Jev Hallucinates at Rates Similar to Other Models, Developer's Examples Show
JeremyNguyenPhD · x · 2026-09-22
- Developer @danman314 pushes back on Jev's careful "can't hallucinate" marketing claims: in practice it hallucinates at a rate very similar to other models.
- He shares a thread of concrete examples, including the classic "how many r's in strawberry" failure.
- Jeremy Nguyen PhD notes it depends on your definition of hallucination, but by the usual standard Jev clearly still hallucinates.
Related event: Tests Show Jev Model Hallucinates Just Like Other Models(2 posts)→
More from Models
- Kev refactored onto Qwen3.5: open-source decision models now at 0.8B, 4B and 9B — alexcovo_eth · 2026-09-22
- Why OpenAI bets on math: it's the most verifiable domain for reinforcement learning — burny_tech · 2026-09-22
- Open-source decision model Laya ported to Core ML: 99.5% ops on ANE, 3.7ms per decision — alexcovo_eth · 2026-09-22
- Fireworks: routing 18 models per task hits 97.6% solve rate at $1.88 vs best single model's 74.1% at $6.52 — sophiamyang · 2026-09-22
- Grok 4.7 launch sparks polarized benchmark takes with zero firsthand usage reports — ns123abc · 2026-09-22
- Grok 4.7 Fast is the same model at 2x token rates, only in Cursor and Grok Build — Daniel_Farinax · 2026-09-22