Ashish Singh·Aug 6, 2025Rethinking AI Copilot Evaluation: Accounting for Bugs, Novelty and Real LearningLarge‑language‑model (LLM) copilots are often sold as time machines: studies claim that developers complete tasks 55 % faster with GitHub
Ashish Singh·Aug 1, 2025Operationalising LLMs: Why Guardrails Are Non-NegotiableBuilding trust, control, and reliability in the era of Generative AI
Ashish Singh·Jul 26, 2025Walking the Line Between Personalisation and Stereotyping in Healthcare AIBalancing helpful personalization with fairness and inclusion in healthcare AI. Principles, pitfalls, and paths forward.
Ashish Singh·Jul 13, 2025Designing a Smarter Customer Support System with RAG and AgentsSmarter support at scale: Learn how agentic RAG systems can classify, respond, and route customer queries with speed, empathy, and…
Ashish Singh·Jun 12, 2025How Apps Trick You: A Deep Dive Into Dark Patterns in UXWe’ve all been there — trying to cancel a subscription or opt out, only to be misled. Welcome to the world of Dark Patterns in UX.
Ashish Singh·Apr 19, 2025How to Fine-Tune Open-Source LLMs on Your Own Data and Evaluate Them EffectivelyLearn how to fine-tune open-source LLMs on your own data for personalized use cases and how to evaluate their performance
Ashish Singh·Apr 9, 2025AI Alignment & Safety: How to Prevent Hallucinations in Generative AIExplore the causes of hallucinations in generative AI, and discover techniques and strategies for building safer, more reliable AI systems.
Ashish Singh·Apr 6, 2025From Vision to Value: The Playbook for Building Successful AI ProductsIn the world of Artificial Intelligence, success isn’t measured merely by technical breakthroughs — it’s about building solutions that…
Ashish Singh·Apr 1, 2025Transformers on GPUs: Architecture, Acceleration, and OptimisationTransformers have transformed deep learning —But have you ever wondered why GPUs are so essential to make them work?
Ashish Singh·Mar 30, 2025Optimizing GPU Costs for Large-Scale GenAI InferenceQuantization, autoscaling, caching, and more — your guide to efficient GPU usage for GenAI inference.A response icon1A response icon1
