Unverified50% confidenceBenchmarkExact time
A GSM8K experiment checked into the repository uses a job flow of 72 sessions with hermes memory turned off, using Qwen3-32B to play the student persona and Qwen3-4B-Thinking as the policy model being trained.
1
Sources
50%
Confidence
Long-term
Relevance
10/2/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedHermes 负责工具调用、记忆管理和任务执行，连接的 LLM 负责推理和生成回答64% similarVerifiedLarge models do not have memory capability by default; a ChatMemory mechanism must be introduced to remember the content of past conversation turns.61% similarVerifiedQwen3 27B has thinking mode enabled by default, supports disabling thinking, and controls reasoning intensity via a Reasoning Effort parameter.61% similarUnverifiedThinking Machines Lab发布了一款规模达9750亿参数的开源权重大语言模型60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/966912API
curl https://kongchang.com/api/v1/knowledge/claims/966912MCP
get_claim(id=966912)