Unverified50% confidenceFactExact time
The focus of the research Perplexity published this time is the serving infrastructure around embedding and ranking models, rather than algorithmic model innovation.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/15/2026
First Seen
Valid until: 12/14/2026
Sources
Related Entities
Related Claims
UnverifiedAnthropic建议始终从最简单的方案开始构建代理式系统，只有当简单方案确实无法满足需求时才增加复杂性68% similarUnverifiedPerplexity does not develop its own underlying large models; instead, it builds its competitiveness by integrating third-party model APIs from OpenAI, Anthropic, Meta, and others, layered with a self-developed real-time retrieval-augmented generation (RAG) layer.66% similarUnverifiedThe real reason open-source large models underperform is often not model capability but systemic defects at the tool-calling layer, which Ahmad calls "Tool Confusion".66% similarUnverifiedThe author believes that the poor tool-calling performance of open-source models is in the vast majority of cases a problem with the framework, not a deficiency in the model's own capabilities.66% similarUnverifiedCritics point out that existing Responsible AI frameworks mostly focus on the attributes of the technical system itself, with insufficient attention to the upstream question of 'who defines the technological goals.'66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/922043API
curl https://kongchang.com/api/v1/knowledge/claims/922043MCP
get_claim(id=922043)