Unverified50% confidenceFactExact time
The heuristic token count in context_ledger.py may differ from the real tokenizer by 15-20%.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedFor texts that are highly dependent on context and metaphor, traditional keyword retrieval or rule-based matching often fails, whereas LLMs can capture implicit semantic associations across large corpora.66% similarUnverifiedThe domain modeling skill now writes to glossary.md instead of context.md — this is a purely cosmetic filename change because context.md was too vague a name and its content had been trimmed down to just a glossary; users must update accordingly.64% similarUnverifiedApproximately 15–25% of the content in spontaneous speech consists of filler words, sentence repetitions, self-corrections, and other redundancies.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1071683API
curl https://kongchang.com/api/v1/knowledge/claims/1071683MCP
get_claim(id=1071683)