Follow-up on emotion-vector critique: does averaging five categories really remove negativity?
rgblong · x · 2026-10-09
rgblong continues questioning the pain/emotion-vector paper: even after contrasting the vector with the average of five disparate categories including 'negative emotion' and 'fear', does the vector truly cease being largely a negative-emotion vector? The follow-up probes whether the paper's contrast design is sufficient given that 80% of examples resemble plain negative emotion.
Related event: Researchers Challenge the 'Pain Axis' Paper as AI Welfare Debate Deepens(19 posts)→
More from Research
- Why AI doesn't actually read words: from BPE subwords to byte-level models like BLT and H-Net — jbhuang0604 · 2026-10-09
- NVIDIA details HSTU recommender inference stack with up to 5.93x lower latency — PyTorch · 2026-10-09
- Preprint: LLMs store numbers as curves and helices, but compute comparisons differently — tweetsatpreet · 2026-10-09
- Best model was cheapest: open-weights model ran 669 clinical decisions for 1.7 cents — antoine_chaffin · 2026-10-09
- Ofir Press Points to ExcelBench as the Right Scale for Benchmarking Coding Agents — OfirPress · 2026-10-09
- tangermeme, a genomic sequence-to-function modeling toolkit, published in Nature Methods — anshulkundaje · 2026-10-09