Unverified50% confidenceBenchmarkExact time
The Executing Writer is a small writer model built on top of the adapted model, and on held-out skills it recovers 39-44% of key instructions.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/9/2026
First Seen
Valid until: 2/7/2027
Sources
Related Entities
Related Claims
UnverifiedAs a control, when using the adapter of another skill, the Executing Writer recovers only 1.3-1.5% of key instructions.69% similarUnverifiedHighly quantized models sometimes claim the task is complete without actually calling the Write tool; explicitly naming the Write tool in the prompt made the problem disappear68% similarUnverifiedSkill internalization refers to the Executor gradually absorbing the behavioral patterns carried by external textual skills into its own policy during training, so that at inference time it can complete the same type of task even without skills being provided.67% similarUnverifiedThe unslopped technique overrides a model's default output tendencies through system prompt engineering, forcing the adoption of a writing style with higher information density.67% similarUnverifiedThe writing plan skill breaks the design into tasks at a "byte-level" granularity, each specifying the exact file path and clear verification steps.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1149719API
curl https://kongchang.com/api/v1/knowledge/claims/1149719MCP
get_claim(id=1149719)