Ex-TikTok ML engineer says JEV could reshape recommendation and search systems
FinanceYF5 · x · 2026-09-24
Huimin Xie, formerly a TikTok ML engineer, argues JEV could transform recommendation and search by bringing general semantic reasoning into discriminative inference: arbitrary context in, calibrated structured decisions out. In one case, JEV + Perfectly analyzed 500 ECCV 2026 researchers and their papers via complex queries, matching a Claude model's performance.
Related event: Ex-TikTok Engineer: JEV Could Reshape Recommendation and Search(2 posts)→
More from Models
- Users find Opus 5.5 has remarkably strong hearing, works via spectrograms — repligate · 2026-09-24
- GPT-6 Astra agent plays Left 4 Dead 2 in first real-time run — imjustnewatai · 2026-09-24
- Same Prompt, Opposite Results: GPT-4 Goes Silent 30/30 Where GPT-3.5 Never Stops — rayanpal_ · 2026-09-24
- Box says Opus 5.5 cuts token usage 63% and runs 30% faster than Opus 5 — bcherny · 2026-09-24
- Claude Opus 5.5 Max Tops Code Arena WebDev at 1818, Leading GPT-6 Astra by 26 — airesearch12 · 2026-09-24
- 36B Agent Model Runs Fully Local on Snapdragon X2 Elite With Just 32GB RAM — Kyrannio · 2026-09-24