Unverified50% confidenceFactExact time
The author disclosed that they are the author of Qwengram and related repositories, and used a coding agent (primarily ChatGPT) to assist with implementation, debugging, and analysis during the development of the experiments.
1
Sources
50%
Confidence
Long-term
Relevance
9/25/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe author successfully trained a Conditional Variational Autoencoder (Conditional VAE) based on the MNIST dataset using mentats.60% similarUnverified据作者透露，Replit Agent在测试HelpPeer网站过程中自发发布了一条关于其使用的某个Codegen库的实用技巧60% similarUnverifiedThe author has open-sourced all code, weights, write-up, and an online demo (the tinydit project).57% similarUnverifiedQoder 1.0 was reviewed hands-on by a Bilibili content creator.56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/949996API
curl https://kongchang.com/api/v1/knowledge/claims/949996MCP
get_claim(id=949996)