Dev Who Spent $8,000 on AI Subscriptions Quits: Coding Agents Are Just Bad Tools Piling Up Code Debt
ryunuck · x · 2026-09-21
A developer with 15 years of experience says he spent roughly $6,000–8,000 on Anthropic and OpenAI subscriptions last year, then canceled them all for good. His argument: coding agents are not just tools but bad tools — refactoring a codebase with an agent puts you back at square one because you have to explain every single type name. What agents actually solve, he says, is the easiest subset of software engineering: demo-able output that earns promotions and Twitter views while quietly piling up real code debt like a Jenga tower. His interlocutor countered that models will keep improving, so build clean, specific designs today; he replied that after a year of waiting, models got worse, not better.
More from coding & agent
- 9 practical Jev API recipes: browser agent flies through Google Flights in 7 seconds — alexcovo_eth · 2026-09-21
- Code review classification saves 122k tokens, author says even 10% savings is a free win — draginol · 2026-09-21
- Microsoft open-sources IQ Solution Accelerator unifying enterprise data, knowledge and decisions — adnan_hashmi · 2026-09-21
- Build an AI team around Claude: role-based subagents instead of one chat — Aiden_Tech_Ai · 2026-09-21
- Thorsten Ball: code review and unit tests will die in the AI era — zetalyrae · 2026-09-21
- "Fix It by 6am, No Mistakes": The Sleep-On-It Agent Prompt Gag — BLUECOW009 · 2026-09-21