LessWrong AI
2026-11-15 22:38 UTC
Score 80.0
USR-0152-20261115-community-fo-53045649
Full article
We found a shortcut in the TASTE benchmark : mech-interp-related proposals are generally scored lower. On the non-interp half, all tested models with ECI > 158 are below 50% on the rubric-only setup, with 8 of 14 significantly below (7 of them OpenAI). In particular, OpenAI models' scores seem to decrease with higher ECI (r = -0.74), suggesting a systematic bias. The shortcut The TASTE benchmark is a benchmark where models decide which of two AI-safety research proposals is preferred by domain experts [1] . In trying to understand the quality of the benchmark, we realized one recurring theme that the mech-interp-related proposals in there are quite bad. We therefore tested a simple baseline: compare the number of mech-interp related terms (without deduplication) on the two proposals, and pick the one with fewer such terms, coin flip on ties. Surprisingly, this shortcut is able to achieve a 63.0% overall accuracy, beating all the LLMs we tested [2] . The list of mech-interp related terms we use probe, probes, probed, probing, patch, patches, patched, patching, lens, SAE, SAEs, sparse autoencoder, sparse autoencoders, interpretability, attention head, attention heads, residual stream, residual streams, circuit, circuits, circuitry, logit, logits, activations, activation patching, activation steering, activation space, activation vector, activation vectors, activation addition, activation additions, steering vector, steering vectors, integrated gradients Analyzing the other hal…