Critique: Rolling Your Own but Using OpenAI APIs is Counterproductive
TejasKumar_ · x · 2026-08-26
The author argues in a reply that developers who claim to "roll their own" solutions (like CUA) but still rely on OpenAI's APIs and models underneath are acting foolishly.
Core Point:
- Brand & Privacy: Meta and Google are often viewed as privacy-violating surveillance companies, and OpenAI has a similar reputation.
- Contradiction: The purpose of rolling your own or choosing a more trustworthy alternative is often to avoid Big Tech privacy issues; relying on OpenAI internally negates those supposed privacy and branding benefits.
Related event: Developers debate why CUA adoption stalls: brand trust and DIY pitfalls(2 posts)→
More from coding & agent
- Veracode: AI now writes ~half of committed code, but security pass rate stuck at 56% — WeldPond · 2026-10-16
- Engineer: my job went from silently thinking at a computer to constantly talking to it — KevinNaughtonJr · 2026-10-16
- LangChain launches Managed Deep Agents: build production agents as a directory of files — hwchase17 · 2026-10-16
- Vercel Goes Full Backend: Python GA, Containers, and Daemons — cramforce · 2026-10-16
- WorldMemArena Accepted at NeurIPS: Memory Storage ≠ Memory Use — xwang_lk · 2026-10-16
- Vercel Ship Demos Container Deploys for Go, Ruby, Java and More — edwin · 2026-10-16