Dev's multi-model review skill finds Gemini hallucinates in over 80% of runs
theo · x · 2026-10-25
Developer theo built a "council skill" that reviews work with multiple models and found Gemini's hallucinations far worse than expected — fabricating content in over 80% of runs, earning it a dedicated "gemini the jester" section.
Repliers pushed back: one reported needle-in-haystack precision with practically unlimited context, suggesting usage patterns (like static vs dynamic links) may explain the gap.
Related event: Debate Erupts Over Gemini Hallucinations in Multi-Model Reviews(2 posts)→
More from Models
- OpenAI reportedly bans user for reverse-engineering his own TV, flagging it as 'cyber abuse' — deliprao · 2026-10-25
- Codex quota fix fully rolled out, user reports usage back from 17% — AIandDesign · 2026-10-25
- Dev trains a 4B coding model that can also generate 3D scenes — ConfidentDinner6648 · 2026-10-25
- DeepSeek may unlock consumer GPU matmul performance with memory-bandwidth-first architecture — teortaxesTex · 2026-10-25
- OpenAI keeps billing a suspended, unused workspace — cancel button unavailable, user fears $1k+ bill — tengisCC · 2026-10-25
- After 24 hours of testing, this dev's hill to die on: Kimi 3.1 is near AstrA — bookwormengr · 2026-10-25