Dev Radar
Support
LiveUpdated 2026-11-03 18:52 UTC

a local model on one GPU read a 2009 SIGGRAPH paper, grew its trees in 28 minutes, then…

a local model on one GPU read a 2009 SIGGRAPH paper, grew its trees in 28 minutes, then checked the paper's lambda…

This is a dev post classified by AGK Intelligence as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.

a local model on one GPU read a 2009 SIGGRAPH paper, grew its trees in 28 minutes, then checked the paper's lambda experiment on its own code and got the paper's answer. 2 of 2 takes passed: - lambda 0.46: 70.3 wide, 71.8 tall - lambda 0.56: 51.7 wide, 136.0 tall lambda sets how much growth goes to the trunk instead of the side branches. more lambda gives a taller, narrower tree, as the paper shows. Qwen3.8-27B Q6_K in Hermes Agent goal mode, one RTX 5090. the model was told the paper's claim and asked to check it, so this is not a blind reproduction. full report: https://github.com/notwit

Posted by witcheer (23.2k followers) 1 h ago · 14 likes · 863 views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: llm-bench-rig.

More dev work like this

Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.3k posts from 5k X accounts over the last 21 days, 9.2k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-03 18:52 UTC. Full method.