Marco Pavone(@drmapavone):Our latest finding: scaling self-verification can make open-weight models significantly more capable at a fraction of the cost. With DeepSeek V4 Flash, sampling just 5 candidate solutions and using the same model to rank them with LLM-as-a-Verifier improves Terminal-Bench 2.1 accuracy from 79% → 88%—outperforming Claude Fable 5 while costing 11× less. 💰 As open-weight models become more capable, we can generate many high-quality candidate solutions and verify them at very low cost. Try it out: https://t.co/ZNDWOl7Dmc More on verification scaling in @jackyk02's previous post: https://t.co/ZxBfEVMbwD @StanfordAILab @StanfordEng

2026.08.18 19:30

Our latest finding: scaling self-verification can make open-weight models significantly more capable at a fraction of the cost. With DeepSeek V4 Flash, sampling just 5 candidate solutions and using the same model to rank them with LLM-as-a-Verifier improves Terminal-Bench 2.1 accuracy from 79% → 88%—outperforming Claude Fable 5 while costing 11× less. 💰 As open-weight models become more capable, we can generate many high-quality candidate solutions and verify them at very low cost. Try it out: More on verification scaling in @jackyk02's previous post: @StanfordAILab @StanfordEng

Jacky Kwok@jackyk02

2026.07.08 21:32

How can we extract richer signals from AI Feedback? Introducing LLM-as-a-Verifier✨— a simple verification scaling framework that achieves SOTA on agentic benchmarks 🚀 The key idea: - Use fine-grained scoring granularity (e.g., 1-20 instead of the standard 1-5 scale) - Take the expectation over the full logprob distribution of score tokens - Scale repeated evaluation and criteria decomposition You can use these fine-grained signals for more effective test-time scaling, RL, and agent monitoring! It achieves SOTA across Terminal-Bench V2, SWE-Bench Verified, RoboRewardBench, and MedAgentBench 👑 Advised by @Azaliamirh @istoica05 @drmapavone @chelseabfinn 🧵👇