Frontier models are hallucinating less about biology, but using terms more loosely
owl_posting · x · 2026-07-26
The author argues that frontier models now mostly stop hallucinating on biological concepts, but have shifted to a subtler failure mode: using terminology loosely in ways that support whatever point they want to make.
He calls it oddly human, suggesting that while factual mistakes may be improving, rhetorical slippage remains.
Related event: Frontier Models Reduce Biological Hallucinations but Misuse Terminology(2 posts)→
More from Models
- OpenAI’s “5.6 Pro” is said to beat Fable 5 on math-heavy rebuttal work — MParakhin · 2026-07-26
- Claude keeps defending Opus 5 instead of writing a critical review — sethlazar · 2026-07-26
- Unsloth’s Qwen3.6-35B-A3B GGUF is trending on Hugging Face — unsloth · 2026-07-26
- SOOFI may still only be tying Nemotron 3 Nano despite 2T extra tokens — JJitsev · 2026-07-26
- A simple “ask clarifying questions first” prompt gets Claude to surface missing assumptions — Commercial-Most3081 · 2026-07-26
- User says Claude Opus 5 feels more forgiving and “common-sense” than GPT-5.6 Sol — dejavucoder · 2026-07-26