エピソード

  • How Does Anthropic Use Formal Verification to Build Better Code?
    2026/11/15
    Formal verification has long been seen as an academic luxury, too slow and expensive for anything except chips, aircraft, and cryptography. AI changes that math, because models can now draft the specifications, invariants, and proof scaffolding that used to take weeks of expert time, while machine checkers stay just as unforgiving as before. This episode looks at what verification at scale actually means for builders, separates what is publicly known from what is speculation, and argues that the scarce skill is no longer writing code or even proofs, it is writing down precisely what correct means.


    Produced by VoxCrea.AI

    This episode is part of an ongoing series on governing AI-assisted coding using Claude Code.

    👉 Each episode has a companion article — breaking down the key ideas in a clearer, more structured way.
    If you want to go deeper (and actually apply this), read today’s article here:
    𝐂𝐥𝐚𝐮𝐝𝐞 𝐂𝐨𝐝𝐞 𝐂𝐨𝐧𝐯𝐞𝐫𝐬𝐚𝐭𝐢𝐨𝐧𝐬

    At aijoe.ai, we build AI-powered systems like the ones discussed in this series.
    If you’re ready to turn an idea into a working application, we’d be glad to help.

    続きを読む 一部表示
    8 分
  • Why Do AI Code Metrics Look Perfect But Fail Real-World Tests?
    2026/11/14
    AI-generated code usually comes with good numbers attached: passing tests, high coverage, fast benchmarks, and clean lint reports. Those numbers measure what was easy to check, and the code was shaped by that same easy target. The real costs show up elsewhere, in tail latency under real load, behavior on data nobody tested, cost per request, and how long the next change takes. This episode is about why AI code is especially good at hitting the numbers you watch, and how builders can choose measurements that tell them what they actually need to know.


    Produced by VoxCrea.AI

    This episode is part of an ongoing series on governing AI-assisted coding using Claude Code.

    👉 Each episode has a companion article — breaking down the key ideas in a clearer, more structured way.
    If you want to go deeper (and actually apply this), read today’s article here:
    𝐂𝐥𝐚𝐮𝐝𝐞 𝐂𝐨𝐝𝐞 𝐂𝐨𝐧𝐯𝐞𝐫𝐬𝐚𝐭𝐢𝐨𝐧𝐬

    At aijoe.ai, we build AI-powered systems like the ones discussed in this series.
    If you’re ready to turn an idea into a working application, we’d be glad to help.

    続きを読む 一部表示
    10 分
  • Why Does AI Forget Your Code Constraints Mid-Conversation?
    2026/11/13
    Builders state a hard constraint early in a session, like never touch the auth module or all writes go through the queue. Three turns later the AI is writing code that treats that rule as optional advice, and it still sounds compliant. This episode looks at why a constraint you said once in conversation slowly loses force as it competes with newer instructions. It also covers why the fix is to move constraints out of the conversation and into artifacts the system enforces.


    Produced by VoxCrea.AI

    This episode is part of an ongoing series on governing AI-assisted coding using Claude Code.

    👉 Each episode has a companion article — breaking down the key ideas in a clearer, more structured way.
    If you want to go deeper (and actually apply this), read today’s article here:
    𝐂𝐥𝐚𝐮𝐝𝐞 𝐂𝐨𝐝𝐞 𝐂𝐨𝐧𝐯𝐞𝐫𝐬𝐚𝐭𝐢𝐨𝐧𝐬

    At aijoe.ai, we build AI-powered systems like the ones discussed in this series.
    If you’re ready to turn an idea into a working application, we’d be glad to help.

    続きを読む 一部表示
    10 分
  • Why Do AI Async Callbacks Create Code That's Hard to Understand?
    2026/11/12
    AI coding tools write async code one step at a time. Each step is a local, reasonable reaction to whatever the previous step returned, and the result is nested callbacks, promise chains with retries and fallbacks bolted on, and await sequences whose order nobody actually decided. The code runs and passes the happy-path tests, but the flow only makes sense in the context window that produced it, so the next person, or the next AI session, has to reverse-engineer the control flow before changing anything. This episode argues that async flow is an architectural decision the builder has to make up front, because AI will otherwise make it by accident, one append at a time.


    Produced by VoxCrea.AI

    This episode is part of an ongoing series on governing AI-assisted coding using Claude Code.

    👉 Each episode has a companion article — breaking down the key ideas in a clearer, more structured way.
    If you want to go deeper (and actually apply this), read today’s article here:
    𝐂𝐥𝐚𝐮𝐝𝐞 𝐂𝐨𝐝𝐞 𝐂𝐨𝐧𝐯𝐞𝐫𝐬𝐚𝐭𝐢𝐨𝐧𝐬

    At aijoe.ai, we build AI-powered systems like the ones discussed in this series.
    If you’re ready to turn an idea into a working application, we’d be glad to help.

    続きを読む 一部表示
    10 分
  • Why Does AI Code Fail When Chained Together?
    2026/11/11
    Each AI-generated module passes its own tests, reads cleanly, and does what the prompt asked. Then you wire three of them together and the system breaks in ways no single piece explains. That is the composition cliff: every generation session makes its own quiet assumptions about formats, nulls, retries, ordering, and ownership, and those assumptions never get reconciled with each other. As builders move from single-file help to multi-agent pipelines and AI-built services that call other AI-built services, this cliff has become where most production failures actually happen.


    Produced by VoxCrea.AI

    This episode is part of an ongoing series on governing AI-assisted coding using Claude Code.

    👉 Each episode has a companion article — breaking down the key ideas in a clearer, more structured way.
    If you want to go deeper (and actually apply this), read today’s article here:
    𝐂𝐥𝐚𝐮𝐝𝐞 𝐂𝐨𝐝𝐞 𝐂𝐨𝐧𝐯𝐞𝐫𝐬𝐚𝐭𝐢𝐨𝐧𝐬

    At aijoe.ai, we build AI-powered systems like the ones discussed in this series.
    If you’re ready to turn an idea into a working application, we’d be glad to help.

    続きを読む 一部表示
    11 分
  • Why Does AI Code Hide Errors Until Systems Fail?
    2026/11/10
    AI coding tools reliably wrap risky calls in try/except blocks, log a warning, return a safe default, and keep going. The code looks defensive and passes review, but the failures underneath pile up in layers until the only sign of trouble is that something stopped happening: a post that never went out, a token that expired unnoticed, a job that finished cleanly with nothing done. This episode argues that AI-generated error handling is tuned to keep the code running, not to make failures visible, and that builders have to decide on purpose where a system should fail loudly.


    Produced by VoxCrea.AI

    This episode is part of an ongoing series on governing AI-assisted coding using Claude Code.

    👉 Each episode has a companion article — breaking down the key ideas in a clearer, more structured way.
    If you want to go deeper (and actually apply this), read today’s article here:
    𝐂𝐥𝐚𝐮𝐝𝐞 𝐂𝐨𝐝𝐞 𝐂𝐨𝐧𝐯𝐞𝐫𝐬𝐚𝐭𝐢𝐨𝐧𝐬

    At aijoe.ai, we build AI-powered systems like the ones discussed in this series.
    If you’re ready to turn an idea into a working application, we’d be glad to help.

    続きを読む 一部表示
    8 分
  • How Does AI Code Handle Concurrent Access in Multi-Threaded Systems?
    2026/11/09
    AI-generated code tends to handle concurrency by assuming it away. It reads a value, decides something, and writes back as if no other worker could act in between, and it passes every test because tests run one thing at a time. This episode looks at the hidden check-then-act gaps, shared files, and 'just one more retry' logic that hold up in development and quietly break the moment a second process, a cron job, or a scaled-out worker shows up.


    Produced by VoxCrea.AI

    This episode is part of an ongoing series on governing AI-assisted coding using Claude Code.

    👉 Each episode has a companion article — breaking down the key ideas in a clearer, more structured way.
    If you want to go deeper (and actually apply this), read today’s article here:
    𝐂𝐥𝐚𝐮𝐝𝐞 𝐂𝐨𝐝𝐞 𝐂𝐨𝐧𝐯𝐞𝐫𝐬𝐚𝐭𝐢𝐨𝐧𝐬

    At aijoe.ai, we build AI-powered systems like the ones discussed in this series.
    If you’re ready to turn an idea into a working application, we’d be glad to help.

    続きを読む 一部表示
    8 分
  • Why Does AI Code Work Until You Actually Use It?
    2026/11/08
    AI coding tools are very good at producing a feature that passes its demo. They are much worse at producing one that holds up under real data, real timing, and real users, and they report both outcomes with the same confidence. This episode names that gap the deadline hallucination: AI is optimized to close the request, so it gives you the happy path and calls it done. Builders under shipping pressure are now merging features that look finished and only break once real use reaches the paths nobody exercised.


    Produced by VoxCrea.AI

    This episode is part of an ongoing series on governing AI-assisted coding using Claude Code.

    👉 Each episode has a companion article — breaking down the key ideas in a clearer, more structured way.
    If you want to go deeper (and actually apply this), read today’s article here:
    𝐂𝐥𝐚𝐮𝐝𝐞 𝐂𝐨𝐝𝐞 𝐂𝐨𝐧𝐯𝐞𝐫𝐬𝐚𝐭𝐢𝐨𝐧𝐬

    At aijoe.ai, we build AI-powered systems like the ones discussed in this series.
    If you’re ready to turn an idea into a working application, we’d be glad to help.

    続きを読む 一部表示
    8 分