Anthropic cut Opus 5.5 prices, then broke four things your agent depends on
rseroter · x · 2026-09-24
Anthropic made Opus 5.5 cheaper, but as The New Stack reports, the update broke four behaviors that production agents rely on. The author stresses this isn't Anthropic-specific: model vendors routinely toggle capabilities on and off between releases, so agent developers should treat model upgrades with mandatory behavior regression checks before deploying. Casey also wrote about the same issue.
More from coding & agent
- 30 lines of JavaScript, no image models: pure-code generative art demo — nc_frey · 2026-09-24
- TRACES: A New Benchmark That Grades AI Problem-Solving Process, Not Just Correct Answers — dr_cintas · 2026-09-24
- Dev reverse-engineers Qwen Image 2.1 PE, ships ComfyUI node that auto-computes dimensions — BleynSpecnaz · 2026-09-24
- Cua Releases Cua-S1-4B, First Multimodal Decision Model RL-Trained on Live Computer-Use Tasks — multimodalart · 2026-09-24
- Applied Compute uses Jev to auto-cluster failure modes in RL training traces — rhythmrg · 2026-09-24
- Four Steps to Stop Opus 5.5 from Wasting Tokens, From a Real User — dr_cintas · 2026-09-24