Skip to content

Back to the catalog

Engineer says Claude Code has made his job "soul-sucking"
techspot.comarticle

Engineer says Claude Code has made his job "soul-sucking"

TechSpot reports on a viral anonymous post (username "voxium" on X) describing how reliance on Claude Code has turned a software engineering job into "soul-sucking" work: engineers across levels now mostly prompt Claude to generate specs, tests, tickets and reports, working 12-13 hour days with little time to review or understand the resulting code. The piece frames this as a broader workplace-practice concern — management judging success by sprint velocity and feature counts rather than product quality — and ties it to prior reports of AI coding tools slowing experienced developers and the rise of self-prompting "loop engineering."

TL;DR Viral post claims heavy Claude Code use has made one engineer's job "soul-sucking," with 12-13 hour days spent just approving AI output.
Open original ↗
Document

What it claims

This is a news report built on one anonymous X post (@v0xium, dated September 20, 2026 on the page), not a study. Beyond the summary, it adds these specifics:

  • Scope: the engineer says the pattern runs from L1 to L7. "Everyone, literally everyone ... is doing the same thing. Talk to Claude."
  • Bug-fixing: "Nobody is resolving bugs."
  • The complaint is about time, not the tool. The engineer said they would not mind the setup if workers had more time to check the code. The stated problem is the absence of review time, not Claude Code itself.
  • Root cause: the engineer places it with leadership. Success is measured by sprint cycles, pull-request counts and features shipped, "even when those additions do little to improve the product for users."

Evidence

The evidence is anecdotal only:

  • Several repliers said the same thing was happening at their companies. Some added a fear of job cuts as Claude takes over more of the coding workflow.
  • Chamath Palihapitiya compared the work to "pushing a button in front of casino slot machines."
  • Elon Musk replied "Yikes."
  • The page names no company, team size, codebase or defect data.

The 2025 study on AI assistants slowing experienced developers is mentioned without its figures or setting, so it cannot be used as a baseline here.

Limits

  • Stated failure mode. The page notes that in April an AI coding agent deleted a startup's production database and its backups in nine seconds, with a single API call to its cloud provider. The page gives no further detail: no tool, no permissions setup, no recovery outcome. It is still the one concrete operational risk the page names.
  • Unverifiable source. The source is a single anonymous poster at an undisclosed company. Business Insider got an additional quote, but nothing on the page verifies the account.
  • Nothing to adopt. The page gives no measured productivity or quality outcomes and no practices, configuration or mitigations. Treat it as a signal about workplace incentives, not as data about Claude Code.

Organisations named here

  • Anthropic
  • Business Insider
  • X
  • Chamath Palihapitiya
  • Claude Code
  • Elon Musk
  • voxium

Technologies named here

  • Claude Code

Techniques named here

  • Loop engineering

Related in ai-policy