Unverified50% confidenceFactExact time
The developer trained a single policy from scratch in MuJoCo to solve the 2D ragdoll getting-up task, and in 160 tests it succeeded in getting up 0 times.
1
Sources
50%
Confidence
Long-term
Relevance
10/31/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedPilot experiments had three coding agents and eight models each run eight 20-minute single-pass tasks, with label-aware F1 showing extremely high variance ranging from 0.143 to 0.892.64% similarUnverifiedThe developer ran 1932 test runs, using 100 realistic tools (including deliberately confusable tools such as pdf_compress, pdf_optimize, image_compress), with tool counts in 8 tiers from 5 to 100, running each condition twice, testing 18 tasks (including 10 ambiguous tasks).63% similarUnverifiedThe project's policy was trained from scratch using mjlab (a MuJoCo wrapper tool) and converged in approximately 4 hours on a single RTX 3080.63% similarUnverifiedAfter RL training, the small model successfully completes 16 out of 24 tasks, whereas before RL it could not successfully complete any tasks.62% similarUnverifiedA long-horizon programming agent built an entire Minecraft clone almost entirely from scratch through code, comprising approximately 100,000 lines of game code, 26,000 lines of test code, 1,000 automated tests, and 775 files, with a cumulative working time of approximately 25 hours.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1120963API
curl https://kongchang.com/api/v1/knowledge/claims/1120963MCP
get_claim(id=1120963)