Discover how TELUS Digital combined multi-turn conversation data, turn-level evaluation and licensed clinical expertise to help a prominent foundation-model provider benchmark and secure its AI model during high-stakes, emotionally sensitive interactions.
Discover how expert safety analysts at TELUS Digital built a structured reasoning framework that taught a content-moderation LLM to detect nuanced, evasive policy violations.
As foundation models commoditize, the real value now lies in fine-tuning, evaluation and domain-specific AI data. Here's where differentiation is built.
Accelerate AI development with Express Interface. Build dynamic, event-driven post-training interfaces fast using a drag-and-drop UI and Python logic. Eliminate engineering bottlenecks, embed real-time LLM-as-a-judge QC and curate high-quality training data for LLMs, VQA and text-to-SQL tasks.
Learn how TELUS Digital combines LLM automation with "human-on-the-loop" policy stewardship to navigate cultural nuance, resolve policy collisions and prioritize accuracy over scale in content moderation.
Compare ChatGPT Apps SDK, MCP UI and Google A2UI. Learn the pros and cons of these GenUI frameworks to choose the right tech for your next AI project.
Discover how mathematical reasoning datasets are fostering genuine mathematical understanding and advancing the journey toward AGI.
Large language models (LLMs) often express high confidence without a mechanism for reasoning about certainty. Existing benchmarks only assess single-turn accuracy, truthfulness or confidence — until now. We introduce a new benchmark that measures how LLMs balance stability and adaptability when chal...
Explore a technical overview of AI red teaming principles, informed by methodologies our experts at TELUS Digital employ when stress-testing our clients' models for safety and security vulnerabilities.
Explore a detailed technical account of how the team at TELUS Digital built a proof of concept using OpenAI’s Apps SDK, including the architecture choices made, the pitfalls encountered and the lessons learned building on this emerging platform.
Explore our benchmarkable multimodal dataset designed for fine-tuning and evaluating scientific reasoning through domain-grounded visual question answering.
Discover how TELUS Digital incorporates automated quality control agents into our training data pipelines for greater efficiency and accuracy.
Get curated content delivered right to your inbox. No more searching. No more scrolling.
