Unverified50% confidenceBenchmarkExact time
When using Ponytail 5, the proportion of high-risk logic shipped with tests reached 98% (vs. 68% without it), and the proportion of injected bugs caught by the agent's own tests was 66% (vs. 46% without it).
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/8/2026
First Seen
Valid until: 1/6/2027
Sources
Related Entities
Related Claims
UnverifiedA single "trusted source" prompt caused 7 out of 8 tested models to reverse between 45% and 88% of their correct answers.68% similarUnverifiedIn a test involving an unfamiliar game with no manual or rules, the previous generation of AI scored 7.8%, while GPT-6 achieved 99.9% under an agent framework that retains reasoning state.68% similarUnverified在漏洞检测基准测试中，让最新模型运行五次，只有50%的漏洞被稳定发现，相比确定性检查工具LLM只发现75%的问题，F1分数仅为40%67% similarUnverifiedPercentile metrics (such as P75 and P95) reveal the poor experiences of long-tail users more effectively than averages.66% similarUnverifiedOn Qwen3-4B, the behavioral test yielded a faithfulness score of 88.2%, which is 11.4 percentage points higher than the causally measured 76.9%.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/987642API
curl https://kongchang.com/api/v1/knowledge/claims/987642MCP
get_claim(id=987642)