User suspects OpenAI's "Approve for me" feature is behind recent token-draining spike
ssh4net · x · 2026-10-22
User ssh4net noticed abnormal token consumption after enabling OpenAI's "Approve for me" feature almost everywhere — following OpenAI's promises to stop draining tokens — and suspects the feature may be the culprit behind last week's usage spikes.
The claim points at a billing transparency problem with OpenAI's agent features: if auto-approval silently inflates usage, users can't audit their costs. No official response yet; unverified.
More from Models
- Recursive's 40B open model Flint ran 732 auto-experiments to improve NanoChat, nearing Claude Haiku 4.5 — cong_ml · 2026-10-22
- Whatever happened to the Yi family of LLMs? Nostalgia for 01.AI's models — code_star · 2026-10-22
- Researcher uses Grok to surface 227 suspected UAE bot accounts overnight — FlorianGallwitz · 2026-10-22
- unsloth ships GGUF quantizations of RecursiveSI/flint on Hugging Face — unsloth · 2026-10-22
- Generalist AI's GEN-1.5 puck-packing bot shows emergent physical reasoning and backtracking — chris_j_paxton · 2026-10-22
- Dev names Kimi K2 his favorite LLM: won't sycophantically agree, may outcode Sonnet 4 — gnukeith · 2026-10-22