A study of reasoning models with fixed weights found that extra thinking time changes how models handle everyday scalar inferences such as reading "some students passed" as meaning not all did, according to the paper's authors. The research holds model weights constant while varying how long a model thinks before answering, examining what additional reasoning does to these pragmatic inferences.
When a speaker says ``some students passed'', listeners infer that not all of them did. Reasoning models now let users decide how long a model thinks before it answers, but we do not know what extra thinking does to such everyday inferences. We study this directly: we keep a model's weights fixed, c
EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.