Coding Is Over. Get over It
A JPMorgan Chase engineer reflects on AI agents outpacing hand-coding, questioning ROI while predicting inference costs will become negligible.
A personal essay by a software engineer with 15+ years at JPMorgan Chase describes how AI coding agents now outperform him and have transformed his workflow. He argues AI ROI is unmeasurable, praises cheap small models such as GPT 5.6 Luna, and cites Claude Code head Boris Cherny's advice to discard AGENTS.md/Claude.md rule files. He contends coding is no longer scarce, worries entry-level jobs will be automated first, and predicts AI's bigger impact lies outside coding.
- AI usage is pervasive at JPMorgan Chase, with sane guardrails but unclear, unmeasured ROI.
- Cheap small models like GPT 5.6 Luna with max reasoning are surprisingly capable.
- Claude Code lead Boris Cherny advises deleting AGENTS.md/Claude.md files as models improve.
- Entry-level coding roles may be automated first; developers must skill up beyond writing code.
- Vendors
- JPMorgan ChaseAnthropic
- Products
- Claude CodeGPT 5.6 Luna
- AI models
- GPT 5.6 Luna
From the original article
5 min read at blog.pitermarx.com
I’m a software engineer at JPMorgan Chase. I have more than 15 years of experience in building software and I used to love it. These are my own observations, not the firm’s position.
By pitermarx · blog.pitermarx.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.