Meta's new Wonder model praised for finding security bug other agents missed
alexandr_wang · x · 2026-10-13
Charlie Holtz shared hands-on impressions of Meta's new Wonder model, reposted with endorsement by Meta Chief AI Officer Alexandr Wang:
- Real security vulnerability: found a genuine vuln in his codebase in one shot that other agents missed
- Strong design & visualizations: likely thanks to the built-in /taste skill in the CLI (no gradients, consistent typography)
- Loves subagents and ships thoughtful CLI details: very fast, nice turn checklist, solid voice mode, well-crafted built-in skills — try /grill and /taste
Wang declared "Meta is now at the frontier" and called the progress super impressive.
More from coding & agent
- OpenAI publishes full Annotations extensibility docs for WebMCP agents — OpenAIDevs · 2026-10-13
- OpenAI ships WebMCP annotations to give browser agents richer page context — OpenAIDevs · 2026-10-13
- Anthropic explains Claude Code pitfall: PreToolUse hooks returning "allow" silently bypass the safety classifier — lydiahallie · 2026-10-13
- Anthropic now lets subscription use inside third-party agents built on Claude Agent SDK — lucasmeijer · 2026-10-13
- Simon Willison on Python 3.15: lazy imports, comprehension unpacking, sampling profiler — charliermarsh · 2026-10-13
- Cursor Composer predictions hit ~60% acceptance rate, users back to tab-tab-tab flow — rudrank · 2026-10-13