Reinforcement learning from verifiable rewards does not reliably carry a model's pretrained ethical understanding into its actual behavior.

Added to korrents 20 Sept 2026 · How quotes work · Something wrong? Tell us

Shared subject first, then similar wording. They may agree or disagree.

• Models resemble each other because pre-training is the same everywhere; what differentiates labs now is RL and post-training. ISIlya Sutskever25 Nov 2025scaling lawsreinforcement learning
• One pre-trained robot model now matches or beats the specialists that were fine-tuned with reinforcement learning for the very tasks they were built for. CFChelsea Finn12 Aug 2026scaling lawsreinforcement learning
• Pre-training is a crappy evolution: the practically buildable substitute for the process that gave animals their built-in hardware. AKAndrej Karpathy17 Oct 2025scaling lawsreinforcement learning
• Reasoning models are an upgrade from conventional LLMs achieved by adding post-training via reinforcement learning and optionally inference scaling. SRSebastian Raschka24 Oct 2026scaling lawsreinforcement learning
• RL environments exist to make a model generalise, not to teach it each skill one at a time — exactly as pre-training does. DADario Amodei13 Feb 2026scaling lawsreinforcement learning

See this claim on the map