Claim◆Article

Running LLM against reasoning models now displays their reasoning traces to standard error, keeping them separate from standard output that may be piped to other tools.

LLM 0.32 makes model reasoning visible by default on stderr, with a -R flag to suppress it, keeping stdout clean for tooling pipelines. ✦ AI generated

Simon Willison · Simon Willison's Weblog · 2026-08-04 · original ↗

Share card ↓Export .md Export .txt

Running LLM against reasoning models now displays their reasoning traces to standard error, so you can see what they are "thinking" without that information being included in the standard output that you might pipe to another tool. Add -R/--hide-reasoning to turn this off.

Read full article ↗excerpt · fair-use quotation

✳ LLM

Related moments

Claim◆Audio · 4:54 · 2m

The same principles that make developer experience good — self-provisioning infrastructure defined in code rather than YAML, with fast feedback loops — apply equally to agent experience, since an agent benefits even more than a human from not having to parse hundreds of untyped Kubernetes config files.

Akshat Bubna · Latent Space

Data◆Article · 39 words

FTPO (Final Token Preference Optimization) training, branded Antidoom, sharply cuts doom-loop rates in small reasoning models: LFM2.5-2.6B falls from 10.2% to 1.4% and Qwen3.5-4B falls from 22.9% to 1% under greedy sampling, alongside downstream eval gains.

Liquid AI · Latent Space

Claim◆Video · 29:32 · 2m

By any definition used 20 or more years ago, we have already achieved artificial general intelligence, even though it hasn't been fully deployed yet.

Jason Calacanis · All-In Podcast