Prover-verifier loop with Carbon high + neon xhigh never converges, user reports
jasondeanlee · x · 2026-11-21
A user reports that running Carbon at high and neon at xhigh in a prover-verifier loop has "gone off the rails": the system keeps patching holes endlessly and can never finish. He also pushes back on claims that neon xhigh is a small model, asking what the best Gemini reasoning model is and what he should be using instead — a snapshot of real-world struggles with high-intensity agent configurations.
More from Models
- OpenAI's coding agents now finish 46% of 2-4 hour tasks fully unattended — AIFlow_ML · 2026-11-21
- Persimmon v0.1 Pro/Ultra doubles Multi-User Turing Test score to 48% — niloofar_mire · 2026-11-21
- OpenAI agents now finish 46% of 2-4 hour tasks autonomously, up from 23% — AIFlow_ML · 2026-11-21
- GPT-6.2 Astra review: stronger at math and economic modeling, now with Ultrafast — soumitrashukla9 · 2026-11-21
- Google launches first interactive Gemma 4 explainer teaching how LLMs work in the browser — DynamicWebPaige · 2026-11-21
- Persimmon built a safety framework from scratch for human-like user models — gharik · 2026-11-21