Research10d ago
Humans Score 100% While GPT-5.6-Sol Hits Only 17%: RoTA-Bench Exposes 3D Interactive Control Gaps, and OpenSAE Pairwise Steering Lifts Fidelity to 0.779
Two top-trending Hugging Face papers dissect the limits of VLM 3D interactive reasoning and LLM mechanistic interpretability: Xiamen University's RoTA-Bench (arXiv:2610.17665, 200 upvotes) evaluates closed-loop 3D-to-2D projection alignment across 674 tasks, finding that humans achieve 100% success while GPT-5.6-Sol reaches only 17%. Meanwhile, UW-Madison's OpenSAE study (arXiv:2610.21261, 104 upvotes) introduces SAE Additivity Residuals (SAR) across 18 model/behavior settings, showing that modeling pairwise feature interactions boosts multi-feature steering rank fidelity from 0.5874 to 0.7790 and cuts ordering error from 0.1444 to 0.0606.
Coding11d ago
PreciseCoder: Augmenting Unit-Test RL with Localized Semantic Rewards Cuts Code Edits from 7–15 Lines to 3 and Boosts GPT-5.6 Sol Precision
While reinforcement learning from unit tests raises code pass rates, researchers discover it inadvertently teaches models to over-edit and hallucinate bugs in already-correct code. PreciseCoder augments unit-test rewards with a semantically verified localized edit signal. Across 4B, 9B, and 27B models, PreciseCoder slashes average edit lines from 7–15 down to 3 at equal pass rates, generalizes from single-line training to repository-level repair, and transfers 9B reasoning traces to boost GPT-5.6 Sol and Qwen3.8-Max edit precision by 4.6–12.4 points without retraining.
Pricing46d ago
GitHub Copilot: GPT-5.6 Sol 30% off for Pro+ and Max until Sep 13 UTC
GitHub is offering GPT-5.6 Sol at 30% off inside Copilot for Pro+ and Max subscribers. The promo ends September 13, 2026 at 00:00 UTC, cutting short-window Sol usage cost for heavy coding-agent users.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.