Antirez says Laguna S2.1 cannot write correct Italian via the official API
antirez · x · 2026-07-23
Antirez says Laguna S2.1 is completely unable to write correct Italian, even though much smaller models handle the task well.
He says this is a red flag for the model, notes the issue is tied to specialization, and adds that he verified the behavior through the official API via OpenRouter after seeing it with Q4 quants.
More from Models
- Kimi K3.1 Pro tops MathArena open models, closing frontier gap to about 6 months — teortaxesTex · 2026-10-26
- Ruff creator Charlie Marsh: frontier models find infinite bugs in any software — charliermarsh · 2026-10-26
- Dev testing one skill across Opus 5.5 and Sol 6.1 finds instruction following 'all over the map' — lucasmeijer · 2026-10-26
- supermemory unveils learner-1, claiming continual learning for any model — julianweisser · 2026-10-26
- Anthropic says Opus 5.5 cuts cost per task by ~40% vs Opus 5 — taufiqintech · 2026-10-26
- AI search APIs ranked: top 12 within 7 points, yet prices differ nearly 7x — FinanceYF5 · 2026-10-26