Unverified50% confidenceFactExact time
In the methods table, the "no tools, pure raw numbers" setting appears in only three experiments, involving networks ranging from 17,000 to 172,000 weights.
1
Sources
50%
Confidence
Long-term
Relevance
11/4/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe research team trained a series of decoder-only architecture models from scratch, with parameter scales ranging from 47 million to 349 million.63% similarUnverifiedThe 6.3-million-parameter network is only about the size of an early convolutional classification model.63% similarUnverifiedThe 4-billion-parameter version of Qwen 3.5, with no external tools and with exact calculation required at each step, got only 22 of 40 multi-digit multiplication problems correct.62% similarUnverifiedThe post mentions that the lab does not have enough data to build foundation models, and the data scale is very small.62% similarUnverifiedOpenAI's published blog posts only tested up to around 16 agents and did not push experiments to a scale of ten thousand agents.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1135383API
curl https://kongchang.com/api/v1/knowledge/claims/1135383MCP
get_claim(id=1135383)