More The TWIML AI Podcast episodes
Published 26 Feb 2026
Duration: 4735
Large Language Models (LLMs) have made significant advancements in 2026, with improved reasoning capabilities and integration of external tools to enhance accuracy, reduce hallucinations, and expand practical applications.
In this episode, Sebastian Raschka, independent LLM researcher and author, joins us to break down how the LLM landscape has changed over the past year...
The podcast examines the current state and recent developments of Large Language Models (LLMs) in 2026, with a focus on improvements in reasoning capabilities and the integration of external tools. Pre-training has reached a mature stage, leading to increased emphasis on post-training techniques that enhance model functionality and accuracy. These advancements have allowed LLMs to perform more reliable tasks such as proofreading, document processing, and information extraction, while also reducing the occurrence of hallucinations. Newer models like Opus 4.6, OpenAI 5.3, OpenClaw, and Multibot have been introduced, along with improved tooling that supports real-world applications and more complex interactions.
LLMs are increasingly being incorporated into coding workflows, aiding in verification, debugging, and performance optimization. The conversation underscores the significance of inference scaling and the development of more reliable, scalable, and cost-effective models to support broader application. While the interface used can influence user experience, the surrounding tools and systems play a critical role in determining the models overall performance and practical utility. There is a growing emphasis on efficiency and the refinement of reasoning techniques to enhance the effectiveness of LLMs across different domains.
7 May 2026 How to Find the Agent Failures Your Evals Miss with Scott Clark
Distributional employs post-production analytics, unsupervised learning, and LLMs to analyze agent traces, detect patterns and anti-patterns like hallucinations, address distributional shifts, and generate actionable insights for AI system refinement in security and enterprise settings, emphasizing adaptive analytics and domain expertise.
30 Apr 2026 How to Engineer AI Inference Systems with Philip Kiely
AI inference deployment is accelerating, emphasizing inference engineering's critical role in optimizing generative models with advanced hardware and complex systems, while addressing challenges like latency, scalability, and modality-specific optimizations amid evolving industry trends and fragmented yet open-source-driven markets.
16 Apr 2026 How Capital One Delivers Multi-Agent Systems with Rashmi Shetty
Capital One's *Chat Concierge* multi-agentic AI system streamlines car-buying through self-reflection, real-time APIs, and LLM-driven workflows, addressing enterprise AI challenges like governance, scalability, and legacy system integration while prioritizing compliance, observability, and flexible platform adoption.
26 Mar 2026 The Race to Production-Grade Diffusion LLMs with Stefano Ermon
The text traces generative models' evolution from early image generation to diffusion models' stability, highlights Mercury II's advancements in speed and efficiency, and addresses ongoing challenges in scalability, multimodal integration, and future research in controllability and cross-modal unification.
10 Mar 2026 Agent Swarms and Knowledge Graphs for Autonomous Software Development with Siddhant Pardeshi
AI integration into software development is transforming code creation, maintenance, and optimization, with significant implications for technical and business outcomes.