The TWIML AI Podcast

In this episode, @jaredq_, founder and CEO at @mlfoundry, introduces the concept of "compound AI systems," which allows users to create powerful, efficient applications by composing multiple, often diverse, AI models and services. We discuss how these "networks of networks" can…

Just 1 hour to go until our Generative AI study group meets! Join us and exchange insights on traditional ML vs. generative AI-native applications, discuss approaches to evaluating long-context model performance, collaborate on ongoing projects like the TWIML-RAG chatbot, and…

Bring someone along and join us tomorrow at 8 am PT for our Generative AI study group and discuss RAG benchmarks, explore cutting-edge generative workflows, swap tips on building production-ready LLM systems, and more! If you haven’t signed up yet, head over to…

Learn, share, and connect in our Generative AI study group! Discuss trending news and topics, explore new tools and techniques together, hear from generative AI experts, and more! Everyone’s welcome—just register at twimlai.com/community/ and meet us every Friday at 8 am PT.

In this episode, @kwindla Kramer, co-founder and CEO of @trydaily and creator of the open source @pipecat_ai framework, joins us to discuss the architecture and challenges of building real-time, production-ready conversational voice AI. Kwin breaks down the full stack for voice…

Fatih Porikli breaks down @QCOMResearch on-device demos from #CVPR2025: ✅ Text-to-3D mesh generation in under 3 seconds ✅ Real-time image-to-video generation + video-to-video stylization ✅ Multimodal visual QA with no cloud connection needed Explore more about the demos and…

Just an hour away from our Generative AI study group! ⏳ Don’t miss out on today's session where you can unpack LLM interpretability methods, explore evaluation strategies for agent performance, discuss model distillation techniques, and more! Be sure to drop by in an hour! ⌚

Join our Generative AI study group tomorrow at 8 am PT for another round of collaborative learning and dig into reinforcement learning techniques like Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO), best practices for chaining…

Fatih Porikli from @QCOMResearch explains how the world knowledge in LLMs acts as a regularizer and helps AVs generalize solutions for rare "long-tail" scenarios, reducing the need to manually model every edge case. By combining that with efficient vision-based perception, we get…

Engage in casual AI discussions, collaborate with fellow enthusiasts on projects, deep dive into codes, and more in our Generative AI study group! Sign up at twimlai.com/community/ and join us weekly on Fridays at 8 am PT. See you there!

Today, we're joined by Fatih Porikli, senior director of technology at @QCOMResearch for an in-depth look at several of Qualcomm's accepted papers and demos featured at this year’s CVPR conference. We start with “DiMA: Distilling Multi-modal Large Language Models for Autonomous…

Get ready to join our Generative AI study group in 1 hour! Share techniques for grounding LLMs, exchange tips on managing prompt libraries, participate in the RAG chatbot project, and more! The conversations are informal and you're welcome to join at any time during the session.

Make it to tomorrow’s session of our Generative AI study group by registering at twimlai.com/community and discuss deep research tools, explore vision-language-action (VLA) pipelines, share strategies for effective unsupervised reinforcement learning, and more! The meeting…

Do you have an interesting LLM project to share? Share it in our Generative AI study group! Join our TWIML community members who share the same passion for generative AI and meet us every Friday at 8 am PT. Sign up at twimlai.com/community/ and see you there!

How do you get AI agents to work together seamlessly? @vijoy from @OutshiftbyCisco outlines the four requirements of agent-to-agent collaboration—discovery & identity, workflow composability, deployment, and observability & evaluation. Gain insights into how these steps ensure AI…

Are we crazy to replace reliable, deterministic APIs with noisy, probabilistic agents? 🤯 In our latest episode, @vijoy of @outshiftbycisco argues it's a necessary pain & introduces the "deterministic sandwich" 🥪 — a pragmatic way for enterprises to tame AI chaos until they're…

Four requirements for agentic collaboration by @vijoy: Discovery, Composability, Deployment, and Evaluation Ensure your agents are validated, well-integrated, efficiently deployed, and constantly evaluated. Essential steps for optimizing the agentic landscape! @AGNTCYAI…

1 hour left before this week’s meetup of our Generative AI study group starts! If you haven’t registered yet, head over now to twimlai.com/community/ and check your email for Slack registration details. Remember to join the #generative-ai Slack channel!

The agent protocol wars are raging: A2A vs MCP vs ACP (vs ACP!) vs... 🔥 But what if this battle just "doesn't make sense"? In this clip from the latest @twimlai ep, @vijoy of @OutshiftbyCisco makes a provocative plea for convergence, arguing that at the end of the day, "it's…

Tomorrow at 8 am PT, join our Generative AI study group and share insights on the role of vector databases in LLM-powered applications, discuss best practices for building agent workflows, swap ideas on prompt storage methods, and more! Head over to twimlai.com/community/ to…