Unverified50% confidenceFactExact time
The State of AI Report 2026 shows that Claude guided about 26% of the research directions in Anthropic's core model R&D, while in February 2026 this figure was still less than 1%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/16/2026
First Seen
Valid until: 1/14/2027
Sources
Related Entities
Related Claims
UnverifiedAnthropic published "Towards Monosemanticity" in 2023 and "Scaling and evaluating sparse autoencoders" in 2024, with researchers using SAEs to identify millions of interpretable features in models such as Claude.67% similarUnverifiedIn 2024, Anthropic successfully decomposed millions of interpretable features in the Claude model using sparse autoencoders (SAE).66% similarUnverifiedAnthropic introduced tool_use capability for the Claude model in 2024.66% similarUnverifiedAnthropic published a paper in 2024 demonstrating how to locate neuron groups related to concepts such as 'honesty' and 'harm recognition' in the Claude model, and how intervening in these neurons can alter model behavior.62% similarVerifiedAnthropic published mechanistic interpretability research on the internal feature interpretation of Claude in 2024, discovering millions of interpretable feature units.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1049348API
curl https://kongchang.com/api/v1/knowledge/claims/1049348MCP
get_claim(id=1049348)