Input token capping bug caused miscalculated OpenClaw numbers, retest planned
vincent_koc · x · 2026-11-06
vincentkoc shares an update: the team found an input token capping bug in the code that caused miscalculations in certain scenarios, making the numbers look worse than they are. A retest will be requested once the issue is fixed—key progress in the disputed OpenClaw trace analysis.
More from Models
- Kimi K3.1 Pro lands on Microsoft Foundry with 1M-token context for agentic work — DanWahlin · 2026-11-07
- Ripple 65B Preview vs Qwen 3.8 coding benchmarks: 79.1 on SWE-Bench Pro — Nota_ReAlperson · 2026-11-07
- Bittensor subnet model tops respected independent leaderboard just ~30 days after launch — airesearch12 · 2026-11-07
- Meituan's LongCat-2.5 multimodal model free for a week on Nous Portal — alexcovo_eth · 2026-11-07
- 8 Types of LLMs Powering AI Agents, from GPT Backbones to LAM Action Models — mdancho84 · 2026-11-07
- ChatGPT Images 2.6 vs Nano Banana 2.1: 4B weekly images vs a 50% price cut — Aiden_Tech_Ai · 2026-11-07