Models resemble each other because pre-training is the same everywhere; what differentiates labs now is RL and post-training.

Added to korrents 7 Sept 2026 · How quotes work · Something wrong? Tell us

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

• 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
• Reinforcement learning from verifiable rewards does not reliably carry a model's pretrained ethical understanding into its actual behavior. SHSamuel Hammond11 Aug 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
• A verifiable task can be optimised by reinforcement learning until a neural network performs it extremely well. AKAndrej Karpathy17 Nov 2025reinforcement learning

See this claim on the map