New embedding approach loses on benchmarks but beats SAE-based ones qualitatively
mayfer · x · 2026-10-23
mayfer shares that an embedding approach he's experimenting with loses to SOTA embedding search models on benchmarks, yet works notably better than sparse-autoencoder-based embeddings he tried before — and its qualitatively different nature makes it worth pursuing.
More from Research
- PoML consensus protocol replaces hash mining with useful LLM inference, paper claims Bitcoin-grade security — chaumian · 2026-10-23
- Microsoft's step-by-step AI diagnosis research lands Science cover — erichorvitz · 2026-10-23
- ADMET-EvO: a 7-step evidence-gated architecture for self-evolving AI agents — MaryamMiradi · 2026-10-23
- Sasha Rush's three laws of 'Vibed ML' papers poke fun at theory-after-hack culture — srush_nlp · 2026-10-23
- KEEP-Bench tests whether context compression preserves the evidence QA evals miss — kaiwei_chang · 2026-10-23
- Martingale Posterior Cox Processes: GPU-friendly Bayesian intensity estimation at a fraction of the cost — chaumian · 2026-10-23