Unverified50% confidenceFactExact time
Anki is fully open-source and local-first, relies on the SM-2 spaced repetition algorithm, has an excellent reputation among medical students and language learners, but has a relatively high barrier to entry.
1
Sources
50%
Confidence
Long-term
Relevance
9/23/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedModern large model alignment training relies heavily on high-quality preference data pairs, with OpenAI's RLHF and RLAIF being representative examples61% similarUnverifiedOpenAI通过定期用新数据微调模型和提供联网搜索工具两种方式缓解训练数据截止的局限60% similarUnverifiedSWE-2 is post-trained on Kimi K3 and uses reinforcement learning (RL), optimizing along both the cost and capability dimensions simultaneously.59% similarUnverifiedThe learning path for local LLMs should progress step by step: from API calls, to running small open-source models locally, to fine-tuning, to optimizing inference performance.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/944348API
curl https://kongchang.com/api/v1/knowledge/claims/944348MCP
get_claim(id=944348)