The dialectics of AI coding: LLMs can't write prod code unsupervised — neither can humans
ShenRaphael · x · 2026-11-10
A viral thesis/antithesis/synthesis joke on the AI coding debate: THESIS — LLMs can't write prod code unsupervised (have you seen their outputs?); ANTITHESIS — LLMs can, or why the SWE layoff rumors?; SYNTHESIS — LLMs can't write prod code unsupervised, but neither can human SWEs (have you seen prod code?). A witty take on both model capability limits and real-world code quality.
More from coding & agent
- Dev discovers Claude Code created a fake virtual display on his Mac to build apps 24/7 — vincent_koc · 2026-11-10
- Agents build Lean models of every CPython 3.15.2 function, validated on 50,000+ generated inputs — ChrSzegedy · 2026-11-10
- 10 open-source repos that review your code with AI, from Alibaba to Anthropic — victor_explore · 2026-11-10
- SteerCamp's multi-agent crew holds daily standups, reporting progress and blockers like employees — pramodk73 · 2026-11-10
- Running Codex for two days to reimplement an outdated Android book's projects and retake screenshots — burkov · 2026-11-10
- Unverified: Fable 5.2 tops FrontierCode 2.0 at 49.1%, half the cost of Opus — FinanceYF5 · 2026-11-10