Why Newer Anthropic Models Are Worse at Third-Party Coding Tools
Anthropic's newest Claude models hallucinate extra fields when calling third-party tools like Pi because their post-training now mimics Claude Code's schema.
Tag
Anthropic's newest Claude models hallucinate extra fields when calling third-party tools like Pi because their post-training now mimics Claude Code's schema.
Which local models can actually use tools, call functions, and run multi-step workflows? Function-calling and TAU-bench picks from 8GB to 32GB VRAM.