X Upgrades Stories Tab, but Jev AI Model Cluster Is Drowned in Spam Tweets
ivan_bezdomny · x · 2026-10-15
- The poster noticed X upgraded its Stories tab with better topic clustering, and the Jev decision model caught his interest.
- Per the screenshot: TypeSafe AI launched Jev on September 15, 2026, built by ex-OpenAI researcher Diogo Almeida — a decision model that scores structured options (yes/no, lists) with confidence levels, claiming to cut common coding-decision session costs from $6.42 to $2.00 (69% savings) by taking typed questions and never generating prose or code; an open-source clone JEV-35B is gaining traction on Hugging Face.
- The catch: most tweet clusters in Stories are spam — neither official announcements nor LLM community content.
Related event: X's Trending Stories Drowned in Spam as Developers Cry Foul(3 posts)→
More from Models
- StepFun releases Step-5-Preview: 600B/27B-active flagship with 1M context — ResearchCrafty1804 · 2026-10-15
- UltraBERT: open 150M/380M encoders with 32K context and an unusual dual-masking recipe — algo_diver · 2026-10-15
- DeepSeek V4.1 measures its own decode speed at 430-460 tok/s — then the claim falls apart — teortaxesTex · 2026-10-15
- OpenCode offers $60 of Gemini 4 Argon usage for $10 until Nov 30 — m4rkmc · 2026-10-15
- After losing 5 Claude accounts, one user's controlled tests show what actually triggers bans — jiayuan_jy · 2026-10-15
- Dev Says Jev Could Easily Detect X Tweet Spam, But X Hasn't Prioritized It — ivan_bezdomny · 2026-10-15