Revision History
Jev (AI model) · 5 revisions
Sizes are character counts of the article source. The signed number is the change from the previous revision.
Recent edit summaries
Detailed summaries recorded by editors. Generic maintenance summaries are omitted here; every recorded revision remains below. Dates describe the edit, not necessarily the event it covers.
- Update: add Intern-Decision (Shanghai AI Laboratory, 26 September 2026), an open-weight Jev-compatible model that benchmarks against Jev
Version 5 · Sep 30, 2026, 07:18 AM
- Verification fixes: context-rot statements reconciled; lead notes 20 Sep general availability
Version 4 · Sep 23, 2026, 07:51 AM
- Freshness pass: waitlist removal and demand, current model ID and context limits, documented limitations (jaggedness page, prompt-injection sensitivity), developer and Vercel adoption, TechCrunch architecture reporting
Version 3 · Sep 23, 2026, 07:32 AM
- Correction: on TypeSafe's customer-service workflow three models score above Jev (GPT-5.6 Sol, DeepSeek V4-Flash and V4-Pro), not two; the evals site's 'every model is more accurate, cheaper and faster in the workflow' claim is an average across four tasks with per-workflow exceptions. Minor: 11 Sep post was four days before launch; 150 ms appears in TypeSafe's own docs; Noul answers carry no confidence score
Version 2 · Sep 16, 2026, 03:14 PM