Unverified50% confidenceOpinionExact time
The creator stated that the LMWiki project, from setting up the development environment to final completion, involved a total of 10 rounds of professional prompts to DeepSeek Harness, and the development process was exceptionally stable and highly efficient, with his personal assessment surpassing the development experience of Codex and Cloud Code.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/16/2026
First Seen
Valid until: 10/30/2026
Sources
Related Entities
Related Claims
UnverifiedThe LMWiki knowledge base has officially launched on the team's self-developed DeepSeek Harness Studio desktop client, usable with a single click; the full set of learning materials (installation package, project source code, Agent preset, development knowledge base, Skills and architecture diagrams, round-by-round prompts, conversation run screenshots, and phased results screenshots) has been released to the relevant community.67% similarUnverifiedThe UP host believes that DeepSeek Harness is more targeted in its optimization for DeepSeek models than Claude Code.65% similarUnverifiedDeepSeek Harness was used in nearly eight practical projects, covering directions such as automated development of LMVK-type projects, automated Skill generation, and e-commerce multimodal Agents.64% similarUnverifiedThe insight this experiment offers to developers who want to build DeepSeek Harness plugins is: decouple the unstable system under test from the stable scheduling system, use a persistent task ledger to maintain the closed loop, and use isolated instances for validation.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1042992API
curl https://kongchang.com/api/v1/knowledge/claims/1042992MCP
get_claim(id=1042992)