Keeping up with AI

Swapnil Talekar
  • 0.0 (0)
  • Technology
  • Semiweekly

Keeping Up with AI is a podcast that helps you stay on top of the fast-moving world of artificial intelligence. The show breaks down the latest AI models, tools, breakthroughs, and workflows in a clear and practical way. Instead of chasing every headline, each episode focuses on what actually matters — the ideas, technologies, and productivity techniques that can help developers, builders, and curious professionals use AI more effectively.

  1. 14h ago

    Building a Simple "Software Factory" that works

    A software factory sounds like a new idea, but the pieces look a lot like the loop engineering building blocks I've been covering all along. In this episode, I walk through how to build one yourself, step by step. I map the four steps of a software factory to the loop engineering pieces: isolating each task in its own worktree, building from a workflow file and a house style skill, proving every change with evidence in the pull request, and shipping through an AI review loop with a cap on how many rounds it can run. Along the way I cover the practical limits, like shared ports and databases, recordings that can leak sensitive data, and the cost of running review loops in parallel. I also add two things the basic setup leaves out. The first ismemory, and how repeated review comments can turn into lint rules. The second is a hard gate, a hook that won't let an agent finish until evidence exists. I tested one against a real Claude Code session, and I share what worked and where an agent that's told otherwise can still get around it. This is the second of three episodes on software factories. It'sfor developers who want to implement this, and it helps if you've heard the first part and my loop engineering episodes. SHOW NOTES Full written post on Substack - "Building a Simple Software Factory" Part 1 of this series, "The Role of Humans in Software Factories" My loop engineering series: Substack link Memory and state patterns for loops: Substack link A deep dive on skills, part one: Substack link Ras Mic on Greg Isenberg's podcast, "Building a Software Factory that actually works" The open-source skills and workflow file: Github link Install command for the skills: npx skills add michaelshimeles/skills Creating a worktree by hand: git fetch origin git worktree add -b feature-x ../feature-x origin/main The workflow file is called AGENTS.md. Claude Code reads CLAUDE.md, so add a one-line CLAUDE.md containing @AGENTS.md The seven skills: new-feature, code-structure, evidence-driven-testing, before-and-after, greploop, greploop-apps, unslop Claude Code hook used in the episode: a Stop hook that blocks until a file exists in an evidence folder, with a counter that gives up after three blocks. The script and settings are in the written post. AI code reviewers mentioned: Greptile, CodeRabbit, Macroscope

    Building a Simple "Software Factory" that works

  2. Oct 19

    The Role of Humans in Software Factories

    AI agents that write, test and ship code with no humans involved sounds like the future of engineering. But what happens when nobody reads the code? In this episode, I look at whether "software factories" really deliver the automation they promise with no human oversight. I cover the difference between a lights-on factory and a dark factory, why review has become the bottleneck (with data from Faros AI, IDC and Gergely Orosz), and why code quality decays so quickly when nobody is reading it, including what Dex Horthy learned from his own experiment and what the SlopCodeBench research shows. Then I compare where StrongDM, Dex Horthy, Geoffrey Litt and Lauren Tan each think the human should stand, and why I think they agree more than it first appears. I close with the rule I'm going to try on my own team: the amount of review a change needs should depend on how much automated proof surrounds it, built from three layers of structure, enforcement and evidence. This is the first of three episodes on software factories. Thisepisode is for developers and engineering leaders deciding how much AI-generated code to trust. If you're a product manager or AI-curious, I explain the terms along the way. SHOW NOTES Lauren Tan, "How I Shipped 2000 PRs Last Month, Trusting AI Agents":https://www.youtube.com/watch?v=NjoZoUm85x0 Dex Horthy, "Why Software Factories Fail" (AI Engineer): https://www.youtube.com/watch?v=Ib5GBkD555M Dex Horthy, "Fighting Code Slop: The State of Software Factories" (Agentic AI Foundation): https://www.youtube.com/watch?v=ix1qQK1IvmA Geoffrey Litt, "Understanding is the new bottleneck" (AI Engineer): https://www.youtube.com/watch?v=WkBPX-oDMnA Gergely Orosz, "The state of the tech industry in 2026" (LDX3 New York): http://www.youtube.com/watch?v=Ru99FGJ_yuE StrongDM's software factory page: https://factory.strongdm.ai/ Simon Willison on StrongDM's software factory: https://simonwillison.net/2026/Feb/7/software-factory Faros AI, "AI Acceleration Whiplash" research: https://faros.ai/research/ai-acceleration-whiplash SlopCodeBench paper: https://arxiv.org/html/2603.24755 IDC survey figures, as reported by TechTarget: https://www.techtarget.com/it-infrastructure/news/366651847/Vendors-build-safeguards-for-autonomous-software-factories

    The Role of Humans in Software Factories

  3. Oct 10

    The Decision Model Gold Rush

    A new kind of AI model called Jev launched on September 15. Within about two weeks, Amazon, OpenAI, Cloudflare, and a long list of open-source projects had shipped rivals. Jev is a decision model, which means it picks an answer instead of writing one. The answer can be a choice, a score, or a yes or no with a confidence number attached. In this episode, I step back from the question of which model is best, because any answer would be outdated before you finish listening. Instead, I focus on how to choose one for a real production pipeline. I start with why vendor benchmarks deserve some skepticism, and what the independent DecideBench results show about accuracy and cost. Then I walk through six questions to ask before you commit: where the model runs, what input it accepts, how fast it needs to be, whether its confidence scores hold up on your own data, what it costs at your volume, and how hard it would be to switch later. I also apply those questions to two very different scenarios, support ticket triage and a latency-sensitive trading or game loop, and I close with my prediction for where this category goes next. This episode is for developers, product managers, and engineering leaders. The full written post and all the links are in the show notes. ---- SHOW NOTES ---- Written post: https://swapniltalekar.substack.com/p/the-decision-model-gold-rush Earlier post on Jev (previous week): https://swapniltalekar.substack.com/p/jev-and-the-return-of-the-classifiers?r=1v4ea Models mentioned: Jev (TypeSafe), Strands Decider 2B (Amazon), Decisions API (OpenAI), Clef (Cloudflare), GLiDE and GLiNER2.5-Decide (Fastino), Imajev-4B, Laya, OpenJev, JevK5, von Benchmarks mentioned: DecideBench (Cho Yin Yong), JevBench Comparison table (first week of October 2026): see the written post

    The Decision Model Gold Rush

  4. Oct 5

    Jev And The Return Of Classifiers

    TypeSafe's new model Jev has been billed everywhere as the end of hallucinations, and that framing is misleading. In this episode, I dig into what Jev actually is: a System One model that returns a structured decision instead of open-ended text, paired with a training method called RLCD that's built for calibration rather than raw accuracy. I walk through why this feels like a swing back to the classifiers we used before LLMs ate every decision-making task, why that framing alone undersells what's new here, and why calibration, not the absence of hallucination, is the real breakthrough. I also get into why Jev needs frontier-level text comprehension even though it never produces a word of output, why that makes it hard to benchmark, and why its calibration claims are still essentially a promise from TypeSafe until it's been tested at scale. Finally, I cover the practical limits worth knowing before you reach for it. If you've seen the hype and want the honest read on what Jev is actually good for, this one's for you.

    Jev And The Return Of Classifiers

  5. Sep 27

    Should you be running local models for AI agents?

    Ever wonder why your AI agent burns through thousands of tokens just to say "hi"? In this episode, I break down what I learned after three months of running my own personal Hermes agent, and why I ended up completely rethinking how I run models for it. We dive deep into how agent frameworks actually use an LLM's context window, and why a single "hi" message can costanywhere from 10,000 to over 40,000 tokens. It's not a bug; it's what makes an agent an agent. From there, I walk through why local models and even frontiermodels like Claude and GPT became impractical for a hobby budget, a sneaky Hermes config bug that cost me weeks, and how I eventually landed on OpenRouter, a model gateway that turned out to be super useful. I cover automatic failover, multi-level caching, and why sticky sessions matter so much for agent workloads specifically. If you're building or running your own AI agent, this one willsave you some expensive trial and error. Show Notes Full article: "Should you be running LLM models locally for your agents?" — Swapnil Talekar's SubstackHermes config fix for the encrypted content error: set include_encrypted_content: false in ~/.hermes/config.yamlModels mentioned: Qwen-3.6-35B-A3B, DeepSeek-v4-Flash, NVIDIA Nemotron (free tier)Inference providers referenced: Together AI, Fireworks AIGateway discussed: OpenRouter

    Should you be running local models for AI agents?

  6. Sep 8

    Running personal AI agents with Hermes

    Three months ago, I gave up on OpenClaw and switched to Hermes for running my own personal AI agents, and I've been living with it since. In this episode, I walk through what actually changed. Everything that I learnt and everything that surprised me. I talk about some of the Hermes internals and what makes it so powerful: profiles that isolate memory, workspace, and even the messaging gateway per agent, which is the single feature that makes Hermes feel more like actually distinct agents. I get into the three agents I use daily: a personal accountantthat watches my investments, a health coach that logs my meals and workouts over Telegram, and a Montessori teacher for my four-year-old, plus how I picked cheap, capable models through OpenRouter instead of running anything locally. I also cover what hasn't gone smoothly: agents that mark work done without checking it, a genuinely strange recurring date bug that hit two unrelated agents, and one agent that looped a hundred and fifty times fixing a bug that turned out to be one missing HTML tag. This one's for anyone experimenting with personal AI agents, or thinking about it- developers and tinkerers especially- or anyone curious what living with an always-on AI assistant is actually like. Full Substack article -https://swapniltalekar.substack.com/p/three-months-of-running-personal?r=1v4ea

    Running personal AI agents with Hermes

  7. Aug 23

    The Truth About Mult-Agent Workflows

    Everyone on AI Twitter seems to be running a twelve-agent swarm that ships products while they sleep. Meanwhile, most real workflows still look like three chat tabs and a lot of copy-pasting. In this episode, I dig into whether multi-agent workflows are real or mostly marketing. I break down how Claude, Cursor, and Codex each approach running multiple agents at once: Claude's Agent Teams, with a team lead, a shared task list, and file locking; Cursor's orchestration workspace, including Best of N and Build in Parallel; and Codex as a specialist agent that other systems orchestrate around. I walk through the five patterns that actually show up in practice, plan-build-review, parallel research, role specialization, best-of-N comparison, and long-task splitting, and explain why splitting work across agents still beats one super-agent, even as models get smarter. This episode is for developers, engineering leaders, and product managers working with AI tools day to day. If you're AI-curious but non-technical, it's a good listen for thinking about how these patterns might apply to your own work eventually. Substack article link - https://swapniltalekar.substack.com/p/are-managers-really-becoming-better?r=1v4ea

    The Truth About Mult-Agent Workflows

  8. Aug 10

    Agent memory and state patterns for loops

    This episode is part of my loop engineering series, and it's about the piece that decides whether a loop actually gets better over time: memory. I talk about what memory actually is, since it gets confused with two other things constantly: the context window, which disappears the moment a session ends, and a project knowledge file, which stays static across runs. Memory is neither. It's the dynamic record of what a loop decided, what failed, and what's still open. From there I walk through three memory patterns, starting with the flat text file, through task trackers, to structured stores for when semantic search actually earns its complexity. I cover how to wire memory updates into hooks so they happen automatically, and four specific ways memory setups break in practice. Hope you find it useful. Show Notes Full article: Substack link Related episodes: Loop Engineering: Putting agents on Autopilot The missing guide for AI Agent Skills – Part I The missing guide for AI Agent Skills – Part II Coming soon: Parallel agents — worktrees, sub-agents, and Agent Teams

    Agent memory and state patterns for loops
See All (17)

About

Keeping Up with AI is a podcast that helps you stay on top of the fast-moving world of artificial intelligence. The show breaks down the latest AI models, tools, breakthroughs, and workflows in a clear and practical way. Instead of chasing every headline, each episode focuses on what actually matters — the ideas, technologies, and productivity techniques that can help developers, builders, and curious professionals use AI more effectively.

Information

  • Creator
    Swapnil Talekar
  • Years Active
    2026
  • Episodes
    17
  • Rating
    Clean
  • Copyright
    © Swapnil Talekar
  • Show Website
    Keeping up with AI