Anecdote◆Article

GPT-5's Auto mode, which tried to automatically select reasoning effort, largely failed in practice and was quietly removed from the UI.

Raschka notes that automatic effort selection is still an unsolved problem, citing GPT-5's Auto mode as an example that was mostly a miss and got pulled from the interface. ✦ AI generated

Sebastian Raschka · Ahead of AI · 2026-07-18 · original ↗

Share card ↓Export .md Export .txt

We saw this a while back with GPT 5's Auto mode. It's a tricky problem to solve, and in the end, the implementation was probably more miss than hit, which is why it got removed from the UI (at least, I can't find it anymore).

Read full article ↗excerpt · fair-use quotation

✳ Auto mode ✳ GPT-5

Related moments

Data◆Article · 64 words

In a third-party Trajectory Labs evaluation of 72 held-out indirect prompt injection scenarios across the latest Claude Code and Codex versions, none of the 720 attack attempts succeeded against Claude Fable 5, Opus 5, or Sonnet 5 running auto mode.

The article author · Simon Willison's Weblog

MechanismVideo · 27:38 · 2m

A core, still-unsolved trade-off in building GPT-5 is between how long the model reasons (reasoning tokens/thinking time) and response latency versus intelligence — models get dramatically smarter given more inference time, which conflicts with product needs for fast responses.

Sherwin Wu · BG2 Pod

ClaimArticle · 43 words

Auto mode is a better solution than asking humans to constantly approve actions, because confirmation fatigue makes human approval clearly unsafe.

The article author · Simon Willison's Weblog