Zvi on Opus 5.5 System Card: Failure Modes Are 'Largely Avoidable' via Prompting and Harness
TheZvi · x · 2026-09-23
Zvi shares common failure patterns from the Opus 5.5 system card and argues they are largely a skill issue: the main failure modes appear avoidable through better prompting and harness design, rather than being hard capability limits of the model.
More from coding & agent
- Pigment Agents now reads and posts in Slack, inheriting user permissions — mattturck · 2026-11-12
- Map of the agent economy: 50+ startups across payments, spend control, identity, memory — venturetwins · 2026-11-12
- OpenCode launches Browse, an on-device browser agent with local logins — Saul_Loveman · 2026-11-12
- VentureTwins maps the B2A economy: dozens of agent infra and app companies in first series installment — venturetwins · 2026-11-12
- Google releases 76-page 'Agents Companion' whitepaper on agent engineering — mdancho84 · 2026-11-12
- Spinning up containers for 20-line agent tools is backwards: Safescript compiles provable, 50ms-deploy apps — uriwa · 2026-11-12