Unverified50% confidenceFactExact time
In October, 97% to 98% of subagent tokens ran on Opus; from late September to early October, 59% to 80% of subagents had no model specified at all.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/18/2026
First Seen
Valid until: 11/1/2026
Sources
Related Entities
Related Claims
UnverifiedIn tasks with propositional constraints, the proportion of models integrating candidates already verified as invalid is as high as 93%–100%.62% similarUnverifiedWhen techniques are explicitly specified, 93% of model proposals avoid clichés, but when only moments are given, that proportion drops to 75%–82%, indicating that models revert to the most formulaic approaches when left to their own devices.57% similarUnverifiedAccording to Sonar research, 96% of people do not fully trust AI-generated code, yet only about half always verify it before submission.55% similarUnverifiedThe task success rate of mainstream AI generation APIs is typically between 92% and 98%, meaning 2–8 out of every 100 tasks may fail.55% similarUnverifiedRanked by question difficulty, persistence rate was 91.4% on the 60 questions that all models answered correctly, but only 73.5% on the 52 questions that at least one model got wrong, indicating that sycophancy tracks uncertainty.55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1057489API
curl https://kongchang.com/api/v1/knowledge/claims/1057489MCP
get_claim(id=1057489)