Longer test-time thinking improves an AI model's robustness to adversarial or unusual inputs.

Added to korrents 1 May 2025 · How quotes work · Something wrong? Tell us

Related korrents

Our reading — they may agree, disagree or merely touch the same thing. Closest first: a shared subject counts for most, then how near the wording is.

• Learned approximations of slow simulators change what science is possible, by turning a six-month screening run into something you do over lunch. JDJeff Dean30 Jul 2026similar wordingChief Scientist at Google DeepMind and Google Research
• Spending compute at inference time to search over plausible solutions is the general fix for unreliable long agent runs. JDJeff Dean30 Jul 2026similar wording
• Higher-perplexity adversarial attack text is easier to detect and mitigate. LWLilian Weng25 Oct 2023similar wordingMachine-learning researcher
• Raising inference-time reasoning effort on a smaller model can match the performance of a larger model run at lower effort. SRSebastian Raschka18 Jul 2026similar wordingAI research engineer working on large language models
• There will be no overnight intelligence explosion, because a model's best work takes so much test-time compute that time itself is the bottleneck. NBNoam Brown26 Jun 2026similar wordingResearch scientist at OpenAI

On the map

Open the map on its own page →