Burkov on Sonnet 5.5 High: 'crazy how fast it is' for code questions
burkov · x · 2026-09-29
ML author Andriy Burkov shared early hands-on impressions of asking code questions and bugs to Sonnet 5.5 at High effort: it is 'crazy how fast' — the fastest he has ever experienced. A first-person reaction without concrete benchmarks or detailed use cases.
Related event: Burkov Tests Sonnet 5.5 High Effort: Bug Fixes 5x Faster(2 posts)→
More from Models
- Is Anthropic 'really back'? User urges running Opus 5.5 + Sonnet 5.5 swarms — IndraVahan · 2026-09-29
- A week with Sonnet 5.5: ask it for ideas and it builds the thing instead — every · 2026-09-29
- Aether AI releases 16B CausalWM, a world model that reasons about causality before generating future frames — jiqizhixin · 2026-09-29
- Early Sonnet 5.5 impressions: ~5x faster bug fixes at high effort — burkov · 2026-09-29
- Why 4o feels different: thread argues native omni training, not capability, shapes model personality — RileyRalmuto · 2026-09-29
- Sonnet 5.5 effort settings make no difference in 15-task coding test: 9/15 at low, medium and high — every · 2026-09-29