About this podcast
פודקסט טכני בעברית על בניית סוכנים ואפליקציות עם מודלי שפה.
הצטרפו לקהילת הווטסאפ שלנו לדיונים ושאלות:
https://chat.whatsapp.com/JKVFSNFMVQu8G1KWx1jqap
ניוזלטר עם סיכום דו-שבועי של כל הנושאים הכי חמים:
www.langtalks.ai
Episodes
The newest 20 of 75 episodes
- 75 - Post-Training | Dan Padnos (Novee) · 28 min · Season 1 Episode 75When vertical AI companies should post-train open-weight models: SFT vs. RL, agentic rollouts, reward design, and simulated environments.
- 74 - Jev · 31 min · Season 1 Episode 74A grounded look at TypeSafe AI's Jev classifier model: architecture, real use cases, and where it falls short.
- 73 - Harness Engineering · 29 min · Season 1 Episode 73How frontier teams make coding agents run autonomously for hours instead of minutes: AI-ready repos, TDD guardrails, ephemeral environments, tracing, and proof-of-work loops.
- 72 - Personal Assistant Agent · 29 min · Season 1 Episode 72Automating meetings end-to-end with agents - calendar tagging, prep briefings, learning loops, skill sharing, and self-closing feedback cycles.
- 71 - Claw Architectures | Gavriel Cohen (NanoClaw) · 33 min · Season 1 Episode 71A deep dive into the architecture and security model behind autonomous agent harnesses - isolation, credential gateways, and skill-based extensibility.
- 70 - Our Claude Code Tips · 32 min · Season 1 Episode 70A behind-the-scenes look at real agentic-coding workflows: visual planning, cloud-first agents, ephemeral PR environments, custom skills, and secrets management.
- 69 - Marketing for Agents | Nevo David (Postiz) · 35 min · Episode 69How to market and sell to AI agents — discovery channels, CLI vs MCP trade-offs, authentication patterns, and the emerging agent-driven economy.
- 68 - AI-SDLC | Yonatan Maor (Clears.ai) · 23 min · Season 1 Episode 68A practical, stage-by-stage look at running your entire development lifecycle with AI agents: from PRD to coding to QA.
- 67 - FinOps for AI | Yizhar Gilboa (Finout) · 27 min · Season 1 Episode 67A practical look at managing AI budgets across coding agents, customer-facing models, and production inference
- 66 - Scaling LLMOps | Avi Lumelsky (Oligo) · 29 min · Season 1 Episode 66Two real-world use cases are covered: CVE Enrichment for open-source vulnerability detection and real-time Malicious Command Detection, along with practical tips on cost…
- 65 - AI SRE | Asaf Savich (Komodor) · 24 minSite Reliability Engineer agent auto fixes production issues
- 64 - AI coding metrics | Liad Elidan (Milestone) · 28 min · Season 1 Episode 64Measure the actual impact of adopting AI across the R&D
- 62 - AI R&D Rollout | Iko Azoulay (Salt Security) · 30 min · Season 1 Episode 62How AI is used across the SDLC in a real R&D org - requirements, tech design, validation, testing, and code review. What worked, what didn’t, and where teams get stuck.
- 61 - Voice Agents | Shay Davidson (Lemonade) · 29 min · Season 1 Episode 61Building and testing voice agents with realtime API or chained approach (TTS->LLM->STT)
- 60 - Brain Memory | Dr. Meytar Zemer · 28 min · Season 1 Episode 60The Neuroscience behind the human brain and memories
- 59 - SLMs | Dr Elad Granot (Trullion) · 34 min · Season 1 Episode 59the production experience and considerations for fine-tuning a small language model for narrow tasks
- 58 - AWS re:Invent 2026 predictions | Shuki Cohen (AI21) · 28 min · Season 1 Episode 58Recap of the major announcements and innovations from the 2025 re:Invent conference, along with our predictions for where things are heading in 2026
- 57 - Memory | Itamar Friedman (Qodo) · 28 min · Season 1 Episode 57Short and long term memory mechanisms for agents
- 56 - n8n | Shay Shitrit · 24 min · Season 1 Episode 56Getting started with no-code agentic automations, popular use cases and tips







