New article asks whether LLMs are stuck seeing the past through a modern lens
_akpiper · x · 2026-07-28
- The post points to a research piece titled “Are LLMs Unstuck in Time?” with the subtitle that LLMs tend to view the past through a modern-looking glass.
- The article, by Samuel Greengard and dated Jul 27, 2026, appears to examine how language models represent historical context and whether they distort the past with present-day assumptions.
More from Research
- ProteinGym-LLM ranks Claude Opus 5 highest on a 217-task protein variant benchmark — LeoTZ03 · 2026-07-28
- A 2-hour AI podcast tackles multilingual models, alignment, and evaluation — simi_97k · 2026-07-28
- Kimi K3 used 51.2 million sandboxes across 1.5 million images — tarantulae · 2026-07-28
- Claude Opus 5 looks strongest in model-welfare tests, but may just be best at taking them — TheZvi · 2026-07-28
- Enterprise AI turns document permissions into the real security bottleneck — Frequent-Engine-9920 · 2026-07-28
- Google’s VGGRPO improves video generation with latent 4D geometry rewards — jiqizhixin · 2026-07-28