Unverified50% confidenceFactExact time
In a simple test, GPT-6 Astra accurately identified which arcade game each of four small networks corresponded to based solely on the raw weights, without running any of these networks throughout.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/4/2026
First Seen
Valid until: 2/2/2027
Sources
Related Entities
Related Claims
UnverifiedThe researchers gave 17,253 weights to GPT-6 Astra, and all four networks were correctly identified as their corresponding games.80% similarUnverifiedGPT-6 Astra can determine what task a network was trained to perform simply by looking at its raw weights.79% similarUnverifiedWithout any environment feedback, GPT-6 Astra can write small game networks from scratch, and these networks outperform networks trained with PPO for 100 million steps.78% similarVerifiedUnder the medium-intensity setting of the Agents' Last Exam benchmark, GPT-6.1 Terra's score is on par with GPT-6 Astra.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1135778API
curl https://kongchang.com/api/v1/knowledge/claims/1135778MCP
get_claim(id=1135778)