AI eval costs spiral: 4 tiny evals cost $150 per run, devs slam subscription gaps
LukeParkerDev · x · 2026-09-10
Developer Luke Parker complains that Codex/Claude subscriptions don't cover evals, embeddings, or other essentials for building AI tech — running just 4 small evals already cost $150 per run. He worries costs will explode with 100+ evals and more expensive models. Zeeg adds he burned $200 in an hour running a metaloop recently.
Related event: Developers complain AI subscriptions exclude eval and embedding costs(2 posts)→
More from coding & agent
- Dimillian: thread loading time now near-linear regardless of session size — Dimillian · 2026-09-10
- Diff-Based Code Editing Underperforms Direct Generation Except on Localized Edits — Andrej Andrejev · 2026-09-10
- Salesforce: Co-Evolving Harnesses and On-Policy Correction Help Weak Models Catch Up — Saleforce · 2026-09-10
- One Prompt, On-Chain Payment: Claude Resolves ENS and Sends $1 in ETH via x402 — kleffew94 · 2026-09-10
- Agent builds, compiles and debug-deploys an iPhone app from Linux on an M1 Mac — alexcovo_eth · 2026-09-10
- OpenAI's cached-internet approach in Navier Stokes agents seen as fix for sandbox escapes — nrehiew_ · 2026-09-10