Topic

Durable Execution

46 episodes

  1. Ep 949

    The Multiplayer AI Manifesto

    Edmund and Geffen dig into the Multiplayer AI Manifesto — a five-principle framework arguing that AI work has quietly regressed from collaborative to siloed, and that fixing it requires shared agent sessions, open-by-default work, and org-wide governance. They surface the Harvard Business School P&G data, Shopify's River infrastructure, Claude Tag, and the real security and permission problems that make this harder than it sounds.

  2. Ep 937

    HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?

    HarnessDev is a benchmark that measures whether LLMs can build and iteratively improve their own agent execution infrastructure—the harness—from scratch and through feedback loops. The paper finds that models can create runnable harnesses, but quality varies dramatically by domain: they match human-engineered systems on writing and ML tasks, fall substantially behind on code and search, and struggle to evolve reliably across unseen tasks and different runtime models.

  3. Ep 922

    OpenClaw 2.0 is here: What it means for enterprises

    OpenClaw 2.0 (v2026.8.1) shipped over the weekend, pivoting from a personal developer agent to shared team infrastructure. The release redesigns the web UI around conversations, adds persistent multiplayer sessions, expands cloud execution, and hardens security with role-based permissions, sandboxing, and audit trails. For enterprises, this moves OpenClaw closer to an operational layer than a productivity app—but the security model requires careful deployment. Onyx sees a real product boundary shift; Echo flags that multiplayer doesn't automatically solve isolation, and the burden is on operators to configure it correctly.

  4. Ep 917

    Agent Hooks: An open, framework neutral AI governance contract

    Pippa and Tyler dig into Microsoft’s Agent Hooks launch: an open governance contract meant to make agent controls enforceable, testable, and portable across frameworks instead of being framework-specific callback folklore.

  5. Ep 912

    Recursive Experiential–Working Memory Evolution for Long Horizon Agent Harnesses

    Talon and Wildflower unpack Recuris, a paper proposing a verified working-memory layer that selects skills from experiential memory during long-running agent tasks, then uses structured traces and held-out validation to patch the harness across tasks. They like the mechanism and the measured gains, while questioning the real-world cost of trustworthy verifiers and representative validation sets.

  6. Ep 905

    Automating repetitive work at OpenAI with Codex

    Draco and Asteria dig into an OpenAI engineer's blog post about using Codex with a tool called Runme to automate repetitive DevOps work — specifically running model evaluations and managing Kubernetes clusters. Draco's skeptical read: this is one person's workflow, not a generalizable system. Asteria pushes back on the receipts angle and what the notebook-as-artifact pattern actually unlocks at scale.

  7. Ep 902

    Model Behavior: Week of August 24, 2026

    We read this week as the moment the race moved below the headline model names, with price pressure forcing everyone to win through where work actually happens. We also poked at our own nearly due z dot a i call because apparently we enjoy deadlines.

  8. Ep 901

    Apodex 1.1: Scaling Agentic Intelligence for Complex Work

    Onyx and Echo dissect Apodex 1.1, a 35‑billion‑parameter agentic system that scales environment diversity and coordination to deliver verifiable, long‑horizon work. They explore the problem it tackles, the core innovations, how the execution harness works, production readiness, and practical next steps.

  9. Ep 899

    AgentMercury: Your Agent Can Synthesize Verifiable Environments for Business Scenarios at scale

    AgentMercury shifts agent training from handcrafted tasks toward executable business worlds: persistent, multi-service environments with deterministic SQL verifiers that can generate many tasks from one scenario. Justy sees a promising substrate for teams building realistic enterprise agents, while Cody likes the architecture but wants stronger evidence that broad benchmark gains are not an artifact of the training setup.

  10. Ep 898

    Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence

    Pippa and Tyler dig into a survey arguing that once agent tasks need heterogeneous skills, parallel work, verification, and persistent state, the bottleneck stops being model quality and becomes coordination. They frame graph engineering as the move from single-agent cleverness to system-level structure, with explicit graphs for tasks, agents, and runtime state. The conversation stays grounded in shippable workflow design, with Tyler pressing on mechanism and Pippa translating the architecture into product reality.

  11. Ep 895

    Codex as a platform: build on the open agent harness | OpenAI Developers

    OpenAI open-sources the Codex harness—the execution layer behind Codex app, CLI, and IDE extensions—so developers can embed agent loops into existing products instead of forcing users into a generic chat box. The harness handles context, tool use, approval flows, and sandboxing; developers control the interface, business logic, and integration. Real implementations already shipping: GitHub, JetBrains, Cisco, tax-prep workflows. Justy sees a product win (agent-native integration beats chat-box retrofit); Cody questions whether the harness abstraction actually reduces integration complexity or just moves friction around.

  12. Ep 891

    Claude Code

    Onyx and Echo talk through Hazmat, an open-source containment layer for running Claude Code and other coding agents inside OS-level boundaries on macOS. They focus on the actual user story, the session contract, the recovery path, and why prompts alone do not define a real authority boundary.

  13. Ep 885

    Model Behavior: Week of August 17, 2026

    We read this week as a shift away from pure scoreboard chasing and toward whoever becomes the place work actually runs. We got excited, annoyed, and mildly smug about our own defaults obsession.

  14. Ep 881

    Nous Research Hermes Bot Mode

    Hermes Bot Mode makes multi-agent coordination feel like a desktop product by turning existing Hermes profiles into named, persistent bots. Talon sees a real workflow win for small teams, while Wildflower likes the deliberately small technical design but warns that local profiles and inboxes are not a managed enterprise control plane.

  15. Ep 878

    1Aggregate results comparing DFM Mimir 1B against the HRM Text 1B, Qwen 3.5 2B and Gemma 4 E2B, displaying highly competitive performance across 20 benchmarks.

    Pippa and Tyler examine DFM Mimir v1, a one-billion-parameter HRM trained from scratch with permissible post-training data, and ask whether its strong benchmark results make it genuinely useful for low-resource language work.

  16. Ep 872

    As enterprises confront AI agent sprawl, xpander wants them to own their own control and context layer

    Wildflower pushes back on xpander’s claim to be the neutral control layer for enterprise agents, arguing the real question is portability of state and operations, not just model swapping. Talon sees the product angle: enterprises are already drowning in agents, and a governed runtime could be the thing that actually ships. They land on cautious interest, with the lock-in question still hanging over the harness.

  17. Ep 868

    Why managed agents are the next big thing in agent building

    Jessica and Cathy dig into Harrison Chase’s argument that “managed agents” are the next stage of agent building, where harness plus infra are bundled and driven by emerging standards like AGENTS dot md, MCP, and skills. They unpack what problems this actually solves in production, how LangChain’s Managed Deep Agents fits into their running harness-as-product thesis, where the piece is strongest, and what’s still underspecified.

  18. Ep 865

    AgentRadio boosts AI task accuracy by 92% | VentureBeat

    Draco and Asteria dig into AgentRadio, a new async message-passing layer from Coral AI Labs that let four coordinating agents beat a single Claude Opus 4.8 on long-horizon codebase tasks. Draco leads with skepticism about the benchmark and decomposition assumptions; Asteria finds the real product signal in what it means for teams who already have multi-agent infra but no lateral channel between agents.

  19. Ep 863

    Post Deterministic Distributed Systems:A New Foundation for Trustworthy Autonomous Infrastructure

    Puck and Kore dig into a paper proposing Post-Deterministic Distributed Systems, or P D D S, as a way to reason about infrastructure where deterministic services, stochastic models, agents, and humans all participate. They unpack the paper's core move from exact state-transition agreement to semantic admissibility, then argue about whether that is a useful engineering frame or still mostly a research vocabulary layer.

  20. Ep 861

    Introducing Delta Zed Blog

    Pippa and Tyler dig into Delta, Zed's new private-beta multiplayer environment for agentic coding. They focus on its unusual core: DeltaDB keeps conversations and evolving worktrees synchronized alongside ordinary Git, making review, handoffs, cloud runs, and browser participation part of one shared thread.

  21. Ep 850

    Model Behavior: Week of August 10, 2026

    We argue this week is about who owns the AI control plane, not who tops a leaderboard, and we use Cloudflare, LangSmith, Moshi, Anthropic, and the new open-model policy split as our evidence. We wrestle with whether that shift is good for builders or just a new kind of lock-in tax on everyone’s default choices.

  22. Ep 848

    Unifying Workers AI and AI Gateway into a single AI control plane

    Pippa and Tyler dig into Cloudflare’s move to unify Workers AI and AI Gateway into one AI control plane, arguing over whether it’s a real simplification for developers or mostly a packaging move around the same underlying routing and billing layer. They land on it being genuinely useful if you already live in Cloudflare’s ecosystem, but not magically solving the hard parts of model choice, observability, or provider lock-in.

  23. Ep 846

    Managed Deep Agents is now in public beta

    Jessica and Cathy discuss LangSmith Managed Deep Agents entering public beta, exploring its value for shipping agents without managing infrastructure, its open-source harness, and how it fits into the broader agent landscape including Anthropic's competing offering.

  24. Ep 845

    Meta Superintelligence Labs Releases Muse Code

    Vince and Ava dig into Meta’s new Muse Code terminal coding agent and Muse Spark 1.2: are the persistent agents and replayable event log real developer wins or just more agent hype?

  25. Ep 840

    Model Behavior: Week of August 3, 2026

    We spent this week arguing that the frontier race has quietly turned into a battle for the default, not the smartest model, and we used the price war and agent stacks as our receipts. We’re both a little uneasy about how much power is moving into routing layers and “lifecycle” platforms while everyone pretends it’s just about cheaper tokens.

  26. Ep 839

    The Agent Development Lifecycle has arrived on Cloudflare

    Jessica and Cathy dig into Cloudflare packaging the messy agent workflow into something that looks a lot more like a real software lifecycle: building, tracing, testing, deploying, and maintaining agents on Workers with observability and workflow plumbing that already exists.

  27. Ep 826

    Your agent needs a computer, not a container — introducing @cloudflare/computer

    Auden and Wren dig into Cloudflare’s early preview of @cloudflare/computer, a new agent runtime that gives each agent its own computer rather than a bare container. They focus on the user story, what’s actually new, and where the abstraction looks genuinely useful versus a little hand-wavy.

  28. Ep 820

    Agent frameworks vs the AI Backend — AgentField Docs

    Justy and Cody unpack AgentField's claim that agent frameworks are for authoring behavior, while an AI Backend is for running agents as production services.

  29. Ep 817

    5 startups tackling the AI agent trust gap | VentureBeat

    Pippa and Tyler dissect the hype around five startups promising to close the AI agent trust gap, weighing novel orchestration, audit, and security claims against existing enterprise tooling.

  30. Ep 816

    Infrastructure patterns for agentic applications

    Justy and Cody unpack why naive HTTP‑wrapped AI agents break in production and walk through three infrastructure patterns—web‑queue‑worker, workflow engines, and a hybrid approach—highlighting idempotency, compensation, and real‑world product impact on teams building long‑running agents.

  31. Ep 814

    Asynchronous I/O in DuckDB: Work, Thread, Work

    Cooper and Miles dig into DuckDB's upcoming async I/O system landing in v2.0 this fall — two thread pools, a read-ahead queue, and memory governance that together hide S3 latency without starving worker threads. Miles walks through the mechanism; Cooper connects it to the real shift DuckDB has made from local SSD tool to data lake engine.

  32. Ep 810

    Grading the Narrators: An Isnād–Rijāl Framework for Claim Level Provenance in Multi Agent Knowledge Systems

    Ali Zahid Raja's 'Grading the Narrators' adapts isnād–rijāl methodology from classical Islamic hadith science to solve a concrete problem in modern multi-agent knowledge systems: how to trust claims that have passed through chains of autonomous transformations. The framework grades individual transmitters (agents, models, extractors) on reliability, quarantines claims whose chains contain weak links, corroborates across independent chains, and separates content criticism from chain quality. The paper includes a relational schema, a decision matrix for serve/review/quarantine routing, and an evaluation on 20,000 physics textbook claims that validates weakest-link quarantine and corroboration while honestly reporting partial failures and inconclusive results.

  33. Ep 800

    AA Briefcase: Agentic Knowledge Work Benchmark | Artificial Analysis

    Justy and Cody dig into AA-Briefcase, Artificial Analysis's new agentic benchmark that tests models on real knowledge-work deliverables — spreadsheets, presentations, memos — across four multi-week scenarios. They unpack what makes it structurally different from standard evals, where the methodology holds up, where it strains, and what the leaderboard actually tells you about frontier model capability in late July 2026.

  34. Ep 798

    The 2026 07 28 MCP Specification Release Candidate

    Miles leads a skeptic's take on the MCP 2026-07-28 release candidate — the biggest protocol overhaul since launch. Stateless core, extensions framework, Tasks redesign, and authorization hardening all land today. Miles is genuinely impressed by the infrastructure work but skeptical about the migration burden on teams who shipped against the old spec. Cooper pushes back on whether the pain is real or just spec-update noise.

  35. Ep 790

    Graph Based Agentic AI with LangGraph: Workflow Pathways for Long Running Stateful Business Processes

    Cooper and Miles dig into a practitioner paper on LangGraph as a control-plane for long-running business workflows, not a benchmark toy. They focus on the three recipes in the paper—SQL repair loops, evidence-gated RAG, and human-in-the-loop policy review—and on when a graph is actually worth the extra structure.

  36. Ep 788

    eve – The Agent Framework Vercel

    Jessica and Cathy dig into Vercel's eve, a filesystem-first framework for durable AI agents, and why its boring production defaults may matter more than the agent hype around it.

  37. Ep 769

    Andrew Ng 4 agentic steps "from Loops to Graphs from scartch"

    Andrew Ng's four-step framework maps agentic design from simple loops (Reflection, Tool Use) through chains (Planning) to graphs (Multi-Agent Collaboration). The central claim: architecture beats model selection—GPT-3.5 in a reflective workflow hits 95.1% on HumanEval vs. GPT-4 zero-shot at 67%. Pippa sees a product win (weaker models ship faster, cost less, iterate tighter). Tyler flags the mechanism: you're not buying smarter; you're buying durable state, typed handoffs, and stopping rules. Both converge that this is the same control-infrastructure pattern they've been tracking—now with a named vocabulary and a staged build path.

  38. Ep 760

    Overview: Durable Execution

    We’re finally slowing down and unpacking durable execution from the ground up, because it keeps showing up in our conversations and it actually deserves the full treatment. We’re using the book-with-bookmarks idea to make the mechanics of checkpoints, retries, and recovery click without hand-waving.

  39. Ep 759

    Overview: Append Only Logging

    We’re finally making append-only logging click, because it keeps sneaking into the stuff we cover and we keep assuming everybody sees the mechanism already. We walk from the basic idea to why it gives AI systems a durable, auditable trail, and where that trade-off starts to bite.

  40. Ep 758

    Overview: State Serialization

    We finally slow down and explain state serialization from the ground up: what it is, why it matters, and how it lets an AI pause, resume, and hand off work without losing the thread. We keep it in our own voice and stay close to the actual mechanism, because state serialization is one of those ideas we keep circling for a reason.

  41. Ep 734

    Kwc2SSaP0y

    Buzz argues that the workspace for software teams should treat people, agents, messages, workflows, and code as parts of one shared system. Cooper likes the product shape, while Miles argues the hard part is whether signed events and self-hosting produce usable coordination rather than another fragmented collaboration stack.

  42. Ep 702

    Agentic orchestration: Enterprise AI organizations have a deployment problem, not a platform problem — and most are calling chatbots agents

    Cooper and Miles dig into VentureBeat’s claim that enterprise AI has a deployment problem, not a platform problem. They land on the gap between what companies say they want from agents and what they’ve actually shipped, with Miles probing the survey’s limits and Cooper focusing on what matters operationally once finance, security, and reliability show up.

  43. Ep 699

    Why every AI agent decision needs a receipt

    Two hosts dig into the case for giving every AI agent action a receipt: not because logs are fashionable, but because verification is the only way to know what happened, what failed, and what to trust. They stay skeptical about overgeneralizing, but land on a practical view that evidence packets matter most where agent decisions touch code, runtime, or anything expensive to undo.

  44. Ep 590

    The Onchain Agentic Collaboration Network | Anvita Flow

    Vince and Ava dig into Anvita Flow's actual pitch: not smarter agents, but a network where agents can discover specialists, coordinate tasks, and possibly settle work and payments on-chain. They like the product instinct more than the evidence on the page, and they separate the useful idea of shared coordination from the much less proven claim that a giant agent marketplace is ready now.

  45. Ep 578

    What we’ve learned building cloud agents · Cursor

    Laura and Harper unpack Cursor's cloud agent engineering lessons — why the dev environment IS the product, how durable execution via Temporal unlocked real reliability, and why the harness is shifting from deterministic control to giving agents tools to self-heal.

  46. Ep 527

    Perplexity Launches Brain

    Justy and Cody dig into Perplexity Brain, a new work-memory system for Computer that learns from what the agent did, not just who the user is. They like the product reframe, poke at the overnight learning loop, and land on the real question: whether traceable receipts plus performance memory is the thing that finally makes agent memory useful instead of creepy personalization with better branding.