Applications
Still refuses to write sestinas for some reason, so I don't think all the rough edges are gone.
Ethan Mollick observes that an AI system (likely Claude or another large language model) still declines to write sestinas, suggesting that certain behavioral constraints or limitations persist despite
Ethan Mollick observes that an AI system (likely Claude or another large language model) still declines to write sestinas, suggesting that certain behavioral constraints or limitations persist despite refinements. This indicates ongoing challenges in removing all restrictions or "rough edges" from AI systems, even after training improvements.
Related
- I have found that asking for a sestina regularly triggers Opus 4.7's safety guardrails. The forbidden poetic form!
- (This is a big part of what was called emergence in earlier academic work on unexpected LLM ability gains)
- Not an unexpected jump in capability given trends, but a significant one.
- Anyhow, it would be awesome if this is a false alarm and we get increasingly powerful coding tools with no downside risk.
- Anyhow, its not bad. Just not the vibe level that the benchmarks might indicate. And, for a first re-entry into the frontier model space, gi…
Source: Ethan Mollick (X) | 2026-04-17