Critical Thinking: Even if labs hide reasoning, tool interfaces may re-expose it, since disabling explicit thinking while providing a deep_think tool can still induce internal-format CoT output.

A practical corollary to the trace exposure: hiding reasoning is not robust, because tool interfaces such as a deep_think tool can still induce internal-format chain-of-thought output even when explicit thinking is disabled. ✦ AI generated

AINews Twitter recap (attributed to @_can1357) · Latent Space · 2026-08-12 · original ↗

A practical corollary: even if labs hide reasoning, tool interfaces may re-expose it; @_can1357 notes that disabling explicit thinking while providing a deep_think tool can still induce internal-format CoT output.

Read full article ↗excerpt · fair-use quotation