenge, particularly in the field of reinforcement learning. In this article, we'll explore a novel approach called Shared Recurrent Memory Transformer (SRMT) that aims to enhance coordination in decentralized multi-agent systems.The Challenge of Multi-Agent CoordinationImagine a group of robots trying to navigate through a crowded warehouse. Each robot has its own goal and can only see what's immediately around it. How can they work together efficiently without bumping into each other or getting stuck? This is the essence of the multi-agent pathfinding problem.Traditional approaches often struggle with this task, especially when the environment is complex or the number of agents is large. They may rely on centralized control, which doesn't scale well, or on explicit communicatio

80
Anbu V
Explorer
jrgosalvez
jrgosalvezCommunity Manager
published in Artificial Intelligence
DeepSeek for Local AI Creation

DeepSeek is an open source, open weight set of pre-trained models people can use for inference through the DeepSeek web app on chat.deepseek.com by agreeing to their terms of service and privacy policies or training by downloading the models. Similarly to OpenAI, the privacy policy lets users know that data and logic shared is collected and fair game for the company to retain and retrain their models, so be careful what you share. However, since DeepSeek is open source, AI creators can download models locally and set-up to use for local AI development and retraining of weights to efficiently create and tune focused models for optimized functions and tasks. Check out DeepSeek’s open models on Github at github.com/deepseek-ai.Mike Le Galloudec at Oakland shares a great 6 min review and will be sharing how to get R1 running locally on private systems.Are you doing something similar? Share how you’re getting DeepSeek models running locally!

801
Sothan
Anbu V
Explorer
Anbu VExplorer
posted in Artificial Intelligence
Titans: Learning to Memorize at Test Time

 A research paper by Ali Behrouz, Peilin Zhong and Vahab Mirrokni from Google Research introduce a groundbreaking neural network module that addresses the limitations of current models in handling long term dependencies. This work is a significant leap forward in the design of memory augmented architectures, offering theoretical and practical advancements in sequence modeling. Below we explore the theoretical underpinnings, technical innovations and experimental results of this advanced neural network module.The Challenge of Long-Term DependenciesModern neural architectures like Transformers and recurrent neural networks (RNNs) have revolutionized sequence modeling. However, they face some challenges:Transformers: While effective at capturing short term dependencies through attention mechanisms, they are computationally expensive for long sequences due to quadratic complexity in context length. Their context window limits their ability to model long term dependencies Recurrent Models

720
Anbu V
Explorer
Sothan
SothanCommunity Manager
published in General Discussion
rethinking creativity: cre[ai]tion x Z by HP

Cre[AI]tion, co-founded by Z by HP Ambassador Nik Dorndorf, is transforming the design landscape by connecting creators with AI tools that enhance creativity and streamline workflows. Acting as a "digital muse," Cre[AI]tion helps designers access advanced AI models and develop custom solutions tailored to their needs.With the power of Z by HP workstations, they’re driving innovation—accelerating model training, optimizing creative processes, and enabling groundbreaking projects. These high-performance workstations are a key part of how Cre[AI]tion supports creators in pushing the boundaries of what’s possible.Explore their case study to see how they’re shaping the future of design.

220
Sothan
Anbu V
Explorer
Anbu VExplorer
posted in Artificial Intelligence
Inside AI’s Black Box:  Mechanistic Interpretability as a Key to AI Transparency

 Image generated using CopilotArtificial intelligence (AI) systems are becoming increasingly sophisticated, capable of generalizing across tasks and domains. However, this complexity makes them harder to understand, raising concerns about their trustworthiness and safety. Mechanistic interpretability offers a promising solution by reverse-engineering neural networks to uncover how they process information internally. Just as neuroscience advanced our understanding of the brain by studying internal cognitive processes, mechanistic interpretability seeks to move beyond black-box methods to provide precise, causal explanations of AI behavior.This article explores the principles, methods, and implications of mechanistic interpretability. By examining its core concepts, such as features, circuits, and hypotheses like superposition and linear representation, we aim to shed light on how this field can contribute to AI safety while addressing the challenges it faces.Mechanistic interpretabilit

440
Anbu V
Explorer
jrgosalvez
jrgosalvezCommunity Manager
asked in General Discussion
Does Google's Willow qubits take AI computing to a new Universe?

Google announced its Willow project with amazing claims on performance capabilities. 

300
jrgosalvez
Sothan
SothanCommunity Manager
published in General Discussion
Ambassador of the Month: Ayon Roy

We’re excited to recognize Ayon Roy as our latest Z by HP Ambassador of the Month! 🎉As an Executive Data Scientist at NielsenIQ, Ayon is making waves in sustainable innovation with his project, Greenscape AI. This AI-powered framework for urban forestry is reshaping how cities approach sustainability. By integrating satellite imagery and drone footage, Greenscape AI maps tree species, analyzes spatial distributions, and creates high-resolution urban forestry maps. These tools help optimize urban green space management, contribute to climate action, and promote ecosystem preservation.Ayon credits the ZBook Studio G10 and Z8 Fury G5 for making this ambitious project possible. With early access to Z by HP Boost, he leveraged the immense processing power of the Z8 Fury remotely from his Studio G10 laptop. This seamless integration of advanced hardware enabled efficient model training and deployment, accelerating his workflow and bringing Greenscape AI to life.Featured Projects:Greenscape

451
A
Starter
janetteguzman
janetteguzmanCommunity Manager
published in Compute
AI Edge Computing for Intelligent Traffic Monitoring

A recent paper titled “Edge computing and AI-driven intelligent traffic monitoring and optimization” explores how edge computing can be used to decentralize AI compute by processing data near IoT devices and vehicles to reduce latency and cloud dependency. The paper finds that edge computing using SLAM technology adequately places compute and storage closer to data sources and end users to enable faster data processing and response times of AI workloads for real-time traffic management, autonomous driving, and V2X communication.  Top five take-aways:1. Bring compute close to the data source: Edge computing places processing power closer to data sources (e.g., IoT devices, vehicles), enabling real-time data analysis and response. This reduces latency, enhances reliability, and alleviates bandwidth constraints, particularly crucial for traffic management and autonomous driving during peak periods.2. Decentralize to improve system efficiency and economy of resource you own:By decentralizi

160
janetteguzman
J
Explorer
jtaylorExplorer
asked in Data Science
Using Ollama in AI Studio

I am looking to run some testing on a local ollama model in AI Studio. However, every time I open AI Studio, I have to redownload ollama and pull llama3 to use from my notebook. Any suggestion for how to save that download (done from terminal) so that it is already loaded when I open AI Studio?

371
jrgosalvez
TomSadlerHPAI
Explorer
TomSadlerHPAIExplorer
posted in General Discussion
New: Anthropic's Model Context Protocol (MCP)

Really great article from Anthropic with the announcement of MCPhttps://www.anthropic.com/news/model-context-protocolAnthropic has unveiled an exciting new initiative: the Model Context Protocol (MCP). This open-source standard simplifies the connection between AI assistants and various data sources, making integration seamless for developers. MCP includes developer tools, local server support within Claude Desktop applications, and pre-configured servers for popular platforms like Google Drive and GitHub. Notably, companies such as Block and Apollo are already leveraging MCP to enhance their AI capabilities.A standout feature of MCP is its remarkable flexibility; it is designed to connect with data sources that may not even exist yet. Developers can easily get started with quickstart guides and open-source resources provided by Anthropic. This initiative aims to break down the barriers that have traditionally isolated AI models from essential data, facilitating a more interconnected a

380
TomSadlerHPAI
Explorer
jrgosalvez
jrgosalvezCommunity Manager
asked in Artificial Intelligence
How Private are Your Chats?

With the proliferation of chatbots and agents, users are rushing to learn more about the technology. The speed with which GenAI is growing is fueled by the data with which the AI has access to. Chatbots are curating a combination of synthetic and user based content to collect questions, data, chain of thought, and context.Do you believe sharing your data and logic online with AI means giving up rights to your IP?  

50
jrgosalvez
Anbu V
Explorer
Anbu VExplorer
posted in Artificial Intelligence
LLM As a Judge

 The rapid evolution of Large Language Models (LLMs) has ushered in a new era of AI-powered chat assistants, leveraging techniques like supervised instruction fine-tuning and reinforcement learning with human feedback (RLHF) to enhance their instruction-following and conversational abilities. These advancements have led to models that are increasingly aligned with human preferences, often outperforming their unaligned predecessors in user satisfaction. However, this progress has brought forth a significant challenge: how to effectively evaluate these sophisticated models. Traditional benchmarks, which typically focus on core capabilities such as knowledge retrieval and problem-solving, fall short in assessing how well these models align with human preferences in real-world applications. We've observed instances where models excel in benchmark tests yet underperform in practical scenarios that demand alignment with human expectations.While human ratings remain the gold standard for eval

791
jrgosalvez
jrgosalvez
jrgosalvezCommunity Manager
published in General Discussion
Exploring Collaboration and Scalability: What Data Scientists Want in AI Platforms

In Part 2 of our survey, we dive into data scientists’ needs for collaboration and scalability in AI platforms. While many find creating multiple experiments manageable, nearly half feel neutral or challenged by the process, signaling room for improvement. Data scientists emphasize the importance of platforms that offer easy deployment, scalability, user-friendly design, seamless integration, and strong security.Most collaboration happens through shared platforms for project management and file sharing, with team communication blending in-person meetings and digital messaging. Moving forward, platform development should prioritize ease of collaboration, integration, security, and scalability. Additionally, aligning with data scientists' success metrics—like accuracy, ROI, and user satisfaction—will help highlight platform benefits effectively.

80
jrgosalvez
Sothan
SothanCommunity Manager
published in General Discussion
Survey Insights: Why Data Scientists Are Prioritizing Security in On-Prem AI Workloads

In our recent survey of over 65 data scientists, we set out to understand the perceived value of AI development and uncover the moments when users experience that crucial ‘aha’ feeling with AI/ML platforms. Knowing when users recognize value within the development lifecycle helps us shape better tools and support.A key takeaway? With the majority of organizations planning to bring AI workloads on-premises within the next few years, security and privacy are top of mind for data scientists when running AI/ML workloads locally.Here's what we found:81% of organizations have firm or potential plans to bring AI workloads on-premises within the next 1-3 years.Over 70% of respondents rated security and privacy as very important when it comes to the ability to run AI/ML workloads locally.Stay tuned for Part 2 of our survey insights, where we’ll dive into what data scientists are looking for in terms of collaboration and scalability. Beyond just easy deployment and experiment creation, they’re s

100
Sothan
jrgosalvez
jrgosalvezCommunity Manager
published in Compute
Fine-tuning Enormous LLMs on Z by HP Workstations

Robert Luciani with The AI Framework discovered that using low-rank adaptation and quantization it is possible to fine-tune LLMs on Z by HP workstations. To validate this, Robert used Hugging Face’s State-of-the-art Parameter-Efficient Fine-Tuning (PEFT) method. 

870
jrgosalvez
Sothan
SothanCommunity Manager
posted in General Discussion
The Community Wrap-Up: October 2024

 Hello Community Members!October has been an eventful month, filled with engaging activities, insightful news, and exciting events. Let's take a look back at the highlights, dive into our latest webinar recap, and learn how you can contribute your ideas to Boost and AI Studio initiatives. Here’s your October community recap!🎤 Last Webinar RecapZ by HP Boost Webinar On October 4th, we hosted a highly informative webinar focused on maximizing on-premise compute power for AI and ML model training. Akash James demonstrated how he leverages remote GPU access from the Himalayas to work on his multi-modal LLM project, VERONICA. His presentation not only highlighted innovative techniques but also inspired many attendees to explore remote compute solutions for their own AI projects. 🗞️ Latest NewsGartner’s AI PC Shipment Forecast A Gartner report predicts that AI-powered PC shipments will surge by 165.5% by 2025. This forecast has initiated discussions in our community about the future of AI

260
Sothan
Sothan
SothanCommunity Manager
published in Compute
Revolutionizing Productivity and Development with AI Workstations

A recent survey showed that 86% of CEOs saw AI as a key part of business operations. Its rapid rise in customer-facing roles and its ability to enhance efficiency across various industries made it a top priority for many leaders. While there are plenty of exciting opportunities, there were also challenges to navigate when it came to implementing these new strategies.In a recent fireside chat, Sama Bali, Senior Product Marketing Manager at NVIDIA, chatted with Alex Klug, Senior Manager of Data Science & AI Product Management at HP. They talked about the current state of generative AI in businesses, the essential role of workstations for data science teams, and took a closer look at Z by HP’s software solutions powered by NVIDIA graphics. You can catch the full discussion: https://www.brighttalk.com/webcast/20544/628829

440
Sothan
Sothan
SothanCommunity Manager
posted in General Discussion
AI PCs Expected to Make Up 43% of Global Shipments by 2025, Says Gartner

Gartner projects that AI-powered PCs will hit 114 million units in 2025, marking a massive 165.5% jump from 2024. These AI PCs, defined by their built-in neural processing units (NPUs), include models running on Windows, macOS, and Arm-based systems.By 2024, shipments are expected to reach 43 million units, nearly double the 2023 total. Laptops lead the way, with AI-enabled models predicted to make up 51% of all laptop shipments by 2025, outpacing desktops.Gartner forecasts AI PC shipments to reach 43 million units in 2024, a 99.8% increase from 2023.AI PC Shipments, Worldwide, 2023-2025 (Thousands of Units)     2023 Shipments   2024 Shipments   2025 Shipments AI Laptops 20,136 40,520 102,421 AI Desktops 1,396 2,507 11,804 AI PC Units Total 21,532 43,027 114,225  With nearly half of all PCs integrating AI by 2025, what industries or activities do you think wi

360
Sothan
jrgosalvez
jrgosalvezCommunity Manager
posted in Compute
Hybrid Memory to Boost GPU Performance

Stanford University research team explores gain cell memory technology to address the limitations of current SRAM and DRAM memory in GPUs. By combining features of both SRAM and DRAM, the goal is to speed up data access and reduce power consumption.Top Three Takeaways:Gain Cell Memory: hybrid gain cells combine the speed of SRAM with the capacity of DRAM, to overcome the memory wall problem in GPUs by reducing data transfer delays. Innovative Materials: combining different materials for transistors (ALD ITO FET and Si PMOS), the hybrid gain cells provide faster data access, non-destructive reads, and significantly longer data retention compared than traditional DRAM. Potential for SoC Applications: can serve as a drop-in replacement for SRAM, offering higher capacity at lower fabrication costs, making it attractive for SoC manufacturers in datacenter GPUs, CPUs, and embedded systems.Check out Chris Mellor article on Blocks & Files: “Stanford team proposes hybrid gain cell memory to

310
jrgosalvez
Sothan
SothanCommunity Manager
published in Data Science
Setting Up a Windows Environment for Data Science: How Benedict Neo Configured His Workstation

As a Z by HP Ambassadors, Benedict Neo was equipped with the HP Z6 G5 Tower Workstation, featuring an AMD Ryzen Threadripper PRO 7965WX processor and NVIDIA RTX 6000 graphics. This powerful setup is tailored to significantly enhance his data science projects. However, a new workstation means he needed to establish a fresh data science environment.Here’s a walkthrough into how he configured his workstation, along with valuable tips to help you optimize your own setup for maximum efficiency. In this setup, Benedict walks you through installing PowerShell 7, WSL, Ubuntu, Git, setting up CUDA, and installing Python with Mamba.How to Setup Windows for Data Science HP Z6 G5 SpecsProcessor: AMD Ryzen Threadripper PRO 7965WX 24-Cores 4.20 GHz Installed RAM: 256 GB (255 GB usable) System type: 64-bit operating system, x64-based processor Graphics: NVIDIA RTX 6000 Ada 48 GB 4DP Graphics

350
Sothan
A
alexander.klugCommunity Manager
published in Artificial Intelligence
📅 GenAI Productionize 2.0 on October 29th

The premier conference for GenAI application development returns on October 29th! Join us at GenAI Productionize 2.0 for an incredible lineup of speakers from HP, Galileo, Databricks, Twilio, Walmart and more.This industry-first summit is all about productionizing generative AI in the enterprise. Gain insights from top AI experts across research labs, startups, and global brands on governance, operational frameworks, and practical evaluation techniques.Don’t miss out—register now: GenAI Productionize 2.0 Registration

740
A
Terms & ConditionsCookie settings